Skip to content

xonevn-ai/XoneAI

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Β 

History

14 Commits
.github
.github
Β 
Β 
docker
docker
Β 
Β 
examples
examples
Β 
Β 
src
src
Β 
Β 
.cursorrules
.cursorrules
Β 
Β 
.gitignore
.gitignore
Β 
Β 
.pre-commit-config.yaml
.pre-commit-config.yaml
Β 
Β 
.windsurfrules
.windsurfrules
Β 
Β 
CLAUDE.md
CLAUDE.md
Β 
Β 
LICENSE
LICENSE
Β 
Β 
README.md
README.md
Β 
Β 
XONE.md
XONE.md
Β 
Β 
api.md
api.md
Β 
Β 
xoneai_cli_guide.md
xoneai_cli_guide.md
Β 
Β 

Repository files navigation

XoneAI Logo

Total Downloads Latest Stable Version License MCP Registry

XoneAI is a production-ready Multi-AI Agents framework with self-reflection, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code solution to streamline the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.

Xone AI

A brand-new AI Agents framework based on PraisonAI.
This is our first revision, intended to learn how it works and kick-start our framework. We appreciate the original creator. We simply want to create our own version and maintain it going forward. The original license belongs to PraisonAI. We will do our best to contribute back to the community and the project as much as possible.

---

Quick Paths:

πŸ“‘ Table of Contents

Getting Started
Python SDK
JavaScript SDK
CLI Reference
Configuration & Features
Architecture & Patterns
Data & Persistence
Learning & Community

⚑ Performance

XoneAI Agents is the fastest AI agent framework for agent instantiation.

Framework Avg Time (ΞΌs) Relative
XoneAI 3.77 1.00x (fastest)
OpenAI Agents SDK 5.26 1.39x
Agno 5.64 1.49x
XoneAI (LiteLLM) 7.56 2.00x
PydanticAI 226.94 60.16x
LangGraph 4,558.71 1,209x
Run benchmarks yourself 
cd xoneai-agents
python benchmarks/simple_benchmark.py

πŸš€ Quick Start

Get started with XoneAI in under 1 minute:

# Install
pip install xoneaiagents

# Set API key
export OPENAI_API_KEY=your_key_here

# Create a simple agent
python -c "from xoneaiagents import Agent; Agent(instructions='You are a helpful AI assistant').start('Write a haiku about AI')"

Next Steps: Single Agent Example | Multi Agents | CLI Auto Mode

πŸ“¦ Installation

Python SDK

Lightweight package dedicated for coding:

pip install xoneaiagents

For the full framework with CLI support:

pip install xoneai

JavaScript SDK

npm install xoneai

Environment Variables

Variable Required Description
OPENAI_API_KEY Yes* OpenAI API key
ANTHROPIC_API_KEY No Anthropic Claude API key
GOOGLE_API_KEY No Google Gemini API key
GROQ_API_KEY No Groq API key
OPENAI_BASE_URL No Custom API endpoint (for Ollama, Groq, etc.)

*At least one LLM provider API key is required.

# Set your API key
export OPENAI_API_KEY=your_key_here

# For Ollama (local models)
export OPENAI_BASE_URL=http://localhost:11434/v1

# For Groq
export OPENAI_API_KEY=your_groq_key
export OPENAI_BASE_URL=https://api.groq.com/openai/v1

✨ Key Features

πŸ€– Core Agents
Feature Code Docs
Single Agent Example πŸ“–
Multi Agents Example πŸ“–
Auto Agents Example πŸ“–
Self Reflection AI Agents Example πŸ“–
Reasoning AI Agents Example πŸ“–
Multi Modal AI Agents Example πŸ“–
πŸ”„ Workflows
Feature Code Docs
Simple Workflow Example πŸ“–
Workflow with Agents Example πŸ“–
Agentic Routing (route()) Example πŸ“–
Parallel Execution (parallel()) Example πŸ“–
Loop over List/CSV (loop()) Example πŸ“–
Evaluator-Optimizer (repeat()) Example πŸ“–
Conditional Steps Example πŸ“–
Workflow Branching Example πŸ“–
Workflow Early Stop Example πŸ“–
Workflow Checkpoints Example πŸ“–
πŸ’» Code & Development
Feature Code Docs
Code Interpreter Agents Example πŸ“–
AI Code Editing Tools Example πŸ“–
External Agents (All) Example πŸ“–
Claude Code CLI Example πŸ“–
Gemini CLI Example πŸ“–
Codex CLI Example πŸ“–
Cursor CLI Example πŸ“–
🧠 Memory & Knowledge
Feature Code Docs
Memory (Short & Long Term) Example πŸ“–
File-Based Memory Example πŸ“–
Claude Memory Tool Example πŸ“–
Add Custom Knowledge Example πŸ“–
RAG Agents Example πŸ“–
Chat with PDF Agents Example πŸ“–
Data Readers (PDF, DOCX, etc.) CLI πŸ“–
Vector Store Selection CLI πŸ“–
Retrieval Strategies CLI πŸ“–
Rerankers CLI πŸ“–
Index Types (Vector/Keyword/Hybrid) CLI πŸ“–
Query Engines (Sub-Question, etc.) CLI πŸ“–
πŸ”¬ Research & Intelligence
Feature Code Docs
Deep Research Agents Example πŸ“–
Query Rewriter Agent Example πŸ“–
Native Web Search Example πŸ“–
Built-in Search Tools Example πŸ“–
Unified Web Search Example πŸ“–
Web Fetch (Anthropic) Example πŸ“–
πŸ“‹ Planning & Execution
Feature Code Docs
Planning Mode Example πŸ“–
Planning Tools Example πŸ“–
Planning Reasoning Example πŸ“–
Prompt Chaining Example πŸ“–
Evaluator Optimiser Example πŸ“–
Orchestrator Workers Example πŸ“–
πŸ‘₯ Specialized Agents
Feature Code Docs
Data Analyst Agent Example πŸ“–
Finance Agent Example πŸ“–
Shopping Agent Example πŸ“–
Recommendation Agent Example πŸ“–
Wikipedia Agent Example πŸ“–
Programming Agent Example πŸ“–
Math Agents Example πŸ“–
Markdown Agent Example πŸ“–
Prompt Expander Agent Example πŸ“–
🎨 Media & Multimodal
Feature Code Docs
Image Generation Agent Example πŸ“–
Image to Text Agent Example πŸ“–
Video Agent Example πŸ“–
Camera Integration Example πŸ“–
πŸ”Œ Protocols & Integration
Feature Code Docs
MCP Transports Example πŸ“–
WebSocket MCP Example πŸ“–
MCP Security Example πŸ“–
MCP Resumability Example πŸ“–
MCP Config Management Example πŸ“–
LangChain Integrated Agents Example πŸ“–
πŸ›‘οΈ Safety & Control
Feature Code Docs
Guardrails Example πŸ“–
Human Approval Example πŸ“–
Rules & Instructions Example πŸ“–
βš™οΈ Advanced Features
Feature Code Docs
Async & Parallel Processing Example πŸ“–
Parallelisation Example πŸ“–
Repetitive Agents Example πŸ“–
Agent Handoffs Example πŸ“–
Stateful Agents Example πŸ“–
Autonomous Workflow Example πŸ“–
Structured Output Agents Example πŸ“–
Model Router Example πŸ“–
Prompt Caching Example πŸ“–
Fast Context Example πŸ“–
πŸ› οΈ Tools & Configuration
Feature Code Docs
100+ Custom Tools Example πŸ“–
YAML Configuration Example πŸ“–
100+ LLM Support Example πŸ“–
Callback Agents Example πŸ“–
Hooks Example πŸ“–
Middleware System Example πŸ“–
Configurable Model Example πŸ“–
Rate Limiter Example πŸ“–
Injected Tool State Example πŸ“–
Shadow Git Checkpoints Example πŸ“–
Background Tasks Example πŸ“–
Policy Engine Example πŸ“–
Thinking Budgets Example πŸ“–
Output Styles Example πŸ“–
Context Compaction Example πŸ“–
πŸ“Š Monitoring & Management
Feature Code Docs
Sessions Management Example πŸ“–
Auto-Save Sessions Example πŸ“–
History in Context Example πŸ“–
Telemetry Example πŸ“–
Project Docs (.xone/docs/) Example πŸ“–
AI Commit Messages Example πŸ“–
@Mentions in Prompts Example πŸ“–
πŸ–₯️ CLI Features
Feature Code Docs
Slash Commands Example πŸ“–
Autonomy Modes Example πŸ“–
Cost Tracking Example πŸ“–
Repository Map Example πŸ“–
Interactive TUI Example πŸ“–
Git Integration Example πŸ“–
Sandbox Execution Example πŸ“–
CLI Compare Example πŸ“–
Profile/Benchmark Example πŸ“–
Auto Mode Example πŸ“–
Init Example πŸ“–
File Input Example πŸ“–
Final Agent Example πŸ“–
Max Tokens Example πŸ“–
πŸ§ͺ Evaluation
Feature Code Docs
Accuracy Evaluation Example πŸ“–
Performance Evaluation Example πŸ“–
Reliability Evaluation Example πŸ“–
Criteria Evaluation Example πŸ“–
🎯 Agent Skills
Feature Code Docs
Skills Management Example πŸ“–
Custom Skills Example πŸ“–
⏰ 24/7 Scheduling
Feature Code Docs
Agent Scheduler Example πŸ“–

🌐 Supported Providers

XoneAI supports 100+ LLM providers through seamless integration:

View all 24 providers
Provider Example
OpenAI Example
Anthropic Example
Google Gemini Example
Ollama Example
Groq Example
DeepSeek Example
xAI Grok Example
Mistral Example
Cohere Example
Perplexity Example
Fireworks Example
Together AI Example
OpenRouter Example
HuggingFace Example
Azure OpenAI Example
AWS Bedrock Example
Google Vertex Example
Databricks Example
Cloudflare Example
AI21 Example
Replicate Example
SageMaker Example
Moonshot Example
vLLM Example

πŸ“˜ Using Python Code

1. Single Agent

Create app.py file and add the code below:

from xoneaiagents import Agent
agent = Agent(instructions="Your are a helpful AI assistant")
agent.start("Write a movie script about a robot in Mars")

Run:

python app.py

2. Multi Agents

Create app.py file and add the code below:

from xoneaiagents import Agent, Agents

research_agent = Agent(instructions="Research about AI")
summarise_agent = Agent(instructions="Summarise research agent's findings")
agents = Agents(agents=[research_agent, summarise_agent])
agents.start()

Run:

python app.py

3. Agent with Planning Mode

Enable planning for any agent - the agent creates a plan, then executes step by step:

from xoneaiagents import Agent

def search_web(query: str) -> str:
    return f"Search results for: {query}"

agent = Agent(
    name="AI Assistant",
    instructions="Research and write about topics",
    planning=True,              # Enable planning mode
    planning_tools=[search_web], # Tools for planning research
    planning_reasoning=True      # Chain-of-thought reasoning
)

result = agent.start("Research AI trends in 2025 and write a summary")

What happens:

  1. πŸ“‹ Agent creates a multi-step plan
  2. πŸš€ Executes each step sequentially
  3. πŸ“Š Shows progress with context passing
  4. βœ… Returns final result

4. Deep Research Agent

Automated research with real-time streaming, web search, and citations using OpenAI or Gemini Deep Research APIs.

from xoneaiagents import DeepResearchAgent

# OpenAI Deep Research
agent = DeepResearchAgent(
    model="o4-mini-deep-research",  # or "o3-deep-research"
    verbose=True
)

result = agent.research("What are the latest AI trends in 2025?")
print(result.report)
print(f"Citations: {len(result.citations)}")
# Gemini Deep Research
from xoneaiagents import DeepResearchAgent

agent = DeepResearchAgent(
    model="deep-research-pro",  # Auto-detected as Gemini
    verbose=True
)

result = agent.research("Research quantum computing advances")
print(result.report)

Features:

  • πŸ” Multi-provider support (OpenAI, Gemini, LiteLLM)
  • πŸ“‘ Real-time streaming with reasoning summaries
  • πŸ“š Structured citations with URLs
  • πŸ› οΈ Built-in tools: web search, code interpreter, MCP, file search
  • πŸ”„ Automatic provider detection from model name

5. Query Rewriter Agent

Transform user queries to improve RAG retrieval quality using multiple strategies.

from xoneaiagents import QueryRewriterAgent, RewriteStrategy

agent = QueryRewriterAgent(model="gpt-4o-mini")

# Basic - expands abbreviations, adds context
result = agent.rewrite("AI trends")
print(result.primary_query)  # "What are the current trends in Artificial Intelligence?"

# HyDE - generates hypothetical document for semantic matching
result = agent.rewrite("What is quantum computing?", strategy=RewriteStrategy.HYDE)

# Step-back - generates broader context question
result = agent.rewrite("GPT-4 vs Claude 3?", strategy=RewriteStrategy.STEP_BACK)

# Sub-queries - decomposes complex questions
result = agent.rewrite("RAG setup and best embedding models?", strategy=RewriteStrategy.SUB_QUERIES)

# Contextual - resolves references using chat history
result = agent.rewrite("What about cost?", chat_history=[...])

Strategies:

  • BASIC: Expand abbreviations, fix typos, add context
  • HYDE: Generate hypothetical document for semantic matching
  • STEP_BACK: Generate higher-level concept questions
  • SUB_QUERIES: Decompose multi-part questions
  • MULTI_QUERY: Generate multiple paraphrased versions
  • CONTEXTUAL: Resolve references using conversation history
  • AUTO: Automatically detect best strategy

6. Agent Memory (Zero Dependencies)

Enable persistent memory for agents - works out of the box without any extra packages.

from xoneaiagents import Agent
from xoneaiagents.memory import FileMemory

# Enable memory with a single parameter
agent = Agent(
    name="Personal Assistant",
    instructions="You are a helpful assistant that remembers user preferences.",
    memory=True,  # Enables file-based memory (no extra deps!)
    user_id="user123"  # Isolate memory per user
)

# Memory is automatically injected into conversations
result = agent.start("My name is John and I prefer Python")
# Agent will remember this for future conversations

Memory Types:

  • Short-term: Rolling buffer of recent context (auto-expires)
  • Long-term: Persistent important facts (sorted by importance)
  • Entity: People, places, organizations with attributes
  • Episodic: Date-based interaction history

Advanced Features:

from xoneaiagents.memory import FileMemory

memory = FileMemory(user_id="user123")

# Session Save/Resume
memory.save_session("project_session", conversation_history=[...])
memory.resume_session("project_session")

# Context Compression
memory.compress(llm_func=lambda p: agent.chat(p), max_items=10)

# Checkpointing
memory.create_checkpoint("before_refactor", include_files=["main.py"])
memory.restore_checkpoint("before_refactor", restore_files=True)

# Slash Commands
memory.handle_command("/memory show")
memory.handle_command("/memory save my_session")

Storage Options:

Option Dependencies Description
memory=True None File-based JSON storage (default)
memory="file" None Explicit file-based storage
memory="sqlite" Built-in SQLite with indexing
memory="chromadb" chromadb Vector/semantic search

7. Rules & Instructions

XoneAI auto-discovers instruction files from your project root and git root:

File Description Priority
XONE.md XoneAI native instructions High
XONE.local.md Local overrides (gitignored) Higher
CLAUDE.md Claude Code memory file High
CLAUDE.local.md Local overrides (gitignored) Higher
AGENTS.md OpenAI Codex CLI instructions High
GEMINI.md Gemini CLI memory file High
.cursorrules Cursor IDE rules High
.windsurfrules Windsurf IDE rules High
.claude/rules/*.md Claude Code modular rules Medium
.windsurf/rules/*.md Windsurf modular rules Medium
.cursor/rules/*.mdc Cursor modular rules Medium
.xone/rules/*.md Workspace rules Medium
~/.xone/rules/*.md Global rules Low 
from xoneaiagents import Agent

# Agent auto-discovers CLAUDE.md, AGENTS.md, GEMINI.md, etc.
agent = Agent(name="Assistant", instructions="You are helpful.")
# Rules are injected into system prompt automatically

@Import Syntax:

# CLAUDE.md
See @README for project overview
See @docs/architecture.md for system design
@~/.xone/my-preferences.md

Rule File Format (with YAML frontmatter):

---
description: Python coding guidelines
globs: ["**/*.py"]
activation: always  # always, glob, manual, ai_decision
---

# Guidelines
- Use type hints
- Follow PEP 8

8. Auto-Generated Memories

from xoneaiagents.memory import FileMemory, AutoMemory

memory = FileMemory(user_id="user123")
auto = AutoMemory(memory, enabled=True)

# Automatically extracts and stores memories from conversations
memories = auto.process_interaction(
    "My name is John and I prefer Python for backend work"
)
# Extracts: name="John", preference="Python for backend"

9. Agentic Workflows

Create powerful multi-agent workflows with the Workflow class:

from xoneaiagents import Agent, Workflow

# Create agents
researcher = Agent(
    name="Researcher",
    role="Research Analyst",
    goal="Research topics thoroughly",
    instructions="Provide concise, factual information."
)

writer = Agent(
    name="Writer",
    role="Content Writer", 
    goal="Write engaging content",
    instructions="Write clear, engaging content based on research."
)

# Create workflow with agents as steps
workflow = Workflow(steps=[researcher, writer])

# Run workflow - agents process sequentially
result = workflow.start("What are the benefits of AI agents?")
print(result["output"])

Key Features:

  • Agent-first - Pass Agent objects directly as workflow steps
  • Pattern helpers - Use route(), parallel(), loop(), repeat()
  • Planning mode - Enable with planning=True
  • Callbacks - Monitor with on_step_complete, on_workflow_complete
  • Async execution - Use workflow.astart() for async

Workflow Patterns (route, parallel, loop, repeat)

from xoneaiagents import Agent, Workflow
from xoneaiagents.workflows import route, parallel, loop, repeat

# 1. ROUTING - Classifier agent routes to specialized agents
classifier = Agent(name="Classifier", instructions="Respond with 'technical' or 'creative'")
tech_agent = Agent(name="TechExpert", role="Technical Expert")
creative_agent = Agent(name="Creative", role="Creative Writer")

workflow = Workflow(steps=[
    classifier,
    route({
        "technical": [tech_agent],
        "creative": [creative_agent]
    })
])

# 2. PARALLEL - Multiple agents work concurrently
market_agent = Agent(name="Market", role="Market Researcher")
competitor_agent = Agent(name="Competitor", role="Competitor Analyst")
aggregator = Agent(name="Aggregator", role="Synthesizer")

workflow = Workflow(steps=[
    parallel([market_agent, competitor_agent]),
    aggregator
])

# 3. LOOP - Agent processes each item
processor = Agent(name="Processor", role="Item Processor")
summarizer = Agent(name="Summarizer", role="Summarizer")

workflow = Workflow(
    steps=[loop(processor, over="items"), summarizer],
    variables={"items": ["AI", "ML", "NLP"]}
)

# 4. REPEAT - Evaluator-Optimizer pattern
generator = Agent(name="Generator", role="Content Generator")
evaluator = Agent(name="Evaluator", instructions="Say 'APPROVED' if good")

workflow = Workflow(steps=[
    generator,
    repeat(evaluator, until=lambda ctx: "approved" in ctx.previous_result.lower(), max_iterations=3)
])

# 5. CALLBACKS
workflow = Workflow(
    steps=[researcher, writer],
    on_step_complete=lambda name, r: print(f"βœ… {name} done")
)

# 6. WITH PLANNING & REASONING
workflow = Workflow(
    steps=[researcher, writer],
    planning=True,
    reasoning=True
)

# 7. ASYNC EXECUTION
result = asyncio.run(workflow.astart("input"))

# 8. STATUS TRACKING
workflow.status  # "not_started" | "running" | "completed"
workflow.step_statuses  # {"step1": "completed", "step2": "skipped"}

YAML Workflow Template

# .xone/workflows/research.yaml
name: Research Workflow
description: Research and write content with all patterns

agents:
  researcher:
    role: Research Expert
    goal: Find accurate information
    tools: [tavily_search, web_scraper]
  writer:
    role: Content Writer
    goal: Write engaging content
  editor:
    role: Editor
    goal: Polish content

steps:
  # Sequential
  - agent: researcher
    action: Research {{topic}}
    output_variable: research_data

  # Routing
  - name: classifier
    action: Classify content type
    route:
      technical: [tech_handler]
      creative: [creative_handler]
      default: [general_handler]

  # Parallel
  - name: parallel_research
    parallel:
      - agent: researcher
        action: Research market
      - agent: researcher
        action: Research competitors

  # Loop
  - agent: writer
    action: Write about {{item}}
    loop_over: topics
    loop_var: item

  # Repeat (evaluator-optimizer)
  - agent: editor
    action: Review and improve
    repeat:
      until: "quality > 8"
      max_iterations: 3

  # Output to file
  - agent: writer
    action: Write final report
    output_file: output/{{topic}}_report.md

variables:
  topic: AI trends
  topics: [ML, NLP, Vision]

workflow:
  planning: true
  planning_llm: gpt-4o
  memory_config:
    provider: chroma
    persist: true

Loading YAML Workflows

from xoneaiagents.workflows import YAMLWorkflowParser, WorkflowManager

# Option 1: Parse YAML string
parser = YAMLWorkflowParser()
workflow = parser.parse_string(yaml_content)
result = workflow.start("Research AI trends")

# Option 2: Load from file with WorkflowManager
manager = WorkflowManager()
workflow = manager.load_yaml("research_workflow.yaml")
result = workflow.start("Research AI trends")

# Option 3: Execute YAML directly
result = manager.execute_yaml(
    "research_workflow.yaml",
    input_data="Research AI trends",
    variables={"topic": "Machine Learning"}
)

Complete workflow.yaml Reference

# workflow.yaml - Full feature reference
name: Complete Workflow
description: Demonstrates all workflow.yaml features
framework: xoneai  # xoneai, crewai, autogen
process: workflow     # sequential, hierarchical, workflow

workflow:
  planning: true
  planning_llm: gpt-4o
  reasoning: true
  verbose: true
  memory_config:
    provider: chroma
    persist: true

variables:
  topic: AI trends
  items: [ML, NLP, Vision]

agents:
  researcher:
    name: Researcher
    role: Research Analyst
    goal: Research topics thoroughly
    instructions: "Provide detailed research findings"
    backstory: "Expert researcher with 10 years experience"  # alias for instructions
    llm: gpt-4o-mini
    function_calling_llm: gpt-4o      # For tool calls
    max_rpm: 10                        # Rate limiting
    max_execution_time: 300            # Timeout in seconds
    reflect_llm: gpt-4o               # For self-reflection
    min_reflect: 1
    max_reflect: 3
    system_template: "You are a helpful assistant"
    tools:
      - tavily_search

  writer:
    name: Writer
    role: Content Writer
    goal: Write clear content
    instructions: "Write engaging content"

steps:
  - name: research_step
    agent: researcher
    action: "Research {{topic}}"
    expected_output: "Comprehensive research report"
    output_file: "output/research.md"
    create_directory: true
    
  - name: writing_step
    agent: writer
    action: "Write article based on research"
    context:                          # Task dependencies
      - research_step
    output_json:                      # Structured output
      type: object
      properties:
        title: { type: string }
        content: { type: string }

callbacks:
  on_workflow_start: log_start
  on_step_complete: log_step
  on_workflow_complete: log_complete

10. Hooks

Intercept and modify agent behavior at various lifecycle points:

from xoneaiagents.hooks import (
    HookRegistry, HookRunner, HookEvent, HookResult,
    BeforeToolInput
)

# Create a hook registry
registry = HookRegistry()

# Log all tool calls
@registry.on(HookEvent.BEFORE_TOOL)
def log_tools(event_data: BeforeToolInput) -> HookResult:
    print(f"Tool: {event_data.tool_name}")
    return HookResult.allow()

# Block dangerous operations
@registry.on(HookEvent.BEFORE_TOOL)
def security_check(event_data: BeforeToolInput) -> HookResult:
    if "delete" in event_data.tool_name.lower():
        return HookResult.deny("Delete operations blocked")
    return HookResult.allow()

# Execute hooks
runner = HookRunner(registry)

CLI Commands:

xoneai hooks list                    # List registered hooks
xoneai hooks test before_tool        # Test hooks for an event
xoneai hooks run "echo test"         # Run a command hook
xoneai hooks validate hooks.json     # Validate configuration

11. Shadow Git Checkpoints

File-level undo/restore using shadow git:

from xoneaiagents.checkpoints import CheckpointService

service = CheckpointService(workspace_dir="./my_project")
await service.initialize()

# Save checkpoint before changes
result = await service.save("Before refactoring")

# Make changes...

# Restore if needed
await service.restore(result.checkpoint.id)

# View diff
diff = await service.diff()

CLI Commands:

xoneai checkpoint save "Before changes"  # Save checkpoint
xoneai checkpoint list                   # List checkpoints
xoneai checkpoint diff                   # Show changes
xoneai checkpoint restore abc123         # Restore to checkpoint

Links:

12. Background Tasks

Run agent tasks asynchronously without blocking:

import asyncio
from xoneaiagents.background import BackgroundRunner, BackgroundConfig

async def main():
    config = BackgroundConfig(max_concurrent_tasks=3)
    runner = BackgroundRunner(config=config)
    
    async def my_task(name: str) -> str:
        await asyncio.sleep(2)
        return f"Task {name} completed"
    
    task = await runner.submit(my_task, args=("example",), name="my_task")
    await task.wait(timeout=10.0)
    print(task.result)

asyncio.run(main())

CLI Commands:

xoneai background list          # List running tasks
xoneai background status <id>   # Check task status
xoneai background cancel <id>   # Cancel a task
xoneai background clear         # Clear completed tasks

Links:

13. Policy Engine

Control what agents can and cannot do with policy-based execution:

from xoneaiagents.policy import (
    PolicyEngine, Policy, PolicyRule, PolicyAction
)

engine = PolicyEngine()

policy = Policy(
    name="no_delete",
    rules=[
        PolicyRule(
            action=PolicyAction.DENY,
            resource="tool:delete_*",
            reason="Delete operations blocked"
        )
    ]
)
engine.add_policy(policy)

result = engine.check("tool:delete_file", {})
print(f"Allowed: {result.allowed}")

CLI Commands:

xoneai policy list                  # List policies
xoneai policy check "tool:name"     # Check if allowed
xoneai policy init                  # Create template

Links:

14. Thinking Budgets

Configure token budgets for extended thinking:

from xoneaiagents.thinking import ThinkingBudget, ThinkingTracker

# Use predefined levels
budget = ThinkingBudget.high()  # 16,000 tokens

# Track usage
tracker = ThinkingTracker()
session = tracker.start_session(budget_tokens=16000)
tracker.end_session(session, tokens_used=12000)

summary = tracker.get_summary()
print(f"Utilization: {summary['average_utilization']:.1%}")

CLI Commands:

xoneai thinking status      # Show current budget
xoneai thinking set high    # Set budget level
xoneai thinking stats       # Show usage statistics

Links:

15. Output Styles

Configure how agents format their responses:

from xoneaiagents.output import OutputStyle, OutputFormatter

# Use preset styles
style = OutputStyle.concise()
formatter = OutputFormatter(style)

# Format output
text = "# Hello\n\nThis is **bold** text."
plain = formatter.format(text)
print(plain)

CLI Commands:

xoneai output status        # Show current style
xoneai output set concise   # Set output style

Links:

16. Context Compaction

Automatically manage context window size:

from xoneaiagents.compaction import (
    ContextCompactor, CompactionStrategy
)

compactor = ContextCompactor(
    max_tokens=4000,
    strategy=CompactionStrategy.SLIDING,
    preserve_recent=3
)

messages = [...]  # Your conversation history
compacted, result = compactor.compact(messages)

print(f"Compression: {result.compression_ratio:.1%}")

CLI Commands:

xoneai compaction status        # Show settings
xoneai compaction set sliding   # Set strategy
xoneai compaction stats         # Show statistics

Links:

17. Field Names Reference (A-I-G-S)

XoneAI accepts both old (agents.yaml) and new (workflow.yaml) field names. Use the canonical names for new projects:

Canonical (Recommended) Alias (Also Works) Purpose
agents roles Define agent personas
instructions backstory Agent behavior/persona
action description What the step does
steps tasks (nested) Define work items
name topic Workflow identifier

A-I-G-S Mnemonic - Easy to remember:

  • Agents - Who does the work
  • Instructions - How they behave
  • Goal - What they achieve
  • Steps - What they do
# Quick Reference - Canonical Format
name: My Workflow              # Workflow name (not 'topic')
agents:                        # Define agents (not 'roles')
  my_agent:
    role: Job Title            # Agent's role
    goal: What to achieve      # Agent's goal
    instructions: How to act   # Agent's behavior (not 'backstory')
    
steps:                         # Define steps (not 'tasks')
  - agent: my_agent
    action: What to do         # Step action (not 'description')

Note: The parser accepts both old and new names. Run xoneai workflow validate <file.yaml> to see suggestions for canonical names.

18. Extended agents.yaml with Workflow Patterns

Feature Parity: Both agents.yaml and workflow.yaml now support the same features:

  • All workflow patterns (route, parallel, loop, repeat)
  • All agent fields (function_calling_llm, max_rpm, max_execution_time, reflect_llm, templates)
  • All step fields (expected_output, context, output_json, create_directory, callback)
  • Framework support (xoneai, crewai, autogen)
  • Process types (sequential, hierarchical, workflow)

You can use advanced workflow patterns directly in agents.yaml by setting process: workflow:

# agents.yaml with workflow patterns
framework: xoneai
process: workflow  # Enables workflow mode
topic: "Research AI trends"

workflow:
  planning: true
  reasoning: true
  verbose: true

variables:
  topic: AI trends

agents:  # Canonical: use 'agents' instead of 'roles'
  classifier:
    role: Request Classifier
    instructions: "Classify requests into categories"  # Canonical: use 'instructions' instead of 'backstory'
    goal: Classify requests
    
  researcher:
    role: Research Analyst
    instructions: "Expert researcher"  # Canonical: use 'instructions' instead of 'backstory'
    goal: Research topics
    tools:
      - tavily_search

steps:
  # Sequential step
  - agent: classifier
    action: "Classify: {{topic}}"
    
  # Route pattern - decision-based branching
  - name: routing
    route:
      technical: [tech_expert]
      default: [researcher]
      
  # Parallel pattern - concurrent execution
  - name: parallel_research
    parallel:
      - agent: researcher
        action: "Research market trends"
      - agent: researcher
        action: "Research competitors"
        
  # Loop pattern - iterate over items
  - agent: researcher
    action: "Analyze {{item}}"
    loop:
      over: topics
      
  # Repeat pattern - evaluator-optimizer
  - agent: aggregator
    action: "Synthesize findings"
    repeat:
      until: "comprehensive"
      max_iterations: 3

Run with the same simple command:

xoneai agents.yaml

19. MCP (Model Context Protocol)

XoneAI supports MCP Protocol Revision 2025-11-25 with multiple transports.

MCP Client (Consume MCP Servers)

from xoneaiagents import Agent, MCP

# stdio - Local NPX/Python servers
agent = Agent(tools=MCP("npx @modelcontextprotocol/server-memory"))

# Streamable HTTP - Production servers
agent = Agent(tools=MCP("https://api.example.com/mcp"))

# WebSocket - Real-time bidirectional
agent = Agent(tools=MCP("wss://api.example.com/mcp", auth_token="token"))

# SSE (Legacy) - Backward compatibility
agent = Agent(tools=MCP("http://localhost:8080/sse"))

# With environment variables
agent = Agent(
    tools=MCP(
        command="npx",
        args=["-y", "@modelcontextprotocol/server-brave-search"],
        env={"BRAVE_API_KEY": "your-key"}
    )
)

# Multiple MCP servers + regular functions
def my_custom_tool(query: str) -> str:
    """Custom tool function."""
    return f"Result: {query}"

agent = Agent(
    name="MultiToolAgent",
    instructions="Agent with multiple MCP servers",
    tools=[
        MCP("uvx mcp-server-time"),                    # Time tools
        MCP("npx @modelcontextprotocol/server-memory"), # Memory tools
        my_custom_tool                                  # Regular function
    ]
)

MCP Server (Expose Tools as MCP Server)

Expose your Python functions as MCP tools for Claude Desktop, Cursor, and other MCP clients:

from xoneaiagents.mcp import ToolsMCPServer

def search_web(query: str, max_results: int = 5) -> dict:
    """Search the web for information."""
    return {"results": [f"Result for {query}"]}

def calculate(expression: str) -> dict:
    """Evaluate a mathematical expression."""
    return {"result": eval(expression)}

# Create and run MCP server
server = ToolsMCPServer(name="my-tools")
server.register_tools([search_web, calculate])
server.run()  # stdio for Claude Desktop
# server.run_sse(host="0.0.0.0", port=8080)  # SSE for web clients

MCP Features

Feature Description
Session Management Automatic Mcp-Session-Id handling
Protocol Versioning Mcp-Protocol-Version header
Resumability SSE stream recovery via Last-Event-ID
Security Origin validation, DNS rebinding prevention
WebSocket Auto-reconnect with exponential backoff

20. A2A (Agent2Agent Protocol)

XoneAI supports the A2A Protocol for agent-to-agent communication, enabling your agents to be discovered and collaborate with other AI agents.

A2A Server (Expose Agent as A2A Server)

from xoneaiagents import Agent, A2A
from fastapi import FastAPI

# Create an agent with tools
def search_web(query: str) -> str:
    """Search the web for information."""
    return f"Results for: {query}"

agent = Agent(
    name="Research Assistant",
    role="Research Analyst",
    goal="Help users research topics",
    tools=[search_web]
)

# Expose as A2A Server
a2a = A2A(agent=agent, url="http://localhost:8000/a2a")

app = FastAPI()
app.include_router(a2a.get_router())

# Run: uvicorn app:app --reload
# Agent Card: GET /.well-known/agent.json
# Status: GET /status

A2A Features

Feature Description
Agent Card JSON metadata for agent discovery
Skills Extraction Auto-generate skills from tools
Task Management Stateful task lifecycle
Streaming SSE streaming for real-time updates

Documentation: docs.xone.ai/a2a | Examples: examples/python/a2a

🎯 CLI / No-Code Interface

XoneAI provides a powerful CLI for no-code automation and quick prototyping.

CLI Quick Reference

Category Commands
Execution xoneai, --auto, --interactive, --chat
Research research, --query-rewrite, --deep-research
Planning --planning, --planning-tools, --planning-reasoning
Workflows workflow run, workflow list, workflow auto
Memory memory show, memory add, memory search, memory clear
Knowledge knowledge add, knowledge query, knowledge list
Sessions session list, session resume, session delete
Tools tools list, tools info, tools search
MCP mcp list, mcp create, mcp enable
Development commit, docs, checkpoint, hooks
Scheduling schedule start, schedule list, schedule stop

Auto Mode

pip install xoneai
export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
xoneai --auto create a movie script about Robots in Mars

Interactive Mode CLI:

# Start interactive terminal mode (inspired by Gemini CLI, Codex CLI, Claude Code)
xoneai --interactive
xoneai -i

# Features:
# - Streaming responses (no boxes)
# - Built-in tools: read_file, write_file, list_files, execute_command, internet_search
# - Slash commands: /help, /exit, /tools, /clear

# Chat mode - single prompt with interactive style (for testing/scripting)
# Use --chat (or --chat-mode for backward compatibility)
xoneai "list files in current folder" --chat
xoneai "search the web for AI news" --chat
xoneai "read README.md" --chat

Chat UI (Web Interface):

# Start web-based Chainlit chat interface (requires xoneai[chat])
pip install "xoneai[chat]"
xoneai chat
# Opens browser at http://localhost:8084

Query Rewriting (works with any command):

# Rewrite query for better results (uses QueryRewriterAgent)
xoneai "AI trends" --query-rewrite

# Rewrite with search tools (agent decides when to search)
xoneai "latest developments" --query-rewrite --rewrite-tools "internet_search"

# Works with any prompt
xoneai "explain quantum computing" --query-rewrite -v

Deep Research CLI:

# Default: OpenAI (o4-mini-deep-research)
xoneai research "What are the latest AI trends in 2025?"

# Use Gemini
xoneai research --model deep-research-pro "Your research query"

# Rewrite query before research
xoneai research --query-rewrite "AI trends"

# Rewrite with search tools
xoneai research --query-rewrite --rewrite-tools "internet_search" "AI trends"

# Use custom tools from file (gathers context before deep research)
xoneai research --tools tools.py "Your research query"
xoneai research -t my_tools.py "Your research query"

# Use built-in tools by name (comma-separated)
xoneai research --tools "internet_search,wiki_search" "Your query"
xoneai research -t "yfinance,calculator_tools" "Stock analysis query"

# Save output to file (output/research/{query}.md)
xoneai research --save "Your research query"
xoneai research -s "Your research query"

# Combine options
xoneai research --query-rewrite --tools tools.py --save "Your research query"

# Verbose mode (show debug logs)
xoneai research -v "Your research query"

Planning Mode CLI:

# Enable planning mode - agent creates a plan before execution
xoneai "Research AI trends and write a summary" --planning

# Planning with tools for research
xoneai "Analyze market trends" --planning --planning-tools tools.py

# Planning with chain-of-thought reasoning
xoneai "Complex analysis task" --planning --planning-reasoning

# Auto-approve plans without confirmation
xoneai "Task" --planning --auto-approve-plan

Tool Approval CLI:

# Auto-approve ALL tool executions (use with caution!)
xoneai "run ls command" --trust

# Auto-approve tools up to a risk level (prompt for higher)
# Levels: low, medium, high, critical
xoneai "write to file" --approve-level high  # Prompts for critical tools only
xoneai "task" --approve-level medium         # Prompts for high and critical

# Default behavior (no flags): prompts for all dangerous tools
xoneai "run shell command"  # Will prompt for approval

Memory CLI:

# Enable memory for agent (persists across sessions)
xoneai "My name is John" --memory

# Memory with user isolation
xoneai "Remember my preferences" --memory --user-id user123

# Memory management commands
xoneai memory show                      # Show memory statistics
xoneai memory add "User prefers Python" # Add to long-term memory
xoneai memory search "Python"           # Search memories
xoneai memory clear                     # Clear short-term memory
xoneai memory clear all                 # Clear all memory
xoneai memory save my_session           # Save session
xoneai memory resume my_session         # Resume session
xoneai memory sessions                  # List saved sessions
xoneai memory checkpoint                # Create checkpoint
xoneai memory restore <checkpoint_id>   # Restore checkpoint
xoneai memory checkpoints               # List checkpoints
xoneai memory help                      # Show all commands

Rules CLI:

# List all loaded rules (from XONE.md, CLAUDE.md, etc.)
xoneai rules list

# Show specific rule details
xoneai rules show <rule_name>

# Create a new rule
xoneai rules create my_rule "Always use type hints"

# Delete a rule
xoneai rules delete my_rule

# Show rules statistics
xoneai rules stats

# Include manual rules with prompts
xoneai "Task" --include-rules security,testing

Workflow CLI:

# List available workflows
xoneai workflow list

# Execute a workflow with tools and save output
xoneai workflow run "Research Blog" --tools tavily --save

# Execute with variables
xoneai workflow run deploy --workflow-var environment=staging --workflow-var branch=main

# Execute with planning mode (AI creates sub-steps for each workflow step)
xoneai workflow run "Research Blog" --planning --verbose

# Execute with reasoning mode (chain-of-thought)
xoneai workflow run "Analysis" --reasoning --verbose

# Execute with memory enabled
xoneai workflow run "Research" --memory

# Show workflow details
xoneai workflow show deploy

# Create a new workflow template
xoneai workflow create my_workflow

# Inline workflow (no template file needed)
xoneai "What is AI?" --workflow "Research,Summarize" --save

# Inline workflow with step actions
xoneai "GPT-5" --workflow "Research:Search for info,Write:Write blog" --tools tavily

# Workflow CLI help
xoneai workflow help

YAML Workflow Files:

# Run a YAML workflow file
xoneai workflow run research.yaml

# Run with variables
xoneai workflow run research.yaml --var topic="AI trends"

# Validate a YAML workflow
xoneai workflow validate research.yaml

# Create from template (simple, routing, parallel, loop, evaluator-optimizer)
xoneai workflow template routing --output my_workflow.yaml

Auto-Generate Workflows:

# Auto-generate a sequential workflow from topic
xoneai workflow auto "Research AI trends"

# Generate parallel workflow (multiple agents work concurrently)
xoneai workflow auto "Research AI trends" --pattern parallel

# Generate routing workflow (classifier routes to specialists)
xoneai workflow auto "Build a chatbot" --pattern routing

# Generate orchestrator-workers workflow (central orchestrator delegates)
xoneai workflow auto "Comprehensive market analysis" --pattern orchestrator-workers

# Generate evaluator-optimizer workflow (iterative refinement)
xoneai workflow auto "Write and refine article" --pattern evaluator-optimizer

# Specify output file
xoneai workflow auto "Build a chatbot" --pattern routing

# Specify output file
xoneai workflow auto "Research AI" --pattern sequential --output my_workflow.yaml

Workflow CLI Options:

Flag Description
--workflow-var key=value Set workflow variable (can be repeated)
--var key=value Set variable for YAML workflows
--pattern <pattern> Pattern for auto-generation (sequential, parallel, routing, loop, orchestrator-workers, evaluator-optimizer)
--output <file> Output file for auto-generation
--llm <model> LLM model (e.g., openai/gpt-4o-mini)
--tools <tools> Tools (comma-separated, e.g., tavily)
--planning Enable planning mode
--reasoning Enable reasoning mode
--memory Enable memory
--verbose Enable verbose output
--save Save output to file

Hooks CLI:

# List configured hooks
xoneai hooks list

# Show hooks statistics
xoneai hooks stats

# Create hooks.json template
xoneai hooks init

Claude Memory Tool CLI:

# Enable Claude Memory Tool (Anthropic models only)
xoneai "Research and remember findings" --claude-memory --llm anthropic/claude-sonnet-4-20250514

Guardrail CLI:

# Validate output with LLM guardrail
xoneai "Write code" --guardrail "Ensure code is secure and follows best practices"

# Combine with other flags
xoneai "Generate SQL query" --guardrail "No DROP or DELETE statements" --save

Metrics CLI:

# Display token usage and cost metrics
xoneai "Analyze this data" --metrics

# Combine with other features
xoneai "Complex task" --metrics --planning

Scheduler CLI:

xoneai schedule start <name> "task" --interval hourly
xoneai schedule list
xoneai schedule logs <name> [--follow]
xoneai schedule stop <name>
xoneai schedule restart <name>
xoneai schedule delete <name>
xoneai schedule describe <name>
xoneai schedule save <name> [file.yaml]
xoneai schedule "task" --interval hourly  # foreground mode
xoneai schedule agents.yaml  # foreground mode

Image Processing CLI:

# Process images with vision-based tasks
xoneai "Describe this image" --image path/to/image.png

# Analyze image content
xoneai "What objects are in this photo?" --image photo.jpg --llm openai/gpt-4o

Telemetry CLI:

# Enable usage monitoring and analytics
xoneai "Task" --telemetry

# Combine with metrics for full observability
xoneai "Complex analysis" --telemetry --metrics

MCP (Model Context Protocol) CLI:

# Use MCP server tools
xoneai "Search files" --mcp "npx -y @modelcontextprotocol/server-filesystem ."

# MCP with environment variables
xoneai "Search web" --mcp "npx -y @modelcontextprotocol/server-brave-search" --mcp-env "BRAVE_API_KEY=your_key"

# Multiple MCP options
xoneai "Task" --mcp "npx server" --mcp-env "KEY1=value1,KEY2=value2"

Fast Context CLI:

# Search codebase for relevant context
xoneai "Find authentication code" --fast-context ./src

# Add code context to any task
xoneai "Explain this function" --fast-context /path/to/project

Knowledge CLI:

# Add documents to knowledge base
xoneai knowledge add document.pdf
xoneai knowledge add ./docs/

# Search knowledge base
xoneai knowledge search "API authentication"

# List indexed documents
xoneai knowledge list

# Clear knowledge base
xoneai knowledge clear

# Show knowledge base info
xoneai knowledge info

# Show all commands
xoneai knowledge help

Session CLI:

# List all saved sessions
xoneai session list

# Show session details
xoneai session show my-project

# Resume a session (load into memory)
xoneai session resume my-project

# Delete a session
xoneai session delete my-project

# Auto-save session after each run
xoneai "Analyze this code" --auto-save my-project

# Load history from last N sessions into context
xoneai "Continue our discussion" --history 5

Session Management (Python):

from xoneaiagents import Agent

# Auto-save session after each run
agent = Agent(
    name="Assistant",
    memory=True,
    auto_save="my-project"
)

# Load history from past sessions via context management
agent = Agent(
    name="Assistant",
    memory=True,
    context=True,  # Enable context management for history
)

Workflow Checkpoints:

from xoneaiagents.memory.workflows import WorkflowManager

manager = WorkflowManager()

# Save checkpoint after each step
result = manager.execute("deploy", checkpoint="deploy-v1")

# Resume from checkpoint
result = manager.execute("deploy", resume="deploy-v1")

# List/delete checkpoints
manager.list_checkpoints()
manager.delete_checkpoint("deploy-v1")

Tools CLI:

xoneai tools list
xoneai tools info internet_search
xoneai tools search "web"
xoneai tools doctor
xoneai tools resolve shell_tool
xoneai tools discover
xoneai tools show-sources
xoneai tools show-sources --template ai-video-editor
Command Example Docs
tools list example docs
tools resolve example docs
tools discover example docs
tools show-sources example docs

Handoff CLI:

# Enable agent-to-agent task delegation
xoneai "Research and write article" --handoff "researcher,writer,editor"

# Complex multi-agent workflow
xoneai "Analyze data and create report" --handoff "analyst,visualizer,writer"

Auto Memory CLI:

# Enable automatic memory extraction
xoneai "Learn about user preferences" --auto-memory

# Combine with user isolation
xoneai "Remember my settings" --auto-memory --user-id user123

Todo CLI:

# Generate todo list from task
xoneai "Plan the project" --todo

# Add a todo item
xoneai todo add "Implement feature X"

# List all todos
xoneai todo list

# Complete a todo
xoneai todo complete 1

# Delete a todo
xoneai todo delete 1

# Clear all todos
xoneai todo clear

# Show all commands
xoneai todo help

Router CLI:

# Auto-select best model based on task complexity
xoneai "Simple question" --router

# Specify preferred provider
xoneai "Complex analysis" --router --router-provider anthropic

# Router automatically selects:
# - Simple tasks β†’ gpt-4o-mini, claude-3-haiku
# - Complex tasks β†’ gpt-4-turbo, claude-3-opus

# Create workflow with model routing template
xoneai workflow create --template model-routing --output my_workflow.yaml

Custom models can be configured in agents.yaml. See Model Router Docs for details.

Flow Display CLI:

# Enable visual workflow tracking
xoneai agents.yaml --flow-display

# Combine with other features
xoneai "Multi-step task" --planning --flow-display

Docs CLI:

# List all project docs
xoneai docs list

# Create a new doc
xoneai docs create project-overview "This project is a Python web app..."

# Show a specific doc
xoneai docs show project-overview

# Delete a doc
xoneai docs delete old-doc

# Show all commands
xoneai docs help

MCP Config CLI:

# List all MCP configurations
xoneai mcp list

# Create a new MCP config
xoneai mcp create filesystem npx -y @modelcontextprotocol/server-filesystem .

# Show a specific config
xoneai mcp show filesystem

# Enable/disable a config
xoneai mcp enable filesystem
xoneai mcp disable filesystem

# Delete a config
xoneai mcp delete filesystem

# Show all commands
xoneai mcp help

AI Commit CLI:

# Full auto mode: stage all, security check, commit, and push
xoneai commit -a

# Interactive mode (requires git add first)
xoneai commit

# Interactive with auto-push
xoneai commit --push

# Skip security check (not recommended)
xoneai commit -a --no-verify

Features:

  • πŸ€– AI-generated conventional commit messages
  • πŸ”’ Built-in security scanning (API keys, passwords, secrets, sensitive files)
  • πŸ“¦ Auto-staging with -a flag
  • πŸš€ Auto-push in full auto mode
  • ✏️ Edit message before commit in interactive mode

Security Detection:

  • API keys, secrets, tokens (AWS, GitHub, GitLab, Slack)
  • Passwords and private keys
  • Sensitive files (.env, id_rsa, .pem, .key, etc.)

Serve CLI (API Server):

# Start API server for agents defined in YAML
xoneai serve agents.yaml

# With custom port and host
xoneai serve agents.yaml --port 8005 --host 0.0.0.0

# Alternative flag style
xoneai agents.yaml --serve

# The server provides:
# POST /agents          - Run all agents sequentially
# POST /agents/{name}   - Run specific agent (e.g., /agents/researcher)
# GET  /agents/list     - List available agents

n8n Integration CLI:

# Export workflow to n8n and open in browser
xoneai agents.yaml --n8n

# With custom n8n URL
xoneai agents.yaml --n8n --n8n-url http://localhost:5678

# Set N8N_API_KEY for auto-import
export N8N_API_KEY="your-api-key"
xoneai agents.yaml --n8n

External Agents CLI:

Use external AI coding CLI tools (Claude Code, Gemini CLI, Codex CLI, Cursor CLI) as agent tools:

# Use Claude Code for coding tasks
xoneai "Refactor the auth module" --external-agent claude

# Use Gemini CLI for code analysis
xoneai "Analyze codebase architecture" --external-agent gemini

# Use OpenAI Codex CLI
xoneai "Fix all bugs in src/" --external-agent codex

# Use Cursor CLI
xoneai "Add comprehensive tests" --external-agent cursor

Python API:

from xoneai.integrations import (
    ClaudeCodeIntegration,
    GeminiCLIIntegration,
    CodexCLIIntegration,
    CursorCLIIntegration
)

# Create integration
claude = ClaudeCodeIntegration(workspace="/project")

# Execute a coding task
result = await claude.execute("Refactor the auth module")

# Use as agent tool
from xoneai import Agent
tool = claude.as_tool()
agent = Agent(tools=[tool])

Environment Variables:

export ANTHROPIC_API_KEY=your-key  # Claude Code
export GEMINI_API_KEY=your-key     # Gemini CLI
export OPENAI_API_KEY=your-key     # Codex CLI
export CURSOR_API_KEY=your-key     # Cursor CLI

See External Agents Documentation for more details.

@Mentions in Prompts:

# Include file content in prompt
xoneai "@file:src/main.py explain this code"

# Include project doc
xoneai "@doc:project-overview help me add a feature"

# Search the web
xoneai "@web:python best practices give me tips"

# Fetch URL content
xoneai "@url:https://docs.python.org summarize this"

# Combine multiple mentions
xoneai "@file:main.py @doc:coding-standards review this code"

Prompt Expansion

Expand short prompts into detailed, actionable prompts:

CLI Usage

# Expand a short prompt into detailed prompt
xoneai "write a movie script in 3 lines" --expand-prompt

# With verbose output
xoneai "blog about AI" --expand-prompt -v

# With tools for context gathering
xoneai "latest AI trends" --expand-prompt --expand-tools tools.py

# Combine with query rewrite
xoneai "AI news" --query-rewrite --expand-prompt

Programmatic Usage

from xoneaiagents import PromptExpanderAgent, ExpandStrategy

# Basic usage
agent = PromptExpanderAgent()
result = agent.expand("write a movie script in 3 lines")
print(result.expanded_prompt)

# With specific strategy
result = agent.expand("blog about AI", strategy=ExpandStrategy.DETAILED)

# Available strategies: BASIC, DETAILED, STRUCTURED, CREATIVE, AUTO

Key Difference:

  • --query-rewrite: Optimizes queries for search/retrieval (RAG)
  • --expand-prompt: Expands prompts for detailed task execution

Web Search, Web Fetch & Prompt Caching

CLI Usage

# Web Search - Get real-time information
xoneai "What are the latest AI news today?" --web-search --llm openai/gpt-4o-search-preview

# Web Fetch - Retrieve and analyze URL content (Anthropic only)
xoneai "Summarize https://docs.xone.ai" --web-fetch --llm anthropic/claude-sonnet-4-20250514

# Prompt Caching - Reduce costs for repeated prompts
xoneai "Analyze this document..." --prompt-caching --llm anthropic/claude-sonnet-4-20250514

Programmatic Usage

from xoneaiagents import Agent

# Web Search
agent = Agent(
    instructions="You are a research assistant",
    llm="openai/gpt-4o-search-preview",
    web_search=True
)

# Web Fetch (Anthropic only)
agent = Agent(
    instructions="You are a content analyzer",
    llm="anthropic/claude-sonnet-4-20250514",
    web_fetch=True
)

# Prompt Caching
agent = Agent(
    instructions="You are an AI assistant..." * 50,  # Long system prompt
    llm="anthropic/claude-sonnet-4-20250514",
    prompt_caching=True
)

Supported Providers:

Feature Providers
Web Search OpenAI, Gemini, Anthropic, xAI, Perplexity
Web Fetch Anthropic
Prompt Caching OpenAI (auto), Anthropic, Bedrock, Deepseek

CLI Features

Feature Docs
πŸ”„ Query Rewrite - RAG optimization πŸ“–
πŸ”¬ Deep Research - Automated research πŸ“–
πŸ“‹ Planning - Step-by-step execution πŸ“–
πŸ’Ύ Memory - Persistent agent memory πŸ“–
πŸ“œ Rules - Auto-discovered instructions πŸ“–
πŸ”„ Workflow - Multi-step workflows πŸ“–
πŸͺ Hooks - Event-driven actions πŸ“–
🧠 Claude Memory - Anthropic memory tool πŸ“–
πŸ›‘οΈ Guardrail - Output validation πŸ“–
πŸ“Š Metrics - Token usage tracking πŸ“–
πŸ–ΌοΈ Image - Vision processing πŸ“–
πŸ“‘ Telemetry - Usage monitoring πŸ“–
πŸ”Œ MCP - Model Context Protocol πŸ“–
⚑ Fast Context - Codebase search πŸ“–
πŸ“š Knowledge - RAG management πŸ“–
πŸ’¬ Session - Conversation management πŸ“–
πŸ”§ Tools - Tool discovery πŸ“–
🀝 Handoff - Agent delegation πŸ“–
🧠 Auto Memory - Memory extraction πŸ“–
πŸ“‹ Todo - Task management πŸ“–
🎯 Router - Smart model selection πŸ“–
πŸ“ˆ Flow Display - Visual workflow πŸ“–
✨ Prompt Expansion - Detailed prompts πŸ“–
🌐 Web Search - Real-time search πŸ“–
πŸ“₯ Web Fetch - URL content retrieval πŸ“–
πŸ’Ύ Prompt Caching - Cost reduction πŸ“–
πŸ“¦ Template Catalog - Browse & discover templates πŸ“–

Template Catalog CLI

Command Description
xoneai templates browse Open template catalog in browser
xoneai templates browse --print Print catalog URL only
xoneai templates validate Validate template YAML files
xoneai templates validate --source <dir> Validate specific directory
xoneai templates validate --strict Strict validation mode
xoneai templates validate --json JSON output format
xoneai templates catalog build Build catalog locally
xoneai templates catalog build --out <dir> Build to specific directory
xoneai templates catalog sync Sync template sources
xoneai templates catalog sync --source <name> Sync specific source

Examples: examples/catalog/ | Docs: Code | CLI

πŸ’» Using JavaScript Code

npm install xoneai
export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx
const { Agent } = require('xoneai');
const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
agent.start('Write a movie script about a robot in Mars');

XoneAI CLI Demo

⭐ Star History

Star History Chart

πŸ“Š Process Types & Patterns

View architecture diagrams and workflow patterns

AI Agents Flow

graph LR
    %% Define the main flow
    Start([β–Ά Start]) --> Agent1
    Agent1 --> Process[βš™ Process]
    Process --> Agent2
    Agent2 --> Output([βœ“ Output])
    Process -.-> Agent1
    
    %% Define subgraphs for agents and their tasks
    subgraph Agent1[ ]
        Task1[πŸ“‹ Task]
        AgentIcon1[πŸ€– AI Agent]
        Tools1[πŸ”§ Tools]
        
        Task1 --- AgentIcon1
        AgentIcon1 --- Tools1
    end
    
    subgraph Agent2[ ]
        Task2[πŸ“‹ Task]
        AgentIcon2[πŸ€– AI Agent]
        Tools2[πŸ”§ Tools]
        
        Task2 --- AgentIcon2
        AgentIcon2 --- Tools2
    end

    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
    classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff
    classDef transparent fill:none,stroke:none

    class Start,Output,Task1,Task2 input
    class Process,AgentIcon1,AgentIcon2 process
    class Tools1,Tools2 tools
    class Agent1,Agent2 transparent
Loading

AI Agents with Tools

Create AI agents that can use tools to interact with external systems and perform actions.

flowchart TB
    subgraph Tools
        direction TB
        T3[Internet Search]
        T1[Code Execution]
        T2[Formatting]
    end

    Input[Input] ---> Agents
    subgraph Agents
        direction LR
        A1[Agent 1]
        A2[Agent 2]
        A3[Agent 3]
    end
    Agents ---> Output[Output]

    T3 --> A1
    T1 --> A2
    T2 --> A3

    style Tools fill:#189AB4,color:#fff
    style Agents fill:#8B0000,color:#fff
    style Input fill:#8B0000,color:#fff
    style Output fill:#8B0000,color:#fff
Loading

AI Agents with Memory

Create AI agents with memory capabilities for maintaining context and information across tasks.

flowchart TB
    subgraph Memory
        direction TB
        STM[Short Term]
        LTM[Long Term]
    end

    subgraph Store
        direction TB
        DB[(Vector DB)]
    end

    Input[Input] ---> Agents
    subgraph Agents
        direction LR
        A1[Agent 1]
        A2[Agent 2]
        A3[Agent 3]
    end
    Agents ---> Output[Output]

    Memory <--> Store
    Store <--> A1
    Store <--> A2
    Store <--> A3

    style Memory fill:#189AB4,color:#fff
    style Store fill:#2E8B57,color:#fff
    style Agents fill:#8B0000,color:#fff
    style Input fill:#8B0000,color:#fff
    style Output fill:#8B0000,color:#fff
Loading

AI Agents with Different Processes

Sequential Process

The simplest form of task execution where tasks are performed one after another.

graph LR
    Input[Input] --> A1
    subgraph Agents
        direction LR
        A1[Agent 1] --> A2[Agent 2] --> A3[Agent 3]
    end
    A3 --> Output[Output]

    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
    classDef transparent fill:none,stroke:none

    class Input,Output input
    class A1,A2,A3 process
    class Agents transparent
Loading

Hierarchical Process

Uses a manager agent to coordinate task execution and agent assignments.

graph TB
    Input[Input] --> Manager
    
    subgraph Agents
        Manager[Manager Agent]
        
        subgraph Workers
            direction LR
            W1[Worker 1]
            W2[Worker 2]
            W3[Worker 3]
        end
        
        Manager --> W1
        Manager --> W2
        Manager --> W3
    end
    
    W1 --> Manager
    W2 --> Manager
    W3 --> Manager
    Manager --> Output[Output]

    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
    classDef transparent fill:none,stroke:none

    class Input,Output input
    class Manager,W1,W2,W3 process
    class Agents,Workers transparent
Loading

Workflow Process

Advanced process type supporting complex task relationships and conditional execution.

graph LR
    Input[Input] --> Start
    
    subgraph Workflow
        direction LR
        Start[Start] --> C1{Condition}
        C1 --> |Yes| A1[Agent 1]
        C1 --> |No| A2[Agent 2]
        A1 --> Join
        A2 --> Join
        Join --> A3[Agent 3]
    end
    
    A3 --> Output[Output]

    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff
    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff
    classDef decision fill:#2E8B57,stroke:#7C90A0,color:#fff
    classDef transparent fill:none,stroke:none

    class Input,Output input
    class Start,A1,A2,A3,Join process
    class C1 decision
    class Workflow transparent
Loading

Agentic Routing Workflow

Create AI agents that can dynamically route tasks to specialized LLM instances.

flowchart LR
    In[In] --> Router[LLM Call Router]
    Router --> LLM1[LLM Call 1]
    Router --> LLM2[LLM Call 2]
    Router --> LLM3[LLM Call 3]
    LLM1 --> Out[Out]
    LLM2 --> Out
    LLM3 --> Out
    
    style In fill:#8B0000,color:#fff
    style Router fill:#2E8B57,color:#fff
    style LLM1 fill:#2E8B57,color:#fff
    style LLM2 fill:#2E8B57,color:#fff
    style LLM3 fill:#2E8B57,color:#fff
    style Out fill:#8B0000,color:#fff
Loading

Agentic Orchestrator Worker

Create AI agents that orchestrate and distribute tasks among specialized workers.

flowchart LR
    In[In] --> Router[LLM Call Router]
    Router --> LLM1[LLM Call 1]
    Router --> LLM2[LLM Call 2]
    Router --> LLM3[LLM Call 3]
    LLM1 --> Synthesizer[Synthesizer]
    LLM2 --> Synthesizer
    LLM3 --> Synthesizer
    Synthesizer --> Out[Out]
    
    style In fill:#8B0000,color:#fff
    style Router fill:#2E8B57,color:#fff
    style LLM1 fill:#2E8B57,color:#fff
    style LLM2 fill:#2E8B57,color:#fff
    style LLM3 fill:#2E8B57,color:#fff
    style Synthesizer fill:#2E8B57,color:#fff
    style Out fill:#8B0000,color:#fff
Loading

Agentic Autonomous Workflow

Create AI agents that can autonomously monitor, act, and adapt based on environment feedback.

flowchart LR
    Human[Human] <--> LLM[LLM Call]
    LLM -->|ACTION| Environment[Environment]
    Environment -->|FEEDBACK| LLM
    LLM --> Stop[Stop]
    
    style Human fill:#8B0000,color:#fff
    style LLM fill:#2E8B57,color:#fff
    style Environment fill:#8B0000,color:#fff
    style Stop fill:#333,color:#fff
Loading

Agentic Parallelization

Create AI agents that can execute tasks in parallel for improved performance.

flowchart LR
    In[In] --> LLM2[LLM Call 2]
    In --> LLM1[LLM Call 1]
    In --> LLM3[LLM Call 3]
    LLM1 --> Aggregator[Aggregator]
    LLM2 --> Aggregator
    LLM3 --> Aggregator
    Aggregator --> Out[Out]
    
    style In fill:#8B0000,color:#fff
    style LLM1 fill:#2E8B57,color:#fff
    style LLM2 fill:#2E8B57,color:#fff
    style LLM3 fill:#2E8B57,color:#fff
    style Aggregator fill:#fff,color:#000
    style Out fill:#8B0000,color:#fff
Loading

Agentic Prompt Chaining

Create AI agents with sequential prompt chaining for complex workflows.

flowchart LR
    In[In] --> LLM1[LLM Call 1] --> Gate{Gate}
    Gate -->|Pass| LLM2[LLM Call 2] -->|Output 2| LLM3[LLM Call 3] --> Out[Out]
    Gate -->|Fail| Exit[Exit]
    
    style In fill:#8B0000,color:#fff
    style LLM1 fill:#2E8B57,color:#fff
    style LLM2 fill:#2E8B57,color:#fff
    style LLM3 fill:#2E8B57,color:#fff
    style Out fill:#8B0000,color:#fff
    style Exit fill:#8B0000,color:#fff
Loading

Agentic Evaluator Optimizer

Create AI agents that can generate and optimize solutions through iterative feedback.

flowchart LR
    In[In] --> Generator[LLM Call Generator] 
    Generator -->|SOLUTION| Evaluator[LLM Call Evaluator] -->|ACCEPTED| Out[Out]
    Evaluator -->|REJECTED + FEEDBACK| Generator
    
    style In fill:#8B0000,color:#fff
    style Generator fill:#2E8B57,color:#fff
    style Evaluator fill:#2E8B57,color:#fff
    style Out fill:#8B0000,color:#fff
Loading

Repetitive Agents

Create AI agents that can efficiently handle repetitive tasks through automated loops.

flowchart LR
    In[Input] --> LoopAgent[("Looping Agent")]
    LoopAgent --> Task[Task]
    Task --> |Next iteration| LoopAgent
    Task --> |Done| Out[Output]
    
    style In fill:#8B0000,color:#fff
    style LoopAgent fill:#2E8B57,color:#fff,shape:circle
    style Task fill:#2E8B57,color:#fff
    style Out fill:#8B0000,color:#fff
Loading

πŸ”§ Configuration & Integration

Ollama Integration

export OPENAI_BASE_URL=http://localhost:11434/v1

Groq Integration

Replace xxxx with Groq API KEY:

export OPENAI_API_KEY=xxxxxxxxxxx
export OPENAI_BASE_URL=https://api.groq.com/openai/v1

100+ Models Support

XoneAI supports 100+ LLM models from various providers. Visit our models documentation for the complete list.

πŸ“‹ Agents Playbook

Simple Playbook Example

Create agents.yaml file and add the code below:

framework: xoneai
topic: Artificial Intelligence
agents:  # Canonical: use 'agents' instead of 'roles'
  screenwriter:
    instructions: "Skilled in crafting scripts with engaging dialogue about {topic}."  # Canonical: use 'instructions' instead of 'backstory'
    goal: Create scripts from concepts.
    role: Screenwriter
    tasks:
      scriptwriting_task:
        description: "Develop scripts with compelling characters and dialogue about {topic}."
        expected_output: "Complete script ready for production."

To run the playbook:

xoneai agents.yaml

πŸ› οΈ Custom Tools / Create Plugins

XoneAI supports multiple ways to create and integrate custom tools (plugins) into your agents.

Using @tool Decorator

from xoneaiagents import Agent, tool

@tool
def search(query: str) -> str:
    """Search the web for information."""
    return f"Results for: {query}"

@tool
def calculate(expression: str) -> float:
    """Evaluate a math expression."""
    return eval(expression)

agent = Agent(
    instructions="You are a helpful assistant",
    tools=[search, calculate]
)
agent.start("Search for AI news and calculate 15*4")

Using BaseTool Class

from xoneaiagents import Agent, BaseTool

class WeatherTool(BaseTool):
    name = "weather"
    description = "Get current weather for a location"
    
    def run(self, location: str) -> str:
        return f"Weather in {location}: 72Β°F, Sunny"

agent = Agent(
    instructions="You are a weather assistant",
    tools=[WeatherTool()]
)
agent.start("What's the weather in Paris?")

Creating a Tool Package (pip installable)

# pyproject.toml
[project]
name = "my-xoneai-tools"
version = "1.0.0"
dependencies = ["xoneaiagents"]

[project.entry-points."xoneaiagents.tools"]
my_tool = "my_package:MyTool"
# my_package/__init__.py
from xoneaiagents import BaseTool

class MyTool(BaseTool):
    name = "my_tool"
    description = "My custom tool"
    
    def run(self, param: str) -> str:
        return f"Result: {param}"

After pip install, tools are auto-discovered:

agent = Agent(tools=["my_tool"])  # Works automatically!

🧠 Memory & Context

XoneAI provides zero-dependency persistent memory for agents. For detailed examples, see section 6. Agent Memory in the Python Code Examples.

πŸ“š Knowledge & Retrieval (RAG)

XoneAI provides a complete knowledge stack for building RAG applications with multiple vector stores, retrieval strategies, rerankers, and query modes.

RAG Quickstart (Agent-first)

from xoneaiagents import Agent
from xoneaiagents.rag.models import RetrievalStrategy

# Agent with RAG - simplest approach
agent = Agent(
    name="Research Assistant",
    knowledge=["docs/manual.pdf", "data/faq.txt"],
    knowledge_config={"vector_store": {"provider": "chroma"}},
    rag_config={
        "include_citations": True,
        "retrieval_strategy": RetrievalStrategy.HYBRID,  # Dense + BM25
        "rerank": True,
    }
)

# Query with citations
result = agent.rag_query("How do I authenticate?")
print(result.answer)
for citation in result.citations:
    print(f"  [{citation.id}] {citation.source}")

RAG CLI Commands

Command Description
xoneai rag query "<question>" One-shot question answering with citations
xoneai rag chat Interactive RAG chat session
xoneai rag serve Start RAG as a microservice API
xoneai rag eval <test_file> Evaluate RAG retrieval quality

RAG CLI Examples

# Query with hybrid retrieval (dense + BM25 keyword search)
xoneai rag query "What are the key findings?" --hybrid

# Query with hybrid + reranking for best quality
xoneai rag query "Summarize conclusions" --hybrid --rerank

# Interactive chat with hybrid retrieval
xoneai rag chat --collection research --hybrid --rerank

# Start API server with OpenAI-compatible endpoint
xoneai rag serve --hybrid --rerank --openai-compat --port 8080

# Query with profiling
xoneai rag query "Summary?" --profile --profile-out ./profile.json

Knowledge CLI Commands

Command Description
xoneai knowledge index <sources> Index documents into knowledge base
xoneai knowledge search <query> Search knowledge base (no LLM generation)
xoneai knowledge list List indexed documents

Knowledge CLI Examples

# Index documents
xoneai knowledge index ./docs/ --collection myproject

# Search with hybrid retrieval
xoneai knowledge search "authentication" --hybrid --collection myproject

# Index with profiling
xoneai knowledge index ./data --profile --profile-out ./profile.json

Knowledge vs RAG vs AutoRagAgent

  • Knowledge is the indexing and retrieval substrate - use for indexing and raw search
  • RAG orchestrates on top - use for question answering with LLM-generated responses and citations
  • AutoRagAgent wraps an Agent with automatic retrieval decision - use when you want the agent to decide when to retrieve
  • All share the same underlying index

AutoRagAgent (Automatic RAG)

AutoRagAgent automatically decides when to retrieve context from knowledge bases vs direct chat, based on query heuristics.

from xoneaiagents import Agent, AutoRagAgent

# Create agent with knowledge
agent = Agent(
    name="Research Assistant",
    knowledge=["docs/manual.pdf"],
    user_id="user123",  # Required for RAG retrieval
)

# Wrap with AutoRagAgent
auto_rag = AutoRagAgent(
    agent=agent,
    retrieval_policy="auto",  # auto, always, never
    top_k=5,
    hybrid=True,
    rerank=True,
)

# Auto-decides: retrieves for questions, skips for greetings
result = auto_rag.chat("What are the key findings?")  # Retrieves
result = auto_rag.chat("Hello!")  # Skips retrieval

# Force retrieval or skip per-call
result = auto_rag.chat("Hi", force_retrieval=True)
result = auto_rag.chat("Summary?", skip_retrieval=True)

CLI Usage:

# Enable auto-rag with default policy (auto)
xoneai --auto-rag "What are the key findings?"

# Always retrieve
xoneai --auto-rag --rag-policy always "Tell me about X"

# With hybrid retrieval and reranking
xoneai --auto-rag --rag-hybrid --rag-rerank "Summarize the document"

Configuration Precedence

Settings are applied in this order (highest priority first):

  1. CLI flags - --hybrid, --rerank, --top-k
  2. Environment variables - XONEAI_HYBRID=true
  3. Config file - YAML configuration (--config)
  4. Defaults
# Environment variables
export XONEAI_HYBRID=true
export XONEAI_RERANK=true
export XONEAI_TOP_K=10

Lightweight Installs

# Base install (minimal, fast imports)
pip install xoneaiagents

# With RAG API server support
pip install "xoneai[rag-api]"

Live Tests (Real API Keys)

Run integration tests with real API keys:

# Enable live tests
export XONEAI_LIVE_TESTS=1
export OPENAI_API_KEY="your-key"

# Run live tests
pytest -m live tests/integration/

Knowledge Stack Features Table

Feature Description SDK Docs CLI Docs
Hybrid Retrieval Dense vectors + BM25 keyword search with RRF fusion SDK CLI
Reranking LLM, Cross-Encoder, Cohere rerankers SDK CLI
RAG Serve Microservice API with OpenAI-compatible mode SDK CLI
Vector Stores ChromaDB, Pinecone, Qdrant, Weaviate, In-Memory SDK CLI
Data Readers Load PDF, Markdown, Text, HTML, URLs SDK CLI
Profiling Performance profiling with --profile flag SDK CLI

πŸ”¬ Advanced Features

Research & Intelligence

  • πŸ”¬ Deep Research Agents - OpenAI & Gemini support for automated research
  • πŸ”„ Query Rewriter Agent - HyDE, Step-back, Multi-query strategies for RAG optimization
  • 🌐 Native Web Search - Real-time search via OpenAI, Gemini, Anthropic, xAI, Perplexity
  • πŸ“₯ Web Fetch - Retrieve full content from URLs (Anthropic)
  • πŸ“ Prompt Expander Agent - Expand short prompts into detailed instructions

Memory & Caching

  • πŸ’Ύ Prompt Caching - Reduce costs & latency (OpenAI, Anthropic, Bedrock, Deepseek)
  • 🧠 Claude Memory Tool - Persistent cross-conversation memory (Anthropic Beta)
  • πŸ’Ύ File-Based Memory - Zero-dependency persistent memory for all agents
  • πŸ” Built-in Search Tools - Tavily, You.com, Exa for web search, news, content extraction

Planning & Workflows

  • πŸ“‹ Planning Mode - Plan before execution for agents & multi-agent systems
  • πŸ”§ Planning Tools - Research with tools during planning phase
  • 🧠 Planning Reasoning - Chain-of-thought planning for complex tasks
  • ⛓️ Prompt Chaining - Sequential prompt workflows with conditional gates
  • πŸ” Evaluator Optimiser - Generate and optimize through iterative feedback
  • πŸ‘· Orchestrator Workers - Distribute tasks among specialised workers
  • ⚑ Parallelisation - Execute tasks in parallel for improved performance
  • πŸ” Repetitive Agents - Handle repetitive tasks through automated loops
  • πŸ€– Autonomous Workflow - Monitor, act, adapt based on environment feedback

Specialised Agents

  • πŸ–ΌοΈ Image Generation Agent - Create images from text descriptions
  • πŸ“· Image to Text Agent - Extract text and descriptions from images
  • 🎬 Video Agent - Analyse and process video content
  • πŸ“Š Data Analyst Agent - Analyse data and generate insights
  • πŸ’° Finance Agent - Financial analysis and recommendations
  • πŸ›’ Shopping Agent - Price comparison and shopping assistance
  • ⭐ Recommendation Agent - Personalised recommendations
  • πŸ“– Wikipedia Agent - Search and extract Wikipedia information
  • πŸ’» Programming Agent - Code development and analysis
  • πŸ“ Markdown Agent - Generate and format Markdown content
  • πŸ”€ Model Router - Smart model selection based on task complexity

MCP Protocol

  • πŸ”Œ MCP Transports - stdio, Streamable HTTP, WebSocket, SSE (Protocol 2025-11-25)
  • 🌐 WebSocket MCP - Real-time bidirectional connections with auto-reconnect
  • πŸ” MCP Security - Origin validation, DNS rebinding prevention, secure sessions
  • πŸ”„ MCP Resumability - SSE stream recovery via Last-Event-ID

A2A & A2UI Protocols

  • πŸ”— A2A Protocol - Agent-to-Agent communication for inter-agent collaboration
  • πŸ–ΌοΈ A2UI Protocol - Agent-to-User Interface for generating rich UIs from agents
  • πŸ“‹ UI Templates - ChatTemplate, ListTemplate, FormTemplate, DashboardTemplate
  • πŸ”§ Surface Builder - Fluent API for building declarative UIs

Safety & Control

  • 🀝 Agent Handoffs - Transfer context between specialised agents
  • πŸ›‘οΈ Guardrails - Input/output validation and safety checks
  • βœ… Human Approval - Require human confirmation for critical actions
  • πŸ” Tool Approval CLI - --trust (auto-approve all) and --approve-level (risk-based approval)
  • πŸ’¬ Sessions Management - Isolated conversation contexts
  • πŸ”„ Stateful Agents - Maintain state across interactions

Developer Tools

  • ⚑ Fast Context - Rapid parallel code search (10-20x faster)
  • πŸ“œ Rules & Instructions - Auto-discover CLAUDE.md, AGENTS.md, GEMINI.md
  • πŸͺ Hooks - Pre/post operation hooks for custom logic
  • πŸ“ˆ Telemetry - Track agent performance and usage
  • πŸ“Ή Camera Integration - Capture and analyse camera input

Other Features

  • πŸ”„ CrewAI & AG2 Integration - Use CrewAI or AG2 (Formerly AutoGen) Framework
  • πŸ’» Codebase Chat - Chat with entire codebase
  • 🎨 Interactive UIs - Multiple interactive interfaces
  • πŸ“„ YAML Configuration - YAML-based agent and workflow configuration
  • πŸ› οΈ Custom Tools - Easy custom tool integration
  • πŸ” Internet Search - Multiple providers (Tavily, You.com, Exa, DuckDuckGo, Crawl4AI)
  • πŸ–ΌοΈ VLM Support - Vision Language Model support
  • πŸŽ™οΈ Voice Interaction - Real-time voice interaction

πŸ’Ύ Persistence (Databases)

Enable automatic conversation persistence with 2 lines of code:

from xoneaiagents import Agent, db

agent = Agent(
    name="Assistant",
    db=db(database_url="postgresql://localhost/mydb"),  # db(...) shortcut
    session_id="my-session"  # Optional: defaults to per-hour ID (YYYYMMDDHH)
)
agent.chat("Hello!")  # Auto-persists messages, runs, traces

Persistence CLI Commands

Command Description
xoneai persistence doctor Validate DB connectivity
xoneai persistence run Run agent with persistence
xoneai persistence resume Resume existing session
xoneai persistence export Export session to JSONL
xoneai persistence import Import session from JSONL
xoneai persistence migrate Apply schema migrations
xoneai persistence status Show schema status

Note: See Knowledge & Retrieval (RAG) for complete Knowledge CLI documentation.

Databases Table

Database Store Type Install Example Docs
PostgreSQL Conversation pip install "xoneai[tools]" simple_db_agent.py docs
MySQL Conversation pip install "xoneai[tools]" - docs
SQLite Conversation pip install "xoneai[tools]" - docs
SingleStore Conversation pip install "xoneai[tools]" - docs
Supabase Conversation pip install "xoneai[tools]" - docs
SurrealDB Conversation pip install "xoneai[tools]" - docs
Qdrant Knowledge pip install "xoneai[tools]" knowledge_qdrant.py docs
ChromaDB Knowledge pip install "xoneai[tools]" - docs
Pinecone Knowledge pip install pinecone pinecone_wow.py docs
Weaviate Knowledge pip install weaviate-client weaviate_wow.py docs
LanceDB Knowledge pip install lancedb lancedb_real_wow.py docs
Milvus Knowledge pip install "xoneai[tools]" - docs
PGVector Knowledge pip install psycopg2-binary pgvector_real_wow.py docs
Redis Vector Knowledge pip install "xoneai[tools]" - docs
Cassandra Knowledge pip install "xoneai[tools]" - docs
ClickHouse Knowledge pip install "xoneai[tools]" - docs
Redis State pip install "xoneai[tools]" state_redis.py docs
MongoDB State pip install "xoneai[tools]" - docs
DynamoDB State pip install "xoneai[tools]" - docs
Firestore State pip install "xoneai[tools]" - docs
Upstash State pip install "xoneai[tools]" - docs
Memory State pip install "xoneai[tools]" - docs

πŸ”§ Tools Table

Install all tools with: pip install "xoneai[tools]"

Tool Category Import Docs
Tavily Web Search from xoneai_tools import TavilyTool docs
DuckDuckGo Web Search from xoneai_tools import DuckDuckGoTool docs
Exa Web Search from xoneai_tools import ExaTool docs
Serper Web Search from xoneai_tools import SerperTool docs
Jina Web Reader from xoneai_tools import JinaTool docs
Firecrawl Web Scraping from xoneai_tools import FirecrawlTool docs
Crawl4AI Web Scraping from xoneai_tools import Crawl4AITool docs
Wikipedia Knowledge from xoneai_tools import WikipediaTool docs
ArXiv Research from xoneai_tools import ArxivTool docs
HackerNews News from xoneai_tools import HackerNewsTool docs
YouTube Media from xoneai_tools import YouTubeTool docs
Weather Data from xoneai_tools import WeatherTool docs
PostgreSQL Database from xoneai_tools import PostgresTool docs
MySQL Database from xoneai_tools import MySQLTool docs
SQLite Database from xoneai_tools import SQLiteTool docs
MongoDB Database from xoneai_tools import MongoDBTool docs
Redis Database from xoneai_tools import RedisTool docs
Qdrant Vector DB from xoneai_tools import QdrantTool docs
GitHub DevOps from xoneai_tools import GitHubTool docs
Slack Communication from xoneai_tools import SlackTool docs
Discord Communication from xoneai_tools import DiscordTool docs
Telegram Communication from xoneai_tools import TelegramTool docs
Email Communication from xoneai_tools import EmailTool docs
Notion Productivity from xoneai_tools import NotionTool docs
File File System from xoneai_tools import FileTool docs
Shell System from xoneai_tools import ShellTool docs
Python Code from xoneai_tools import PythonTool docs
JSON Data from xoneai_tools import JSONTool docs
CSV Data from xoneai_tools import CSVTool docs
Calculator Math from xoneai_tools import CalculatorTool docs

See full tools documentation for all 100+ available tools.

πŸŽ“ Video Tutorials

Learn XoneAI through our comprehensive video series:

View all 22 video tutorials
Topic Video
AI Agents with Self Reflection Self Reflection
Reasoning Data Generating Agent Reasoning Data
AI Agents with Reasoning Reasoning
Multimodal AI Agents Multimodal
AI Agents Workflow Workflow
Async AI Agents Async
Mini AI Agents Mini
AI Agents with Memory Memory
Repetitive Agents Repetitive
Introduction Introduction
Tools Overview Tools Overview
Custom Tools Custom Tools
Firecrawl Integration Firecrawl
User Interface UI
Crawl4AI Integration Crawl4AI
Chat Interface Chat
Code Interface Code
Mem0 Integration Mem0
Training Training
Realtime Voice Interface Realtime
Call Interface Call
Reasoning Extract Agents Reasoning Extract

πŸ‘₯ Contributing

We welcome contributions from the community! Here's how you can contribute:

  1. Fork on GitHub - Use the "Fork" button on the repository page
  2. Clone your fork - git clone https://github.com/yourusername/xoneAI.git
  3. Create a branch - git checkout -b new-feature
  4. Make changes and commit - git commit -am "Add some feature"
  5. Push to your fork - git push origin new-feature
  6. Submit a pull request - Via GitHub's web interface
  7. Await feedback - From project maintainers

πŸ”§ Development

Using uv

# Install uv if you haven't already
pip install uv

# Install from requirements
uv pip install -r pyproject.toml

# Install with extras
uv pip install -r pyproject.toml --extra code
uv pip install -r pyproject.toml --extra "crewai,autogen"

Bump and Release

# From project root - bumps version and releases in one command
python src/xoneai/scripts/bump_and_release.py 2.2.99

# With xoneaiagents dependency
python src/xoneai/scripts/bump_and_release.py 2.2.99 --agents 0.0.169

# Then publish
cd src/xoneai && uv publish

❓ FAQ & Troubleshooting

ModuleNotFoundError: No module named 'xoneaiagents'

Install the package:

pip install xoneaiagents
API key not found / Authentication error

Ensure your API key is set:

export OPENAI_API_KEY=your_key_here

For other providers, see Environment Variables.

How do I use a local model (Ollama)? 
# Start Ollama server first
ollama serve

# Set environment variable
export OPENAI_BASE_URL=http://localhost:11434/v1

See Ollama Integration for more details.

How do I persist conversations to a database?

Use the db parameter:

from xoneaiagents import Agent, db

agent = Agent(
    name="Assistant",
    db=db(database_url="postgresql://localhost/mydb"),
    session_id="my-session"
)

See Persistence (Databases) for supported databases.

How do I enable agent memory? 
from xoneaiagents import Agent

agent = Agent(
    name="Assistant",
    memory=True,  # Enables file-based memory (no extra deps!)
    user_id="user123"
)

See Agent Memory for more options.

How do I run multiple agents together? 
from xoneaiagents import Agent, Agents

agent1 = Agent(instructions="Research topics")
agent2 = Agent(instructions="Summarize findings")
agents = Agents(agents=[agent1, agent2])
agents.start()

See Multi Agents for more examples.

How do I use MCP tools? 
from xoneaiagents import Agent, MCP

agent = Agent(
    tools=MCP("npx @modelcontextprotocol/server-memory")
)

See MCP Protocol for all transport options.

Getting Help

Made with ❀️ by the XoneAI Team

Documentation β€’ GitHub β€’ Issues

About

XoneAI is a production-ready Multi AI Agents framework, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code solution to streamline the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.

Resources

Readme

License

MIT license
Activity

Stars

1 star

Watchers

0 watching

Forks

0 forks
Report repository

Releases

No releases published

Packages

 
 
 

Contributors

Languages