PraisonAI 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. By integrating PraisonAI Agents, AG2 (Formerly AutoGen), and CrewAI into a low-code solution, it streamlines the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.

Quick Paths:

• 🆕 New here? → Quick Start (1 minute to first agent)
• 📦 Installing? → Installation
• 🐍 Python SDK? → Python Examples
• 🎯 CLI user? → CLI Quick Reference
• 🔧 Need config? → Configuration
• 🤝 Contributing? → Development

📑 Table of Contents

⚡ Performance

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

cd praisonai-agents
python benchmarks/simple_benchmark.py

🚀 Quick Start

Get started with PraisonAI in under 1 minute:

# Install
pip install praisonaiagents

# Set API key
export OPENAI_API_KEY=your_key_here

# Create a simple agent
python -c "from praisonaiagents 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

📦 Installation

Python SDK

Lightweight package dedicated for coding:

pip install praisonaiagents

For the full framework with CLI support:

pip install praisonai

JavaScript SDK

npm install praisonai

Environment Variables

*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

🌐 Supported Providers

PraisonAI supports 100+ LLM providers through seamless integration:

📘 Using Python Code

1. Single Agent

Create app.py file and add the code below:

from praisonaiagents 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 praisonaiagents 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 praisonaiagents 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. 📋 Agent creates a multi-step plan
2. 🚀 Executes each step sequentially
3. 📊 Shows progress with context passing
4. ✅ 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 praisonaiagents 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 praisonaiagents 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:

• 🔍 Multi-provider support (OpenAI, Gemini, LiteLLM)
• 📡 Real-time streaming with reasoning summaries
• 📚 Structured citations with URLs
• 🛠️ Built-in tools: web search, code interpreter, MCP, file search
• 🔄 Automatic provider detection from model name

5. Query Rewriter Agent

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

from praisonaiagents 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 praisonaiagents import Agent
from praisonaiagents.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 praisonaiagents.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:

7. Rules & Instructions

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

from praisonaiagents 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
@~/.praison/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 praisonaiagents.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 praisonaiagents 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 praisonaiagents import Agent, Workflow
from praisonaiagents.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"✅ {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

# .praison/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 praisonaiagents.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: praisonai  # praisonai, 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 praisonaiagents.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:

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

11. Shadow Git Checkpoints

File-level undo/restore using shadow git:

from praisonaiagents.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:

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

Links:

• 📖 Coding Docs
• 📖 CLI Docs
• 💻 Example

12. Background Tasks

Run agent tasks asynchronously without blocking:

import asyncio
from praisonaiagents.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:

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

Links:

• 📖 Coding Docs
• 📖 CLI Docs
• 💻 Example

13. Policy Engine

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

from praisonaiagents.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:

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

Links:

• 📖 Coding Docs
• 📖 CLI Docs
• 💻 Example

14. Thinking Budgets

Configure token budgets for extended thinking:

from praisonaiagents.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:

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

Links:

• 📖 Coding Docs
• 📖 CLI Docs
• 💻 Example

15. Output Styles

Configure how agents format their responses:

from praisonaiagents.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:

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

Links:

• 📖 Coding Docs
• 📖 CLI Docs
• 💻 Example

16. Context Compaction

Automatically manage context window size:

from praisonaiagents.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:

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

Links:

• 📖 Coding Docs
• 📖 CLI Docs
• 💻 Example

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

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

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 praisonai 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 (praisonai, 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: praisonai
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:

praisonai agents.yaml

19. MCP (Model Context Protocol)

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

MCP Client (Consume MCP Servers)

from praisonaiagents 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 praisonaiagents.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

20. A2A (Agent2Agent Protocol)

PraisonAI 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 praisonaiagents 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

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

🎯 CLI / No-Code Interface

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

CLI Quick Reference

Auto Mode

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

Interactive Mode CLI:

# Start interactive terminal mode (inspired by Gemini CLI, Codex CLI, Claude Code)
praisonai --interactive
praisonai -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)
praisonai "list files in current folder" --chat
praisonai "search the web for AI news" --chat
praisonai "read README.md" --chat

Chat UI (Web Interface):

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

Query Rewriting (works with any command):

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

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

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

Deep Research CLI:

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

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

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

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

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

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

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

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

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

Planning Mode CLI:

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

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

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

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

Tool Approval CLI:

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

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

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

Memory CLI:

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

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

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

Rules CLI:

# List all loaded rules (from PRAISON.md, CLAUDE.md, etc.)
praisonai rules list

# Show specific rule details
praisonai rules show <rule_name>

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

# Delete a rule
praisonai rules delete my_rule

# Show rules statistics
praisonai rules stats

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

Workflow CLI:

# List available workflows
praisonai workflow list

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

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

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

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

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

# Show workflow details
praisonai workflow show deploy

# Create a new workflow template
praisonai workflow create my_workflow

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

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

# Workflow CLI help
praisonai workflow help

YAML Workflow Files:

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

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

# Validate a YAML workflow
praisonai workflow validate research.yaml

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

Auto-Generate Workflows:

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

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

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

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

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

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

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

Workflow CLI Options:

Hooks CLI:

# List configured hooks
praisonai hooks list

# Show hooks statistics
praisonai hooks stats

# Create hooks.json template
praisonai hooks init

Claude Memory Tool CLI:

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

Guardrail CLI:

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

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

Metrics CLI:

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

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

Scheduler CLI:

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

Image Processing CLI:

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

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

Telemetry CLI:

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

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

MCP (Model Context Protocol) CLI:

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

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

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

Fast Context CLI:

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

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

Knowledge CLI:

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

# Search knowledge base
praisonai knowledge search "API authentication"

# List indexed documents
praisonai knowledge list

# Clear knowledge base
praisonai knowledge clear

# Show knowledge base info
praisonai knowledge info

# Show all commands
praisonai knowledge help

Session CLI:

# List all saved sessions
praisonai session list

# Show session details
praisonai session show my-project

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

# Delete a session
praisonai session delete my-project

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

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

Session Management (Python):

from praisonaiagents 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 praisonaiagents.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:

praisonai tools list
praisonai tools info internet_search
praisonai tools search "web"
praisonai tools doctor
praisonai tools resolve shell_tool
praisonai tools discover
praisonai tools show-sources
praisonai tools show-sources --template ai-video-editor

Handoff CLI:

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

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

Auto Memory CLI:

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

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

Todo CLI:

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

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

# List all todos
praisonai todo list

# Complete a todo
praisonai todo complete 1

# Delete a todo
praisonai todo delete 1

# Clear all todos
praisonai todo clear

# Show all commands
praisonai todo help

Router CLI:

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

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

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

# Create workflow with model routing template
praisonai 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
praisonai agents.yaml --flow-display

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

Docs CLI:

# List all project docs
praisonai docs list

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

# Show a specific doc
praisonai docs show project-overview

# Delete a doc
praisonai docs delete old-doc

# Show all commands
praisonai docs help

MCP Config CLI:

# List all MCP configurations
praisonai mcp list

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

# Show a specific config
praisonai mcp show filesystem

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

# Delete a config
praisonai mcp delete filesystem

# Show all commands
praisonai mcp help

AI Commit CLI:

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

# Interactive mode (requires git add first)
praisonai commit

# Interactive with auto-push
praisonai commit --push

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

Features:

• 🤖 AI-generated conventional commit messages
• 🔒 Built-in security scanning (API keys, passwords, secrets, sensitive files)
• 📦 Auto-staging with -a flag
• 🚀 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
praisonai serve agents.yaml

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

# Alternative flag style
praisonai 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
praisonai agents.yaml --n8n

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

# Set N8N_API_KEY for auto-import
export N8N_API_KEY="your-api-key"
praisonai 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
praisonai "Refactor the auth module" --external-agent claude

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

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

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

Python API:

from praisonai.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 praisonai 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
praisonai "@file:src/main.py explain this code"

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

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

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

# Combine multiple mentions
praisonai "@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
praisonai "write a movie script in 3 lines" --expand-prompt

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

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

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

Programmatic Usage

from praisonaiagents 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
praisonai "What are the latest AI news today?" --web-search --llm openai/gpt-4o-search-preview

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

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

Programmatic Usage

from praisonaiagents 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:

CLI Features

Template Catalog CLI

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

💻 Using JavaScript Code

npm install praisonai
export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx

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

⭐ Star History

📊 Process Types & Patterns

graph LR
    %% Define the main flow
    Start([▶ Start]) --> Agent1
    Agent1 --> Process[⚙ Process]
    Process --> Agent2
    Agent2 --> Output([✓ Output])
    Process -.-> Agent1
    
    %% Define subgraphs for agents and their tasks
    subgraph Agent1[ ]
        Task1[📋 Task]
        AgentIcon1[🤖 AI Agent]
        Tools1[🔧 Tools]
        
        Task1 --- AgentIcon1
        AgentIcon1 --- Tools1
    end
    
    subgraph Agent2[ ]
        Task2[📋 Task]
        AgentIcon2[🤖 AI Agent]
        Tools2[🔧 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

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

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

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

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

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

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

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

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

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

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

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

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

🔧 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

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

📋 Agents Playbook

Simple Playbook Example

Create agents.yaml file and add the code below:

framework: praisonai
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:

praisonai agents.yaml

🛠️ Custom Tools / Create Plugins

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

Using @tool Decorator

from praisonaiagents 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 praisonaiagents 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}: 72°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-praisonai-tools"
version = "1.0.0"
dependencies = ["praisonaiagents"]

[project.entry-points."praisonaiagents.tools"]
my_tool = "my_package:MyTool"

# my_package/__init__.py
from praisonaiagents 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

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

📚 Knowledge & Retrieval (RAG)

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

RAG Quickstart (Agent-first)

from praisonaiagents import Agent
from praisonaiagents.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

RAG CLI Examples

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

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

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

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

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

Knowledge CLI Commands

Knowledge CLI Examples

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

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

# Index with profiling
praisonai 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 praisonaiagents 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)
praisonai --auto-rag "What are the key findings?"

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

# With hybrid retrieval and reranking
praisonai --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 - PRAISONAI_HYBRID=true
3. Config file - YAML configuration (--config)
4. Defaults

# Environment variables
export PRAISONAI_HYBRID=true
export PRAISONAI_RERANK=true
export PRAISONAI_TOP_K=10

Lightweight Installs

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

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

Live Tests (Real API Keys)

Run integration tests with real API keys:

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

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

Knowledge Stack Features Table

🔬 Advanced Features

Research & Intelligence

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

Memory & Caching

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

Planning & Workflows

• 📋 Planning Mode - Plan before execution for agents & multi-agent systems
• 🔧 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
• 🔍 Evaluator Optimiser - Generate and optimize through iterative feedback
• 👷 Orchestrator Workers - Distribute tasks among specialised workers
• ⚡ Parallelisation - Execute tasks in parallel for improved performance
• 🔁 Repetitive Agents - Handle repetitive tasks through automated loops
• 🤖 Autonomous Workflow - Monitor, act, adapt based on environment feedback

Specialised Agents

• 🖼️ Image Generation Agent - Create images from text descriptions
• 📷 Image to Text Agent - Extract text and descriptions from images
• 🎬 Video Agent - Analyse and process video content
• 📊 Data Analyst Agent - Analyse data and generate insights
• 💰 Finance Agent - Financial analysis and recommendations
• 🛒 Shopping Agent - Price comparison and shopping assistance
• ⭐ Recommendation Agent - Personalised recommendations
• 📖 Wikipedia Agent - Search and extract Wikipedia information
• 💻 Programming Agent - Code development and analysis
• 📝 Markdown Agent - Generate and format Markdown content
• 🔀 Model Router - Smart model selection based on task complexity

MCP Protocol

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

A2A & A2UI Protocols

• 🔗 A2A Protocol - Agent-to-Agent communication for inter-agent collaboration
• 🖼️ A2UI Protocol - Agent-to-User Interface for generating rich UIs from agents
• 📋 UI Templates - ChatTemplate, ListTemplate, FormTemplate, DashboardTemplate
• 🔧 Surface Builder - Fluent API for building declarative UIs

Safety & Control

• 🤝 Agent Handoffs - Transfer context between specialised agents
• 🛡️ Guardrails - Input/output validation and safety checks
• ✅ Human Approval - Require human confirmation for critical actions
• 🔐 Tool Approval CLI - --trust (auto-approve all) and --approve-level (risk-based approval)
• 💬 Sessions Management - Isolated conversation contexts
• 🔄 Stateful Agents - Maintain state across interactions

Developer Tools

• ⚡ Fast Context - Rapid parallel code search (10-20x faster)
• 📜 Rules & Instructions - Auto-discover CLAUDE.md, AGENTS.md, GEMINI.md
• 🪝 Hooks - Pre/post operation hooks for custom logic
• 📈 Telemetry - Track agent performance and usage
• 📹 Camera Integration - Capture and analyse camera input

Other Features

• 🔄 CrewAI & AG2 Integration - Use CrewAI or AG2 (Formerly AutoGen) Framework
• 💻 Codebase Chat - Chat with entire codebase
• 🎨 Interactive UIs - Multiple interactive interfaces
• 📄 YAML Configuration - YAML-based agent and workflow configuration
• 🛠️ Custom Tools - Easy custom tool integration
• 🔍 Internet Search - Multiple providers (Tavily, You.com, Exa, DuckDuckGo, Crawl4AI)
• 🖼️ VLM Support - Vision Language Model support
• 🎙️ Voice Interaction - Real-time voice interaction

💾 Persistence (Databases)

Enable automatic conversation persistence with 2 lines of code:

from praisonaiagents 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

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

Databases Table

🔧 Tools Table

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

See full tools documentation for all 100+ available tools.

🎓 Video Tutorials

Learn PraisonAI through our comprehensive video series:

View all 22 video tutorials

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

👥 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/praisonAI.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

🔧 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/praisonai/scripts/bump_and_release.py 2.2.99

# With praisonaiagents dependency
python src/praisonai/scripts/bump_and_release.py 2.2.99 --agents 0.0.169

# Then publish
cd src/praisonai && uv publish

❓ FAQ & Troubleshooting

pip install praisonaiagents

export OPENAI_API_KEY=your_key_here

# Start Ollama server first
ollama serve

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

from praisonaiagents import Agent, db

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

from praisonaiagents import Agent

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

from praisonaiagents import Agent, Agents

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

from praisonaiagents import Agent, MCP

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

Getting Help

• 📚 Full Documentation
• 🐛 Report Issues
• 💬 Discussions