Praisonai

## 🚀 Praison AI

PraisonAI is a production-ready Multi-AI Agents framework with self-reflection. It's designed to create AI Agents that can 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 simplifies the building and management of multi-agent LLM systems, emphasizing simplicity, customization, and effective human-agent collaboration.

## 🚀 Quick Start
Get started with PraisonAI in under 1 minute:
```bash
# 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')"

✨ Features

🤖 Core Agents

🔄 Workflows

💻 Code & Development

🧠 Memory & Knowledge

🔬 Research & Intelligence

📋 Planning & Execution

👥 Specialized Agents

🎨 Media & Multimodal

🔌 Protocols & Integration

🛡️ Safety & Control

🛠️ Tools & Configuration

📊 Monitoring & Management

🖥️ CLI Features

🧪 Evaluation

🎯 Agent Skills

⏰ 24/7 Scheduling

📦 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

💻 Usage Examples

Python Code Examples

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

# 2. Multi Agents
from praisonaiagents import Agent, PraisonAIAgents

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

# 3. Agent with Planning Mode
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")

# 4. Deep Research Agent
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)

# 5. Query Rewriter Agent
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=[...])

# 6. Agent Memory (Zero Dependencies)
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

# 7. Rules & Instructions
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

# 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
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"])

# 10. Hooks
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)

# 11. Shadow Git Checkpoints
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()

# 12. Background Tasks
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())

# 13. Policy Engine
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}")

# 14. Thinking Budgets
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%}")

# 15. Output Styles
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)

# 16. Context Compaction
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%}")

# 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:

| 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 |

# 18. Extended agents.yaml with Workflow Patterns
# 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

# 19. MCP (Model Context Protocol)
# 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)
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

# 20. A2A (Agent2Agent Protocol)
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

JavaScript Code Examples

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');

📚 Documentation

🌐 Supported Providers

PraisonAI supports 100+ LLM providers through seamless integration:

📊 Process Types & Patterns

AI Agents Flow

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

AI Agents with Tools

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

AI Agents with Memory

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

AI Agents with Different Processes

Sequential Process

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

Hierarchical Process

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

Workflow Process

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

Agentic Routing Workflow

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

Agentic Orchestrator Worker

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

Agentic Autonomous Workflow

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

Agentic Parallelization

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

Agentic Prompt Chaining

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

Agentic Evaluator Optimizer

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

Repetitive Agents

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

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.

Knowledge CLI Commands

Knowledge CLI Options

Knowledge CLI Examples

# Add documents
praisonai knowledge add ./docs/
praisonai knowledge add https://example.com/page.html
praisonai knowledge add "*.pdf"

# Query with advanced options
praisonai knowledge query "How to authenticate?" --retrieval fusion --reranker llm

# Full advanced query
praisonai knowledge query "authentication flow" \
  --vector-store chroma \
  --retrieval fusion \
  --reranker llm \
  --index-type hybrid \
  --query-mode sub_question

Knowledge SDK Usage

from praisonaiagents import Agent, Knowledge

# Simple usage with Agent
agent = Agent(
    name="Research Assistant",
    knowledge=["docs/manual.pdf", "data/faq.txt"],
    knowledge_config={
        "vector_store": {"provider": "chroma"}
    }
)
response = agent.chat("How do I authenticate?")

# Direct Knowledge usage
knowledge = Knowledge()
knowledge.add("document.pdf")
results = knowledge.search("authentication", limit=5)

Knowledge Stack Features Table

🔧 Technical Details

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

Knowledge CLI Commands {#knowledge-cli}

Knowledge Query Flags:

Examples:

# Add documents
praisonai knowledge add document.pdf
praisonai knowledge add ./docs/
praisonai knowledge add "*.md"

# Query with options
praisonai knowledge query "How to authenticate?" \
  --vector-store chroma \
  --retrieval-strategy fusion \
  --reranker simple \
  --query-mode sub_question

Databases Table