> ## Documentation Index > Fetch the complete documentation index at: https://docs.praison.ai/llms.txt > Use this file to discover all available pages before exploring further. # Complete Reference > Comprehensive reference documentation for PraisonAI including all features, diagrams, and examples.
PraisonAI Logo PraisonAI Logo
Total Downloads
GitHub Stars
GitHub Forks
MervinPraison/PraisonAI | Trendshift ## Key Features Automated creation and management of AI agents with self-reflection capabilities Sequential, parallel, hierarchical, and custom workflow orchestration Support for 100+ Language Learning Models Chat with your entire codebase using advanced context understanding Rich, interactive user interfaces for better control and monitoring YAML-based configuration for easy setup and customization Custom tool integration for extended functionality Internet search using Crawl4AI and Tavily ## Install ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} pip install praisonaiagents ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx ``` Create `app.py` file ## Code Example ```python Single Agent theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonaiagents import Agent agent = Agent(instructions="Your are a helpful AI assistant") agent.start("Write a movie script about a robot in Mars") ``` ```python Multi Agents theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonaiagents import Agent, AgentTeam research_agent = Agent(instructions="Research about AI") summarise_agent = Agent(instructions="Summarise research agent's findings") agents = AgentTeam(agents=[research_agent, summarise_agent]) agents.start() ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} python app.py ``` Install the No Code PraisonAI Package: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} pip install praisonaiagents ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} export OPENAI_API_KEY=your_openai_key ``` Create `agents.yaml`: ```yaml Single Agent theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} agents: # Canonical summarise_agent: instructions: Summarise Photosynthesis ``` ```yaml Multiple Agents theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} agents: # Canonical diet_agent: instructions: Give me 5 healthy food recipes blog_agent: instructions: Write a blog post about the food recipes ``` You can automatically create `agents.yaml` using: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai --init "your task description" ``` Execute your config: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai agents.yaml ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} npm install praisonai ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx ``` Create `app.js` file ## Code Example ```javascript Single Agent theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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'); ``` ```javascript Multi AgentTeam theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} const { Agent, AgentTeam } = require('praisonai'); const researchAgent = new Agent({ instructions: 'Research about AI' }); const summariseAgent = new Agent({ instructions: 'Summarise research agent\'s findings' }); const agents = new AgentTeam({ agents: [researchAgent, summariseAgent] }); agents.start(); ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} node app.js ``` ```bash npm theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} npm install praisonai ``` ```bash yarn theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} yarn add praisonai ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx ``` Create `app.ts` file ## Code Example ```javascript Single Agent theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} import { Agent } from 'praisonai'; const agent = new Agent({ instructions: `You are a creative writer who writes short stories with emojis.`, name: "StoryWriter" }); agent.start("Write a story about a time traveler") ``` ```javascript Multi AgentTeam theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} import { Agent, AgentTeam } from 'praisonai'; const storyAgent = new Agent({ instructions: "Generate a very short story (2-3 sentences) about artificial intelligence with emojis.", name: "StoryAgent" }); const summaryAgent = new Agent({ instructions: "Summarize the provided AI story in one sentence with emojis.", name: "SummaryAgent" }); const agents = new AgentTeam({ agents: [storyAgent, summaryAgent] }); agents.start() ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} npx ts-node app.ts ``` *** ## How Execution Works PraisonAI offers multiple ways to run AI agents. Choose the approach that fits your use case. ### 1. Agent Execution The simplest way to run AIβ€”create an agent and give it a task. ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonaiagents import Agent agent = Agent(instructions="You are a helpful assistant") agent.start("Summarize the latest AI news") ``` ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} flowchart LR User[User Input] --> Agent[AI Agent] Agent --> LLM[LLM Call] LLM --> Tools{Use Tools?} Tools -->|Yes| Tool[Execute Tool] Tool --> LLM Tools -->|No| Response[Response] Response --> User style User fill:#8B0000,color:#fff style Agent fill:#189AB4,color:#fff style LLM fill:#2E8B57,color:#fff style Tools fill:#2E8B57,color:#fff style Tool fill:#2E8B57,color:#fff style Response fill:#8B0000,color:#fff ``` Create single agents, configure instructions, add tools, and enable memory. ### 2. Workflow Execution For complex tasks, use **workflows** to chain multiple agents together. ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonaiagents import Agent, AgentFlow researcher = Agent(name="Researcher", instructions="Research topics") writer = Agent(name="Writer", instructions="Write content") workflow = AgentFlow(steps=[researcher, writer]) result = workflow.start("Write an article about AI trends") ``` ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} flowchart LR Input[Input] --> Step1[Agent 1] Step1 --> Step2[Agent 2] Step2 --> Step3[Agent 3] Step3 --> Output[Output] subgraph Patterns[Workflow Patterns] direction TB P1[Sequential] P2[Parallel] P3[Routing] P4[Loop] end style Input fill:#8B0000,color:#fff style Step1 fill:#189AB4,color:#fff style Step2 fill:#189AB4,color:#fff style Step3 fill:#189AB4,color:#fff style Output fill:#8B0000,color:#fff style Patterns fill:#2E8B57,color:#fff ``` Build multi-step workflows with routing, parallel execution, loops, and conditionals. ### 3. Agent Recipes **Recipes** are pre-built, production-ready AI tools you can run instantly. 55+ recipes available. ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # List available recipes praisonai recipe list # Run a recipe praisonai recipe run ai-blog-generator --input '{"topic": "AI trends"}' ``` ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} flowchart LR subgraph Discovery[Recipe Discovery] Custom[Custom Recipes] Local[~/.praisonai/templates] Builtin[Built-in Recipes] end Discovery --> Runner[Recipe Runner] Runner --> Validate[Validate Input] Validate --> Execute[Execute] Execute --> Output[JSON Output] style Discovery fill:#189AB4,color:#fff style Runner fill:#2E8B57,color:#fff style Validate fill:#2E8B57,color:#fff style Execute fill:#2E8B57,color:#fff style Output fill:#8B0000,color:#fff ``` 55+ production-ready AI tools for video, documents, images, code, and more. ### 4. Custom Tools Extend agent capabilities by creating **custom tools**. ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonaiagents import Agent def search_web(query: str) -> str: """Search the web for information.""" return f"Results for: {query}" agent = Agent( instructions="You are a research assistant", tools=[search_web] ) agent.start("Find the latest news about Python") ``` ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} flowchart TB Agent[AI Agent] --> Decision{Need External Data?} Decision -->|Yes| SelectTool[Select Tool] SelectTool --> Execute[Execute Tool] Execute --> Result[Tool Result] Result --> Agent Decision -->|No| Response[Generate Response] subgraph ToolTypes[Tool Types] direction LR T1[Search] T2[File I/O] T3[Database] T4[API Calls] end style Agent fill:#189AB4,color:#fff style Decision fill:#2E8B57,color:#fff style SelectTool fill:#2E8B57,color:#fff style Execute fill:#2E8B57,color:#fff style Result fill:#2E8B57,color:#fff style Response fill:#8B0000,color:#fff style ToolTypes fill:#189AB4,color:#fff ``` Create custom tools, use built-in tools, and integrate with external APIs. *** ## Feature Map ### Python SDK (praisonaiagents) Create a single AI agent Coordinate multiple agents Build multi-step pipelines Persistent agent memory Document retrieval Safety and validation ### Tools Ecosystem Search the internet Read/write files Run Python code Query databases Build your own Browse all tools ### MCP (Model Context Protocol) What is MCP? Local process communication HTTP streaming GitHub integration Build MCP servers Expose agents via MCP ### Deploy Deployment options HTTP API for agents Deploy as MCP server Agent-to-agent communication Container deployment AWS, Azure, GCP ### JavaScript/TypeScript SDK Getting started TypeScript guide Create agents Add tools Agent memory Multi-step workflows *** ## CLI at a Glance ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Install CLI pip install praisonai # Run an agent with a prompt praisonai "Summarize the latest AI news" # Run agents from YAML config praisonai agents.yaml # Start interactive mode praisonai --auto # Deep research mode praisonai --deep-research "What are the latest AI trends?" # List available recipes praisonai recipe list # Start agent server praisonai serve ``` | Command | Description | | --------------------------- | --------------------- | | `praisonai "prompt"` | Run agent with prompt | | `praisonai agents.yaml` | Run from YAML config | | `praisonai --auto` | Interactive auto mode | | `praisonai --deep-research` | Deep research mode | | `praisonai recipe list` | List recipes | | `praisonai recipe run` | Run a recipe | | `praisonai serve` | Start HTTP server | | `praisonai mcp list` | List MCP servers | Complete documentation for all CLI commands and options. *** ## AI Agents Flow ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} graph LR %% Define the main flow Start([β–Ά Start]) --> Agent1 Agent1 --> Process[βš™ Process] Process --> Agent2 Agent2 --> Output([βœ“ Output]) Process -.-> Agent1 %% Define subgraphs for agents and their tasks subgraph Agent1[ ] Task1[πŸ“‹ Task] AgentIcon1[πŸ€– AI Agent] Tools1[πŸ”§ Tools] Task1 --- AgentIcon1 AgentIcon1 --- Tools1 end subgraph Agent2[ ] Task2[πŸ“‹ Task] AgentIcon2[πŸ€– AI Agent] Tools2[πŸ”§ Tools] Task2 --- AgentIcon2 AgentIcon2 --- Tools2 end classDef input fill:#8B0000,stroke:#7C90A0,color:#fff classDef process fill:#189AB4,stroke:#7C90A0,color:#fff classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff classDef transparent fill:none,stroke:none class Start,Output,Task1,Task2 input class Process,AgentIcon1,AgentIcon2 process class Tools1,Tools2 tools class Agent1,Agent2 transparent ``` ## AI Agents with Tools Create AI agents that can use tools to interact with external systems and perform actions. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Create AI agents with memory capabilities for maintaining context and information across tasks. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 The simplest form of task execution where tasks are performed one after another. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Uses a manager agent to coordinate task execution and agent assignments. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Advanced process type supporting complex task relationships and conditional execution. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Create AI agents that can dynamically route tasks to specialized LLM instances. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Create AI agents that orchestrate and distribute tasks among specialized workers. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Create AI agents that can autonomously monitor, act, and adapt based on environment feedback. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Create AI agents that can execute tasks in parallel for improved performance. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Create AI agents with sequential prompt chaining for complex workflows. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Create AI agents that can generate and optimize solutions through iterative feedback. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 Create AI agents that can efficiently handle repetitive tasks through automated loops. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} 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 ```