{"id":13634725,"url":"https://github.com/MervinPraison/PraisonAI","last_synced_at":"2025-04-18T23:32:49.927Z","repository":{"id":228633125,"uuid":"774497032","full_name":"MervinPraison/PraisonAI","owner":"MervinPraison","description":"PraisonAI is a production-ready Multi AI Agents framework, designed to create AI Agents to automate and solve problems ranging from simple tasks to complex challenges. It provides a low-code solution to streamline the building and management of multi-agent LLM systems, emphasising simplicity, customisation, and effective human-agent collaboration.","archived":false,"fork":false,"pushed_at":"2025-04-08T11:05:05.000Z","size":21867,"stargazers_count":4005,"open_issues_count":83,"forks_count":573,"subscribers_count":62,"default_branch":"main","last_synced_at":"2025-04-09T03:00:45.411Z","etag":null,"topics":["agents","ai","ai-agent-framework","ai-agent-sdk","ai-agents","ai-agents-framework","ai-agents-sdk","ai-framwork","aiagent","aiagentframework","aiagents","aiagentsframework","framework","multi-agent","multi-agent-collaboration","multi-agent-system","multi-agent-systems","multi-agents","multi-ai-agent","multi-ai-agents"],"latest_commit_sha":null,"homepage":"https://docs.praison.ai","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MervinPraison.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"docs/contributing.mdx","funding":".github/FUNDING.yml","license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null},"funding":{"patreon":"MervinPraison","ko_fi":"MervinPraison"}},"created_at":"2024-03-19T16:45:25.000Z","updated_at":"2025-04-09T01:19:27.000Z","dependencies_parsed_at":"2024-04-24T08:36:50.916Z","dependency_job_id":"e420b81e-c8b6-4ee3-99e4-cb419115341f","html_url":"https://github.com/MervinPraison/PraisonAI","commit_stats":null,"previous_names":["mervinpraison/praisonai"],"tags_count":169,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MervinPraison%2FPraisonAI","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MervinPraison%2FPraisonAI/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MervinPraison%2FPraisonAI/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MervinPraison%2FPraisonAI/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MervinPraison","download_url":"https://codeload.github.com/MervinPraison/PraisonAI/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":249565248,"owners_count":21292427,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agents","ai","ai-agent-framework","ai-agent-sdk","ai-agents","ai-agents-framework","ai-agents-sdk","ai-framwork","aiagent","aiagentframework","aiagents","aiagentsframework","framework","multi-agent","multi-agent-collaboration","multi-agent-system","multi-agent-systems","multi-agents","multi-ai-agent","multi-ai-agents"],"created_at":"2024-08-02T00:00:31.864Z","updated_at":"2025-04-18T23:32:49.891Z","avatar_url":"https://github.com/MervinPraison.png","language":"Jupyter Notebook","readme":"\u003cp align=\"center\"\u003e\n  \u003cpicture\u003e\n    \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\"docs/logo/dark.png\" /\u003e\n    \u003csource media=\"(prefers-color-scheme: light)\" srcset=\"docs/logo/light.png\" /\u003e\n    \u003cimg alt=\"PraisonAI Logo\" src=\"docs/logo/light.png\" /\u003e\n  \u003c/picture\u003e\n\u003c/p\u003e\n\n\u003cp align=\"center\"\u003e\n\u003ca href=\"https://github.com/MervinPraison/PraisonAI\"\u003e\u003cimg src=\"https://static.pepy.tech/badge/PraisonAI\" alt=\"Total Downloads\" /\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/MervinPraison/PraisonAI\"\u003e\u003cimg src=\"https://img.shields.io/github/v/release/MervinPraison/PraisonAI\" alt=\"Latest Stable Version\" /\u003e\u003c/a\u003e\n\u003ca href=\"https://github.com/MervinPraison/PraisonAI\"\u003e\u003cimg src=\"https://img.shields.io/badge/License-MIT-yellow.svg\" alt=\"License\" /\u003e\u003c/a\u003e\n\u003c/p\u003e\n\n\u003cdiv align=\"center\"\u003e\n\n# Praison AI\n\n\u003ca href=\"https://trendshift.io/repositories/9130\" target=\"_blank\"\u003e\u003cimg src=\"https://trendshift.io/api/badge/repositories/9130\" alt=\"MervinPraison%2FPraisonAI | Trendshift\" style=\"width: 250px; height: 55px;\" width=\"250\" height=\"55\"/\u003e\u003c/a\u003e\n\n\u003c/div\u003e\n\nPraisonAI 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.\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://docs.praison.ai\"\u003e\n    \u003cp align=\"center\"\u003e\n      \u003cimg src=\"https://img.shields.io/badge/📚_Documentation-Visit_docs.praison.ai-blue?style=for-the-badge\u0026logo=bookstack\u0026logoColor=white\" alt=\"Documentation\" /\u003e\n    \u003c/p\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\n## Key Features\n\n- 🤖 Automated AI Agents Creation\n- 🔄 Self Reflection AI Agents\n- 🧠 Reasoning AI Agents\n- 👁️ Multi Modal AI Agents\n- 🤝 Multi Agent Collaboration\n- 🎭 AI Agent Workflow\n- 📚 Add Custom Knowledge\n- 🧠 Agents with Short and Long Term Memory\n- 📄 Chat with PDF Agents\n- 💻 Code Interpreter Agents\n- 📚 RAG Agents\n- 🤔 Async \u0026 Parallel Processing\n- 🔄 Auto Agents\n- 🔢 Math Agents\n- 🎯 Structured Output Agents\n- 🔗 LangChain Integrated Agents\n- 📞 Callback Agents\n- 🤏 Mini AI Agents\n- 🛠️ 100+ Custom Tools\n- 📄 YAML Configuration\n- 💯 100+ LLM Support\n\n## Using Python Code\n\nLight weight package dedicated for coding:\n```bash\npip install praisonaiagents\n```\n\n```bash\nexport OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx\n```\n\n### 1. Single Agent\n\nCreate app.py file and add the code below:\n```python\nfrom praisonaiagents import Agent\nagent = Agent(instructions=\"Your are a helpful AI assistant\")\nagent.start(\"Write a movie script about a robot in Mars\")\n```\n\nRun:\n```bash\npython app.py\n```\n\n### 2. Multi Agents\n\nCreate app.py file and add the code below:\n```python\nfrom praisonaiagents import Agent, PraisonAIAgents\n\nresearch_agent = Agent(instructions=\"Research about AI\")\nsummarise_agent = Agent(instructions=\"Summarise research agent's findings\")\nagents = PraisonAIAgents(agents=[research_agent, summarise_agent])\nagents.start()\n```\n\nRun:\n```bash\npython app.py\n```\n\n## Using No Code\n\n### Auto Mode:\n```bash\npip install praisonai\nexport OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx\npraisonai --auto create a movie script about Robots in Mars\n```\n\n## Using JavaScript Code\n\n```bash\nnpm install praisonai\nexport OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxx\n```\n\n```javascript\nconst { Agent } = require('praisonai');\nconst agent = new Agent({ instructions: 'You are a helpful AI assistant' });\nagent.start('Write a movie script about a robot in Mars');\n```\n\n![PraisonAI CLI Demo](docs/demo/praisonai-cli-demo.gif)\n\n## AI Agents Flow\n\n```mermaid\ngraph LR\n    %% Define the main flow\n    Start([▶ Start]) --\u003e Agent1\n    Agent1 --\u003e Process[⚙ Process]\n    Process --\u003e Agent2\n    Agent2 --\u003e Output([✓ Output])\n    Process -.-\u003e Agent1\n    \n    %% Define subgraphs for agents and their tasks\n    subgraph Agent1[ ]\n        Task1[📋 Task]\n        AgentIcon1[🤖 AI Agent]\n        Tools1[🔧 Tools]\n        \n        Task1 --- AgentIcon1\n        AgentIcon1 --- Tools1\n    end\n    \n    subgraph Agent2[ ]\n        Task2[📋 Task]\n        AgentIcon2[🤖 AI Agent]\n        Tools2[🔧 Tools]\n        \n        Task2 --- AgentIcon2\n        AgentIcon2 --- Tools2\n    end\n\n    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff\n    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff\n    classDef tools fill:#2E8B57,stroke:#7C90A0,color:#fff\n    classDef transparent fill:none,stroke:none\n\n    class Start,Output,Task1,Task2 input\n    class Process,AgentIcon1,AgentIcon2 process\n    class Tools1,Tools2 tools\n    class Agent1,Agent2 transparent\n```\n\n## AI Agents with Tools\n\nCreate AI agents that can use tools to interact with external systems and perform actions.\n\n```mermaid\nflowchart TB\n    subgraph Tools\n        direction TB\n        T3[Internet Search]\n        T1[Code Execution]\n        T2[Formatting]\n    end\n\n    Input[Input] ---\u003e Agents\n    subgraph Agents\n        direction LR\n        A1[Agent 1]\n        A2[Agent 2]\n        A3[Agent 3]\n    end\n    Agents ---\u003e Output[Output]\n\n    T3 --\u003e A1\n    T1 --\u003e A2\n    T2 --\u003e A3\n\n    style Tools fill:#189AB4,color:#fff\n    style Agents fill:#8B0000,color:#fff\n    style Input fill:#8B0000,color:#fff\n    style Output fill:#8B0000,color:#fff\n```\n\n## AI Agents with Memory\n\nCreate AI agents with memory capabilities for maintaining context and information across tasks.\n\n```mermaid\nflowchart TB\n    subgraph Memory\n        direction TB\n        STM[Short Term]\n        LTM[Long Term]\n    end\n\n    subgraph Store\n        direction TB\n        DB[(Vector DB)]\n    end\n\n    Input[Input] ---\u003e Agents\n    subgraph Agents\n        direction LR\n        A1[Agent 1]\n        A2[Agent 2]\n        A3[Agent 3]\n    end\n    Agents ---\u003e Output[Output]\n\n    Memory \u003c--\u003e Store\n    Store \u003c--\u003e A1\n    Store \u003c--\u003e A2\n    Store \u003c--\u003e A3\n\n    style Memory fill:#189AB4,color:#fff\n    style Store fill:#2E8B57,color:#fff\n    style Agents fill:#8B0000,color:#fff\n    style Input fill:#8B0000,color:#fff\n    style Output fill:#8B0000,color:#fff\n```\n\n## AI Agents with Different Processes\n\n### Sequential Process\n\nThe simplest form of task execution where tasks are performed one after another.\n\n```mermaid\ngraph LR\n    Input[Input] --\u003e A1\n    subgraph Agents\n        direction LR\n        A1[Agent 1] --\u003e A2[Agent 2] --\u003e A3[Agent 3]\n    end\n    A3 --\u003e Output[Output]\n\n    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff\n    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff\n    classDef transparent fill:none,stroke:none\n\n    class Input,Output input\n    class A1,A2,A3 process\n    class Agents transparent\n```\n\n### Hierarchical Process\n\nUses a manager agent to coordinate task execution and agent assignments.\n\n```mermaid\ngraph TB\n    Input[Input] --\u003e Manager\n    \n    subgraph Agents\n        Manager[Manager Agent]\n        \n        subgraph Workers\n            direction LR\n            W1[Worker 1]\n            W2[Worker 2]\n            W3[Worker 3]\n        end\n        \n        Manager --\u003e W1\n        Manager --\u003e W2\n        Manager --\u003e W3\n    end\n    \n    W1 --\u003e Manager\n    W2 --\u003e Manager\n    W3 --\u003e Manager\n    Manager --\u003e Output[Output]\n\n    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff\n    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff\n    classDef transparent fill:none,stroke:none\n\n    class Input,Output input\n    class Manager,W1,W2,W3 process\n    class Agents,Workers transparent\n```\n\n### Workflow Process\n\nAdvanced process type supporting complex task relationships and conditional execution.\n\n```mermaid\ngraph LR\n    Input[Input] --\u003e Start\n    \n    subgraph Workflow\n        direction LR\n        Start[Start] --\u003e C1{Condition}\n        C1 --\u003e |Yes| A1[Agent 1]\n        C1 --\u003e |No| A2[Agent 2]\n        A1 --\u003e Join\n        A2 --\u003e Join\n        Join --\u003e A3[Agent 3]\n    end\n    \n    A3 --\u003e Output[Output]\n\n    classDef input fill:#8B0000,stroke:#7C90A0,color:#fff\n    classDef process fill:#189AB4,stroke:#7C90A0,color:#fff\n    classDef decision fill:#2E8B57,stroke:#7C90A0,color:#fff\n    classDef transparent fill:none,stroke:none\n\n    class Input,Output input\n    class Start,A1,A2,A3,Join process\n    class C1 decision\n    class Workflow transparent\n```\n\n#### Agentic Routing Workflow\n\nCreate AI agents that can dynamically route tasks to specialized LLM instances.\n\n```mermaid\nflowchart LR\n    In[In] --\u003e Router[LLM Call Router]\n    Router --\u003e LLM1[LLM Call 1]\n    Router --\u003e LLM2[LLM Call 2]\n    Router --\u003e LLM3[LLM Call 3]\n    LLM1 --\u003e Out[Out]\n    LLM2 --\u003e Out\n    LLM3 --\u003e Out\n    \n    style In fill:#8B0000,color:#fff\n    style Router fill:#2E8B57,color:#fff\n    style LLM1 fill:#2E8B57,color:#fff\n    style LLM2 fill:#2E8B57,color:#fff\n    style LLM3 fill:#2E8B57,color:#fff\n    style Out fill:#8B0000,color:#fff\n```\n\n#### Agentic Orchestrator Worker\n\nCreate AI agents that orchestrate and distribute tasks among specialized workers.\n\n```mermaid\nflowchart LR\n    In[In] --\u003e Router[LLM Call Router]\n    Router --\u003e LLM1[LLM Call 1]\n    Router --\u003e LLM2[LLM Call 2]\n    Router --\u003e LLM3[LLM Call 3]\n    LLM1 --\u003e Synthesizer[Synthesizer]\n    LLM2 --\u003e Synthesizer\n    LLM3 --\u003e Synthesizer\n    Synthesizer --\u003e Out[Out]\n    \n    style In fill:#8B0000,color:#fff\n    style Router fill:#2E8B57,color:#fff\n    style LLM1 fill:#2E8B57,color:#fff\n    style LLM2 fill:#2E8B57,color:#fff\n    style LLM3 fill:#2E8B57,color:#fff\n    style Synthesizer fill:#2E8B57,color:#fff\n    style Out fill:#8B0000,color:#fff\n```\n\n#### Agentic Autonomous Workflow\n\nCreate AI agents that can autonomously monitor, act, and adapt based on environment feedback.\n\n```mermaid\nflowchart LR\n    Human[Human] \u003c--\u003e LLM[LLM Call]\n    LLM --\u003e|ACTION| Environment[Environment]\n    Environment --\u003e|FEEDBACK| LLM\n    LLM --\u003e Stop[Stop]\n    \n    style Human fill:#8B0000,color:#fff\n    style LLM fill:#2E8B57,color:#fff\n    style Environment fill:#8B0000,color:#fff\n    style Stop fill:#333,color:#fff\n```\n\n#### Agentic Parallelization\n\nCreate AI agents that can execute tasks in parallel for improved performance.\n\n```mermaid\nflowchart LR\n    In[In] --\u003e LLM2[LLM Call 2]\n    In --\u003e LLM1[LLM Call 1]\n    In --\u003e LLM3[LLM Call 3]\n    LLM1 --\u003e Aggregator[Aggregator]\n    LLM2 --\u003e Aggregator\n    LLM3 --\u003e Aggregator\n    Aggregator --\u003e Out[Out]\n    \n    style In fill:#8B0000,color:#fff\n    style LLM1 fill:#2E8B57,color:#fff\n    style LLM2 fill:#2E8B57,color:#fff\n    style LLM3 fill:#2E8B57,color:#fff\n    style Aggregator fill:#fff,color:#000\n    style Out fill:#8B0000,color:#fff\n```\n\n#### Agentic Prompt Chaining\n\nCreate AI agents with sequential prompt chaining for complex workflows.\n\n```mermaid\nflowchart LR\n    In[In] --\u003e LLM1[LLM Call 1] --\u003e Gate{Gate}\n    Gate --\u003e|Pass| LLM2[LLM Call 2] --\u003e|Output 2| LLM3[LLM Call 3] --\u003e Out[Out]\n    Gate --\u003e|Fail| Exit[Exit]\n    \n    style In fill:#8B0000,color:#fff\n    style LLM1 fill:#2E8B57,color:#fff\n    style LLM2 fill:#2E8B57,color:#fff\n    style LLM3 fill:#2E8B57,color:#fff\n    style Out fill:#8B0000,color:#fff\n    style Exit fill:#8B0000,color:#fff\n```\n\n#### Agentic Evaluator Optimizer\n\nCreate AI agents that can generate and optimize solutions through iterative feedback.\n\n```mermaid\nflowchart LR\n    In[In] --\u003e Generator[LLM Call Generator] \n    Generator --\u003e|SOLUTION| Evaluator[LLM Call Evaluator] --\u003e|ACCEPTED| Out[Out]\n    Evaluator --\u003e|REJECTED + FEEDBACK| Generator\n    \n    style In fill:#8B0000,color:#fff\n    style Generator fill:#2E8B57,color:#fff\n    style Evaluator fill:#2E8B57,color:#fff\n    style Out fill:#8B0000,color:#fff\n```\n\n#### Repetitive Agents\n\nCreate AI agents that can efficiently handle repetitive tasks through automated loops.\n\n```mermaid\nflowchart LR\n    In[Input] --\u003e LoopAgent[(\"Looping Agent\")]\n    LoopAgent --\u003e Task[Task]\n    Task --\u003e |Next iteration| LoopAgent\n    Task --\u003e |Done| Out[Output]\n    \n    style In fill:#8B0000,color:#fff\n    style LoopAgent fill:#2E8B57,color:#fff,shape:circle\n    style Task fill:#2E8B57,color:#fff\n    style Out fill:#8B0000,color:#fff\n```\n\n## Adding Models\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://docs.praison.ai/models\"\u003e\n    \u003cp align=\"center\"\u003e\n      \u003cimg src=\"https://img.shields.io/badge/%F0%9F%93%9A_Models-Visit_docs.praison.ai-blue?style=for-the-badge\u0026logo=bookstack\u0026logoColor=white\" alt=\"Models\" /\u003e\n    \u003c/p\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\n## Ollama Integration\n```bash\nexport OPENAI_BASE_URL=http://localhost:11434/v1\n```\n\n## Groq Integration\nReplace xxxx with Groq API KEY:\n```bash\nexport OPENAI_API_KEY=xxxxxxxxxxx\nexport OPENAI_BASE_URL=https://api.groq.com/openai/v1\n```\n\n## No Code Options\n\n## Agents Playbook\n\n### Simple Playbook Example\n\nCreate `agents.yaml` file and add the code below:\n\n```yaml\nframework: praisonai\ntopic: Artificial Intelligence\nroles:\n  screenwriter:\n    backstory: \"Skilled in crafting scripts with engaging dialogue about {topic}.\"\n    goal: Create scripts from concepts.\n    role: Screenwriter\n    tasks:\n      scriptwriting_task:\n        description: \"Develop scripts with compelling characters and dialogue about {topic}.\"\n        expected_output: \"Complete script ready for production.\"\n```\n\n*To run the playbook:*\n```bash\npraisonai agents.yaml\n```\n\n## Use 100+ Models\n\n- https://docs.praison.ai/models/\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://docs.praison.ai\"\u003e\n    \u003cp align=\"center\"\u003e\n      \u003cimg src=\"https://img.shields.io/badge/📚_Documentation-Visit_docs.praison.ai-blue?style=for-the-badge\u0026logo=bookstack\u0026logoColor=white\" alt=\"Documentation\" /\u003e\n    \u003c/p\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\n## Development:\n\nBelow is used for development only.\n\n### Using uv\n```bash\n# Install uv if you haven't already\npip install uv\n\n# Install from requirements\nuv pip install -r pyproject.toml\n\n# Install with extras\nuv pip install -r pyproject.toml --extra code\nuv pip install -r pyproject.toml --extra \"crewai,autogen\"\n```\n\n## Contributing\n\n- Fork on GitHub: Use the \"Fork\" button on the repository page.\n- Clone your fork: `git clone https://github.com/yourusername/praisonAI.git`\n- Create a branch: `git checkout -b new-feature`\n- Make changes and commit: `git commit -am \"Add some feature\"`\n- Push to your fork: `git push origin new-feature`\n- Submit a pull request via GitHub's web interface.\n- Await feedback from project maintainers.\n\n## Other Features\n\n- 🔄 Use CrewAI or AG2 (Formerly AutoGen) Framework\n- 💻 Chat with ENTIRE Codebase\n- 🎨 Interactive UIs\n- 📄 YAML-based Configuration\n- 🛠️ Custom Tool Integration\n- 🔍 Internet Search Capability (using Crawl4AI and Tavily)\n- 🖼️ Vision Language Model (VLM) Support\n- 🎙️ Real-time Voice Interaction\n\n## Star History\n\n[![Star History Chart](https://api.star-history.com/svg?repos=MervinPraison/PraisonAI\u0026type=Date)](https://docs.praison.ai)\n\n## Video Tutorials\n\n| Topic | Video |\n|-------|--------|\n| AI Agents with Self Reflection | [![Self Reflection](https://img.youtube.com/vi/vLXobEN2Vc8/0.jpg)](https://www.youtube.com/watch?v=vLXobEN2Vc8) |\n| Reasoning Data Generating Agent | [![Reasoning Data](https://img.youtube.com/vi/fUT332Y2zA8/0.jpg)](https://www.youtube.com/watch?v=fUT332Y2zA8) |\n| AI Agents with Reasoning | [![Reasoning](https://img.youtube.com/vi/KNDVWGN3TpM/0.jpg)](https://www.youtube.com/watch?v=KNDVWGN3TpM) |\n| Multimodal AI Agents | [![Multimodal](https://img.youtube.com/vi/hjAWmUT1qqY/0.jpg)](https://www.youtube.com/watch?v=hjAWmUT1qqY) |\n| AI Agents Workflow | [![Workflow](https://img.youtube.com/vi/yWTH44QPl2A/0.jpg)](https://www.youtube.com/watch?v=yWTH44QPl2A) |\n| Async AI Agents | [![Async](https://img.youtube.com/vi/VhVQfgo00LE/0.jpg)](https://www.youtube.com/watch?v=VhVQfgo00LE) |\n| Mini AI Agents | [![Mini](https://img.youtube.com/vi/OkvYp5aAGSg/0.jpg)](https://www.youtube.com/watch?v=OkvYp5aAGSg) |\n| AI Agents with Memory | [![Memory](https://img.youtube.com/vi/1hVfVxvPnnQ/0.jpg)](https://www.youtube.com/watch?v=1hVfVxvPnnQ) |\n| Repetitive Agents | [![Repetitive](https://img.youtube.com/vi/dAYGxsjDOPg/0.jpg)](https://www.youtube.com/watch?v=dAYGxsjDOPg) |\n| Introduction | [![Introduction](https://img.youtube.com/vi/Fn1lQjC0GO0/0.jpg)](https://www.youtube.com/watch?v=Fn1lQjC0GO0) |\n| Tools Overview | [![Tools Overview](https://img.youtube.com/vi/XaQRgRpV7jo/0.jpg)](https://www.youtube.com/watch?v=XaQRgRpV7jo) |\n| Custom Tools | [![Custom Tools](https://img.youtube.com/vi/JSU2Rndh06c/0.jpg)](https://www.youtube.com/watch?v=JSU2Rndh06c) |\n| Firecrawl Integration | [![Firecrawl](https://img.youtube.com/vi/UoqUDcLcOYo/0.jpg)](https://www.youtube.com/watch?v=UoqUDcLcOYo) |\n| User Interface | [![UI](https://img.youtube.com/vi/tg-ZjNl3OCg/0.jpg)](https://www.youtube.com/watch?v=tg-ZjNl3OCg) |\n| Crawl4AI Integration | [![Crawl4AI](https://img.youtube.com/vi/KAvuVUh0XU8/0.jpg)](https://www.youtube.com/watch?v=KAvuVUh0XU8) |\n| Chat Interface | [![Chat](https://img.youtube.com/vi/sw3uDqn2h1Y/0.jpg)](https://www.youtube.com/watch?v=sw3uDqn2h1Y) |\n| Code Interface | [![Code](https://img.youtube.com/vi/_5jQayO-MQY/0.jpg)](https://www.youtube.com/watch?v=_5jQayO-MQY) |\n| Mem0 Integration | [![Mem0](https://img.youtube.com/vi/KIGSgRxf1cY/0.jpg)](https://www.youtube.com/watch?v=KIGSgRxf1cY) |\n| Training | [![Training](https://img.youtube.com/vi/aLawE8kwCrI/0.jpg)](https://www.youtube.com/watch?v=aLawE8kwCrI) |\n| Realtime Voice Interface | [![Realtime](https://img.youtube.com/vi/frRHfevTCSw/0.jpg)](https://www.youtube.com/watch?v=frRHfevTCSw) |\n| Call Interface | [![Call](https://img.youtube.com/vi/m1cwrUG2iAk/0.jpg)](https://www.youtube.com/watch?v=m1cwrUG2iAk) |\n| Reasoning Extract Agents | [![Reasoning Extract](https://img.youtube.com/vi/2PPamsADjJA/0.jpg)](https://www.youtube.com/watch?v=2PPamsADjJA) |\n\n","funding_links":["https://patreon.com/MervinPraison","https://ko-fi.com/MervinPraison"],"categories":["AI Agent Frameworks","Python","开源工具","Large Language Models (LLMs)","LLMOps","Machine Learning","Jupyter Notebook","A01_文本生成_文本对话","Frameworks","AI","Tools \u0026 Code","Repos","Multi-Agent \u0026 Orchestration","Tools","Projects","AI Agent Frameworks \u0026 SDKs","Agent Categories","MCP Frameworks and libraries","🌟 Core Frameworks","📦 Isolate Context"],"sub_categories":["General Agent Frameworks","RAG框架","Autonomous LLM Agents","Observability","大语言对话模型及数据","Other IDEs","General-Purpose Machine Learning","Multi-Agent Collaboration Systems","Tools","\u003ca name=\"Unclassified\"\u003e\u003c/a\u003eUnclassified","Python","Multi-Agent Frameworks"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMervinPraison%2FPraisonAI","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FMervinPraison%2FPraisonAI","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FMervinPraison%2FPraisonAI/lists"}