Alternatives and similar repositories for OpenManus

Users that are interested in OpenManus are comparing it to the libraries listed below

• camel-ai / owl
  🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
  ☆18,865Updated this week
• bytedance / UI-TARS-desktop
  The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
  ☆24,141Updated this week
• kortix-ai / suna
  Kortix – build, manage and train AI Agents.
  ☆19,158Updated this week
• microsoft / OmniParser
  A simple screen parsing tool towards pure vision based GUI agent
  ☆24,207Updated 4 months ago
• bytedance / deer-flow
  DeerFlow is a community-driven Deep Research framework, combining language models with tools like web search, crawling, and Python execut…
  ☆19,129Updated last week
• zilliztech / deep-searcher
  Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
  ☆7,324Updated 2 months ago
• QwenLM / Qwen-Agent
  Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.
  ☆12,920Updated 3 months ago
• OpenManus / OpenManus-RL
  A live stream development of RL tunning for LLM agents
  ☆3,814Updated 3 months ago
• camel-ai / camel
  🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org
  ☆15,452Updated this week
• mem0ai / mem0
  Universal memory layer for AI Agents
  ☆45,538Updated this week
• browser-use / web-ui
  🖥️ Run AI Agent in your browser.
  ☆15,441Updated 4 months ago
• bytedance / UI-TARS
  Pioneering Automated GUI Interaction with Native Agents
  ☆8,979Updated last week
• allenai / olmocr
  Toolkit for linearizing PDFs for LLM datasets/training
  ☆16,759Updated this week
• browser-use / browser-use
  🌐 Make websites accessible for AI agents. Automate tasks online with ease.
  ☆75,584Updated this week
• QwenLM / Qwen3
  Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
  ☆26,197Updated last week
• unslothai / unsloth
  Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama, Gemma, TTS 2x faster with 70% less VRAM.
  ☆50,714Updated this week
• cline / cline
  Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your p…
  ☆56,860Updated this week
• microsoft / autogen
  A programming framework for agentic AI
  ☆53,572Updated 3 months ago
• langgenius / dify
  Production-ready platform for agentic workflow development.
  ☆126,441Updated this week
• hiyouga / LlamaFactory
  Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
  ☆65,942Updated this week
• ConardLi / easy-dataset
  A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval
  ☆12,852Updated this week
• microsoft / graphrag
  A modular graph-based Retrieval-Augmented Generation (RAG) system
  ☆30,284Updated last week
• ScrapeGraphAI / Scrapegraph-ai
  Python scraper based on AI
  ☆22,279Updated last week
• BerriAI / litellm
  Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing a…
  ☆33,981Updated this week
• Mintplex-Labs / anything-llm
  The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
  ☆53,230Updated last week
• unclecode / crawl4ai
  🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN
  ☆58,569Updated this week
• RooCodeInc / Roo-Code
  Roo Code gives you a whole dev team of AI agents in your code editor.
  ☆21,775Updated this week
• assafelovic / gpt-researcher
  An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations.
  ☆24,894Updated last month
• huggingface / open-r1
  Fully open reproduction of DeepSeek-R1
  ☆25,825Updated last month
• jingyaogong / minimind
  🚀🚀 「大模型」2小时完全从0训练26M的小参数GPT！🌏 Train a 26M-parameter GPT from scratch in just 2h!
  ☆37,249Updated this week