Stars
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
No fortress, purely open ground. OpenManus is Coming.
Learn how to use CUA (our Computer Using Agent) via the API on multiple computer environments.
A lightweight, powerful framework for multi-agent workflows
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
20+ high-performance LLMs with recipes to pretrain, finetune and deploy at scale.
A simple screen parsing tool towards pure vision based GUI agent
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
A library for efficient similarity search and clustering of dense vectors.
Opiniated RAG for integrating GenAI in your apps 🧠 Focus on your product rather than the RAG. Easy integration in existing products with customisation! Any LLM: GPT4, Groq, Llama. Any Vectorstore: …
Typescript/React Library for AI Chat💬🚀
morph-labs / gpt-engineer
Forked from AntonOsika/gpt-engineerSpecify what you want it to build, the AI asks for clarification, and then builds it.
SigNoz is an open-source observability platform native to OpenTelemetry with logs, traces and metrics in a single application. An open-source alternative to DataDog, NewRelic, etc. 🔥 🖥. 👉 Open sour…
Twilio Webchat React App is an application that demonstrates a website chat widget built with Twilio's Conversations JS SDK, Twilio Paste Design library and Create React App.
Twilio Conversations Demo Web Application
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)
Decoupling Reasoning from Observations for Efficient Augmented Language Models
The official Python SDK for Model Context Protocol servers and clients
Model Context Protocol Servers
TensorZero creates a feedback loop for optimizing LLM applications — turning production data into smarter, faster, and cheaper models.
CrewAI agents that can plan your vacation.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Easily integrate your custom JWT auth service in NextJS app
JWA, JWS, JWE, JWT, JWK, JWKS for Node.js, Browser, Cloudflare Workers, Deno, Bun, and other Web-interoperable runtimes