Starred repositories
Lightweight coding agent that runs in your terminal
Simultaneous speech-to-text model
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
A list of Free Software network services and web applications which can be hosted on your own servers
😎 Awesome lists about all kinds of interesting topics
The ultimate training toolkit for finetuning diffusion models
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
A powerful multi-modal AI Agent system with modern architecture
Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…
An open-source AI agent that brings the power of Gemini directly into your terminal.
Agent samples built using the Strands Agents SDK.
A model-driven approach to building AI agents in just a few lines of code.
The open-source CapCut alternative
AdalFlow: The library to build & auto-optimize LLM applications.
An open protocol enabling communication and interoperability between opaque agentic applications.
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
Examples and guides for using the Gemini API
A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.
A powerful framework for building realtime voice AI agents 🤖🎙️📹
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.
[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)
📚 Freely available programming books
A TTS model capable of generating ultra-realistic dialogue in one pass.
A curated and opinionated list of resources for Chief Technology Officers, with the emphasis on startups
🚀 The fast, Pythonic way to build MCP servers and clients
Model Context Protocol Servers