Open Source
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace.
Explore the latest AI open-source projects from GitHub and HuggingFace. Discover projects across categories like LLM, Vision, Audio, and more.
489 projects
OpenSRE is an open-source framework from Tracer Cloud for building AI Site Reliability Engineering (SRE) agents that autonomously investigate production incidents. Released in public alpha in 2026, it has accumulated 3,600 GitHub stars from platfo…
GenericAgent is a compact autonomous agent framework from Fudan University researchers, introduced in April 2026 via a GitHub release and an arXiv paper (2604.17091). At just 3,300 lines of core code, it achieves full local system control while co…
LangExtract is an open-source Python library from Google that uses large language models to extract precisely structured information from unstructured text documents. Released in February 2026 and now at v1.2.1, the library has already accumulated…
Gemini CLI is an open-source AI agent developed by Google that integrates the full power of Gemini models directly into your terminal environment. Released under the Apache 2.0 license, it offers developers a free tier with 60 requests/minute and …
free-claude-code is an open-source Python proxy that allows developers to use Anthropic's Claude Code CLI, VSCode extension, and Discord bot entirely without a paid Anthropic API key. Built by the community and gaining 13,900 GitHub stars within d…
A curated collection of 50+ modular instruction bundles for automating workflows through OpenAI Codex CLI and API, enabling integration with 1000+ applications. Skills cover PR review, CI/CD, Linear, Notion, Slack, Datadog, and more using a progre…
Memori is agent-native memory infrastructure that converts agent execution and conversation into structured, persistent state. LLM-agnostic and framework-compatible (LangChain, Pydantic AI, Agno), it achieves 81.95% LoCoMo accuracy at only 4.97% o…
TileLang is a domain-specific language (DSL) for streamlining high-performance GPU/CPU/accelerator kernel development using Pythonic syntax with TVM compiler infrastructure. It supports GEMM, FlashAttention, LinearAttention, and sparse operations …
OpenAI
OpenAI Skills is the official Skills Catalog for Codex, implementing the Agent Skills open standard — a framework for packaging reusable capabilities that AI agents can discover and execute. The core principle is simple: write a skill once, use it…
Hugging Face
HuggingFace ML Intern is a fully autonomous AI agent developed by Hugging Face that operates as an independent machine learning engineer. It can research academic papers, generate ML code, train models, and deploy them — all without human interven…
Google ADK Samples is the official reference collection of production-quality agents built on top of Google's Agent Development Kit (ADK). The repository demonstrates how to build everything from simple conversational bots to complex multi-agent o…
Evolver is an open-source self-evolving engine for AI agents, built around the Genome Evolution Protocol (GEP) — a principled approach to making AI agents improve themselves over time without manual prompt engineering. Rather than directly modifyi…