Best AI GitHub Repos
Browse 532 repos. Filter by type or sort.
khoj-ai/Khoj
Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free.
openai/openai-chatkit-advanced-samplesOfficial
Starter app to build with OpenAI ChatKit SDK
OpenBB-finance/OpenBB
Open Data Platform for analysts, quants and AI agents.
SalesforceAIResearch/agentforce-adlc
Agent Development Life Cycle — Build, deploy, test, and optimize Agentforce agents using Claude Code skills and Agent Script DSL.
google-labs-code/design.mdOfficial
A format specification for describing a visual identity to coding agents. DESIGN.md gives agents a persistent, structured understanding of a design system.
openai/gpt-ossOfficial
gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI
daytonaio/daytona
Daytona is a Secure and Elastic Infrastructure for Running AI-Generated Code
openai/build-hoursOfficial
Build hours code to share.
Automattic/build-with-wordpress
Build and manage WordPress websites and applications on your chosen AI surface.
spotify/save-to-spotify
Command line interface to save your personal media to Spotify.
openai/GABRIELOfficial
An official OpenAI toolkit for social scientists and data scientists to measure quantitative attributes in text, images, or audio using the GPT API.
openai/codex-plugin-ccOfficial
Use Codex from Claude Code to review code or delegate tasks.
superdesigndev/superdesign
AI Product Design Agent - Open Source
microsoft/dataverse
PowerShell module to simplify working with the Power Platform Dataverse Web API
Aider-AI/Aider
aider is AI pair programming in your terminal
VantaInc/vanta-mcp-plugin
Official Vanta plugin for Claude Code
openai/parameter-golfOfficial
Train the smallest LM you can that fits in 16MB. Best model wins!
openai/codex-universalOfficial
Base docker image used in Codex environments
openai/mle-benchOfficial
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
duckdb/duckdb-skills
DuckDB-powered skills for Claude Code: read any data file, attach and query DuckDB databases, search DuckDB/DuckLake docs, search past session logs, and install/update DuckDB extensions.
openai/frontier-evalsOfficial
OpenAI Frontier Evals
openai/swarmOfficial
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
openai/openai-apps-sdk-examplesOfficial
Example apps for the Apps SDK
microsoft/autogen
A programming framework for agentic AI
Everything AI. One email. Every Monday.
New tools. Model launches. Plugins. Repos. Tactics. The moves the sharpest builders are making right now, before everyone else. 5-minute read.