Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Released model weights, reference implementations and architecture research.
Signals: large-language-models, llm, foundation-models, transformer, gpt, llama, mistral, qwen
1,475 results
🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with quadrillions of tokens tracked.
Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics
The agent-native LLM router for autonomous agents. 66 models (8 free), <1ms local routing, USDC payments on Base & Solana via x402.
The programming language for agents
🌐 The open-source Agentic browser; alternative to ChatGPT Atlas, Perplexity Comet, Dia.
The AI Toolkit for TypeScript. From the creators of Next.js, the AI SDK is a free open-source library for building AI-powered applications and agents
Open-source, community-driven agent harness
Lemonade helps users discover and run local AI apps by serving optimized LLMs right from their own GPUs and NPUs. Join our discord: https://discord.gg/5xXzkMu8Zk
Stop wasting tokens and re-explaining your project every session. Recall gives Claude Code durable memory — entirely offline.
LLMs and VLMs with MLX Swift
A LLM trained only on data from certain time periods to reduce modern bias
Open-source TypeScript terminal coding agent for DeepSeek-V4 — builds on DeepSeek's strong price-performance and ultra-cheap cache pricing, engineering byte-stable prefixes and cache-reusing forks so cross-session memory and a continuous self-correction layer add almost no token cost; 1M context, Skills/MCP/Hooks, Claude Code config compatible.
open-source agentic AI data assistant for the next generation of AI + Data products.
Let Claude (or any LLM) actually watch a video — scene-aware, deduplicated frames + transcript, from a URL or local file. Runs locally, MIT.
Build AI agents from first principles using a local LLM - no frameworks, no cloud APIs, no hidden reasoning.
A neurosymbolic perspective on LLMs
Modular Python framework for AI agents and workflows with chain-of-thought reasoning, tools, and memory.
Framework to build resilient language agents as graphs.
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
开箱即用的AI标书编写工具，标书AI生成工具，投标工具箱、知识库、标书查重、废标项检查，完全开源免费，欢迎使用
The pretty much "official" DSPy framework for Typescript
An AI-powered threat modeling tool that leverages OpenAI's GPT models to generate threat models for a given application based on the STRIDE methodology.
Go with your own intelligence - Go applications that directly integrate llama.cpp for local inference using hardware acceleration.
[ICLR 2026] RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation
24,523 repositories in the index in total.
