Stars
Open Claude Is Open-source coding-agent CLI for OpenAI, Gemini, DeepSeek, Ollama, Codex, GitHub Models, and 200+ models via OpenAI-compatible APIs.
AI agent toolkit: coding agent CLI, unified LLM API, TUI & web UI libraries, Slack bot, vLLM pods
Roo Code gives you a whole dev team of AI agents in your code editor.
turbo-tan / llama.cpp-tq3
Forked from ggml-org/llama.cppllama.cpp fork with TQ3_1S/4S CUDA kernels — 3.5-bit WHT quantization achieving Q4s quality at 10% smaller size. Based on RaBitQ-inspired Walsh-Hadamard transform. Enables 27B models on 16GB GPUs w…
A coding agent optimized to smaller LLMs
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
DenchHQ / DenchClaw
Forked from openclaw/openclawFully Managed OpenClaw Framework for all knowledge work ever. CRM Automation and Outreach agents. The only local productivity tool you need.
Open-source orchestration for zero-human companies
Sloc, Cloc and Code: scc is a very fast accurate code counter with complexity calculations and COCOMO estimates written in pure Go
Accomplish™ is the open source Al coworker that lives on your desktop
AirLLM 70B inference with single 4GB GPU
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Seamlessly link any Trading Strategy in ANY programming language to Darwinex liquidity via MetaTrader 4 or 5. DWX Connect is your very own, fully customizable Trading API!
Lets make video diffusion practical!
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
ymichael / open-codex
Forked from openai/codexLightweight coding agent that runs in your terminal
UI Layouts isn’t just a library. It’s your complete front-end universe with components, effects, design tools, and ready-to-use blocks, everything you need to build modern interfaces, faster.
stackblitz-labs / bolt.diy
Forked from stackblitz/bolt.newPrompt, run, edit, and deploy full-stack web applications using any LLM you want!
iii unifies your existing backend stack with a single engine and three primitives: Function, Trigger, and Worker.
🦉 OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
Websocket using FastAPI, calling ollama LLM model for action to user responses.
This is the official repository for submitting MCP servers to be included in Cline's MCP Marketplace. If you’ve built an MCP server and want it to be discoverable and easily installable by millions…
SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer
100+ AI Agent & RAG apps you can actually run — clone, customize, ship.