Highlights
- Pro
Stars
Raw-Metal inference engine for Qwen3.8-Flash-Next on Apple M5: EXL3 weights, MTP, OpenAI + Anthropic APIs
Sushi engine runs very high quality quant model in Apple Silicon, using both STQ and EXL3 format with special tuning technology to achieve frontier sub 4 bits compression.
DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm
The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on App…
High performance coding agent harness written in Rust, built for heavy multi-agent dev workflows
Integrations between MongoDB, Atlas, LangChain, and LangGraph
Agent skill: make LLMs write docs in ASD-STE100 Simplified Technical
The MongoDB version of SQLite. The real MongoDB engine, embedded directly in your application.
Reliable model swapping for any local AI server. Chosen by thousands of users. Batteries included. If we don't have it, you probably don't need it.
Ask your terminal anything. A zero-friction CLI assistant for shell commands and developer questions.
A privacy-focused iOS app that raises awareness about what native apps can see
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
Find the local LLM that actually runs and performs best on your hardware. Ranked by real, recency-aware benchmarks, not parameter count. One command, run it instantly.
Run Pi-Hole + Unbound on Docker
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
The official repository of Mozilla's Firefox web browser.
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
Use the official MongoDB Skills with your favorite coding agent to build faster.
A desktop app for isolated, parallel agentic development
Ghostty for the web with xterm.js API compatibility
a secure dotenv—from the creator of `dotenv`
Blink is a self-hosted platform for building and running custom, in-house AI agents.
A tool/website/article by @kognise about how routing on the Internet works.
A Model Context Protocol server to connect to MongoDB databases and MongoDB Atlas Clusters.
NodeJS library for managing Atlas local environments.