vLLM Metal plugin powered by mlx-swift — high-performance LLM inference on Apple Silicon

Pi package inspired by Hermes Agent Self-Evolution with hybrid TypeScript + optional Python DSPy/GEPA backends.

GitNexus: The Zero-Server Code Intelligence Engine - GitNexus is a client-side knowledge graph creator that runs entirely in your browser. Drop in a GitHub repo or ZIP file, and get an interactive …

Web dashboard for Hermes Agent — multi-platform AI chat, session management, scheduled jobs, usage analytics & channel configuration (Telegram, Discord, Slack, WhatsApp)

AI-powered news aggregation and clustering system for San Jose Sharks hockey news

Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.

The first open-source harness builder for AI coding. Make AI coding deterministic and repeatable.

an open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM

A very fast, portable and hackable fuzzy finder.

Robust Speech Recognition via Large-Scale Weak Supervision

Context-isolated workflow automation for Pi coding agent

worktree coding agents command center.

Plan-Apply-Unify Loop — Structured AI-assisted development for Claude Code. Quality over speed-for-speed's-sake.

The operational layer for coding agents. Memory, validation, and feedback loops that compound between sessions.

AI project incubator for Claude Code — type-aware guided exploration from raw idea to structured plan, ready for PAUL-managed builds

Use your Claude Max subscription with OpenCode, Pi, Droid, Aider, Crush, Cline. Proxy that bridges Anthropic's official SDK to enable Claude Max in third-party tools.

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloning

Your personal AI assistant that remembers everything across Telegram, Slack, WhatsApp, and Signal

The memory-first coding agent

Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.

🚀🤖 Crawl4AI: Open-source LLM Friendly Web Crawler & Scraper. Don't be shy, join here: https://discord.gg/jP8KfhDhyN

Memory library for building stateful agents

Pop-up dictionary browser extension for language learning. Successor to Yomichan.

Use your locally running AI models to assist you in your web browsing

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

Minimal reproduction of DeepSeek R1-Zero