Stars
The highest-scoring AI memory system ever benchmarked. And it's free.
Talk to your Obsidian vault with local models. 8ms semantic lookup via Enzyme, ~2,400 lines of TypeScript, any OpenAI-compatible endpoint.
Model-agnostic MoE compression automation: build calibration bundles, run REAP/quantization/benchmark/publish stages, and render auditable reports.
[ICML 2024] Binoculars: Zero-Shot Detection of LLM-Generated Text
a recursive self-improving harness designed to help your agents (and future iterations of those agents) succeed on any task
A GPU-accelerated cross-platform terminal emulator and multiplexer written by @wez and implemented in Rust
CLI for Recursive Language Models (arXiv:2512.24601)
AI agents running research on single-GPU nanochat training automatically
Open-source orchestration for zero-human companies
Parallel rsync-like pull sync over SSH with resume
Symphony turns project work into isolated, autonomous implementation runs, allowing teams to manage work instead of supervising coding agents.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
A free and open source instant messaging and VoIP platform built for friends, groups, and communities. Self-hosting and more activity in this repository is coming very soon! See the README.
A sandboxed Python runtime for AI agents, written in Rust.
A powerful Telegram bot that provides remote access to Claude Code, enabling developers to interact with their projects from anywhere with full AI assistance and session persistence.
Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig
Fast, small, and fully autonomous AI personal assistant infrastructure, ANY OS, ANY PLATFORM — deploy anywhere, swap anything 🦀
Codebase for the paper "Biases in the Blind Spot: Detecting What LLMs Fail to Mention"
Lightweight coding agent that runs in your terminal