The open-source managed agents platform. Turn coding agents into real teammates — assign tasks, track progress, compound skills.

A Python implementation of Google's TurboQuant framework (WIP)

Implementation of Band Split Roformer, SOTA Attention network for music source separation out of ByteDance AI Labs

open-arms-mini: cheap human like teleoperation device that supports human in the loop corrections

AI agents running research on Hugging Face infra

A vector index built on TurboQuant, written in Rust with Python bindings

Become a cracked AI/ML Research Engineer

mac code — Claude Code, but it runs on your Mac for free. 35B AI agent at 30 tok/s via Apple Silicon flash-paging. $0/month.

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

plotting on terminal

100M tokens. Infinite compute. Lowest val loss wins.

Allow all your Claude Codes to message each other ad-hoc!

Train the smallest LM you can that fits in 16MB. Best model wins!

A fast, helpful, and open-source document parser

Low-level unprivileged sandboxing tool used by Flatpak and similar projects

Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours

System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge

Curated list of datasets and tools for post-training.

Ghostty-based macOS terminal with vertical tabs and notifications for AI coding agents

An open-source Text2SQL tool that transforms natural language into SQL using graph-powered schema understanding. Ask your database questions in plain English, QueryWeaver handles the weaving.

A multi-agent AI system that teaches research judgment

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

"ClawWork: OpenClaw as Your AI Coworker - 💰 $15K earned in 11 Hours"

Pre-submission compliance scanner for the Apple App Store

Modalities, a PyTorch-native framework for distributed and reproducible foundation model training.

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"