Hierarchical agent loops with recursive self-organization.

An MCP server plus a CLI tool that indexes local code into a graph database to provide context to AI assistants.

Temporal service

LLM-supervised persistent memory for AI agents — graph-based recall, cross-session knowledge, single binary. Works with DeepSeek Harness, Claude Code, OpenClaw, and any agent runtime.

Humanoid Parkour — Apex competition (Bittensor Subnet 1). ONNX locomotion policies over procedural MuJoCo courses.

Paper trading simulator for Polymarket

A reproducibility lab for trading AI: published RL and LLM trading claims re-tested under a pre-registered protocol, with a causal benchmark and a live track.

replay generals.io game events on Redis for bot development

reference bot implementation for generals.io using a combination of heuristics and graph algorithms

Reverse engineer anything with agents, from app behavior down to native binaries.

Orca lets you run a fleet of coding agents (e.g. Claude Code, Codex) with your own subscription. Available on desktop, mobile and remote runtime.

Local voice dictation for mac, windows and linux

AI-Driven Scientific, Algorithmic, and Systems Discovery

Fully autonomous AI Agents system capable of performing complex penetration testing tasks

28 eval-informed mental models and critical-thinking skills for Claude Code, GitHub Copilot, Codex, Cursor, and other Agent Skills-compatible tools

AI coworkers that run your work. Self-hostable, AGPL-3.0.

Blazing fast Apple Silicon inference engine optimized for Qwen & Nemotron. OpenAI + Anthropic API compatible. Built by folks from nace.ai

Your iPhone helps your Mac run a 27B model: faster prompt reading and more context over a USB-C cable

JuiceFS is a distributed POSIX file system built on top of Redis and S3.

Measure and explain performance: web pages, Electron apps, Bun/Node, any process. Agent-native CLI + MCP.

learn LLM inference system on Apple Silicon for systems engineers: build a tiny vLLM + Qwen

AI Code Security Anti-Patterns distilled from 150+ sources to help LLMs generate safer code.

Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results

A self-modifying, durable agent that lives on your iPhone. Brain on the phone, hands on your machines.

A local coding agent with a web UI that builds itself while it runs, on Pi Durable

An open source, self-hosted implementation of the Tailscale control server

Run GLM-5.3 (744B), GLM-5.3-Flash (321B), DeepSeek-V4.1-Flash (748B) and MiniMax-M3.1-Flash (428B) on your own GPUs - one engine, one dashboard, OpenAI- and Anthropic-compatible API.

Open-source AI penetration testing tool to find and fix your app’s vulnerabilities.