An open standard for shared agent learning. Agents persist, share, and query collective knowledge so they stop rediscovering the same failures independently.

A persistent 18+ private HRP, whitelist only server based on SpaceStation 14.

The best ChatGPT that $100 can buy.

AI agents running research on single-GPU nanochat training automatically

An autonomous novel writing pipeline, by Hermes Agent

A Pokemon Place for Lenny.

Toolkit for the AI for Industry Challenge

Coding agent with lossless context management

Lossless Claw — LCM (Lossless Context Management) plugin for OpenClaw

OpenClaw-RL: Train any agent simply by talking

Various things I had to figure out recently to make things work better...

Run OpenClaw more securely inside NVIDIA OpenShell with managed inference

OpenShell is the safe, private runtime for autonomous AI agents.

Daemons with DX

Fully Managed OpenClaw Framework for all knowledge work ever. CRM Automation and Outreach agents. The only local productivity tool you need.

OpenClaw but it runs entirely on github actions

Accessible large language models via k-bit quantization for PyTorch.

OpenTelemetry Collector

A universal git-native AI agent framework. Your agent lives inside a git repo — identity, rules, memory, tools, and skills are all version-controlled files.

SWE-CI: Evaluating Agent Capabilities in Maintaining Codebases via Continuous Integration

🎥 Make videos programmatically with React

Blacksky fork of bluesky-social/atproto with AppView performance optimizations, caching, and community features

Fastest, smallest, and fully autonomous AI assistant infrastructure written in Zig

one million chessboards, synced for everyone

Skills for AI Evals to compliment the course: AI Evals For Engineers & PMs

Gossip-based service discovery (and more) for large distributed systems.

Recovery-Bench is a benchmark for evaluating the capability of LLM agents to recover from mistakes