Zero-cloud AI memory that works everywhere. SQLite-backed. One pure-Python dependency.

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…

Infrastructure that's powering E2B Cloud.

Run Coding Agents in Sandboxes. Control Them Over HTTP. Supports Claude Code, Codex, OpenCode, and Amp.

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

Secure local dev environment for collaboration with AI coding agents

A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.

Open-source, secure environment with real-world tools for enterprise-grade agents.

Hindsight: Agent Memory That Learns

Multiplayer agent harness for work

Open-source developer platform to power your entire infra and turn scripts into webhooks, workflows and UIs. Fastest workflow engine (13x vs Airflow). Open-source alternative to Retool and Temporal.

Self-hosted AI workspace.

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality

A TTS that fits in your CPU (and pocket)

DeepTutor: Lifelong Personalized Tutoring. https://deeptutor.info/.

Gym-Anything: Turn any Software into an Agent Environment

TriAttention — Efficient long reasoning with trigonometric KV cache compression. Enables OpenClaw local deployment on memory-constrained GPUs.

Write HTML. Render video. Built for agents.

🚀 EvoAgentX: Building a Self-Evolving Ecosystem of AI Agents

Reference code for the Meta-Harness paper.

RAGChecker: A Fine-grained Framework For Diagnosing RAG

The agent that grows with you

Meta-Harness: 76.4% on Terminal-Bench 2.0 (Claude Opus 4.6)

Skills for Real Engineers. Straight from my .agents directory.

Official code for "SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization"

A distributed networking stack for connecting peers.

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing…