A motivational interviewing skill for AI agents. Helps work through ambivalence, stuckness, and decisions.

Sandboxed devcontainer for running Claude Code in bypass mode safely. Built for security audits and untrusted code review.

High-performance model counter

Fully automatic censorship removal for language models

an implementation of the ideas in Erik Meijer's "Guardians of the Agents: Formal Verification of AI Workflows" (Communications of the ACM, January 2026)

Fully automatic censorship removal for language models

Mellea is a library for writing generative programs.

A CLI issue tracker for AI Agents

Allow MCP clients like claude-desktop to use rooms to coordinate with other agents

Official implementation and models for OVIE (One View Is Enough! Monocular Training for In-the-Wild Novel View Generation)

Reference code for the Meta-Harness paper.

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

Official implementation of the paper 'Exploring Robust Features for Few-Shot Object Detection in Satellite Imagery'

A high-throughput and memory-efficient inference and serving engine for LLMs

Build and query a graph database representation of source code

Property-based testing for web and terminal UIs

Find issues worth your attention.

Repo for vLLM Hook, an vLLM plug-in for programming internal states of models deployed on vLLM

OBLITERATE THE CHAINS THAT BIND YOU

DASL — Data-Addressed Structures & Links

Why can't an AI agent harness ship systems thinking as a skill?

wandb-compatible single-process server, and a bad pun

Simple opinionated issue tracker for AI Agents

Run the rr debugger in a Linux VM on apple silicon macOS or in the cloud. Use the rr debugger without HW performance counters on x86-64 and aarch64. Tutorial Link 👇