S3-backed Nix binary cache with garbage collection

a Docker + Kubernetes network trouble-shooting swiss-army container

Warp is an agentic development environment, born out of the terminal.

Your local AI session library. Browse, pin, and ⌘K-search every Claude Code, Codex, Gemini & OpenCode session — and let the built-in scanner catch leaked secrets. Local-first, nothing leaves your m…

Core logic of Slay the Spire implemented in Lean4 for formal verification proofs

Claw-Eval is an evaluation harness for evaluating LLM as agents. All tasks verified by humans.

Official Implementation of "CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion"

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

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents

HTTP(s) request filter for processes

CL-bench: A Benchmark for Context Learning

KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)

k0s - The Zero Friction Kubernetes

Claude Code notifications without the context switch. A minimal, always-present session manager for macOS.

symbolic link maintenance utility

Windows 7 in the browser

Experimental new browser engine

Inference at the speed of light.

Photoshop 1.0 Source Code

The open source coding agent.

The Modern Application Platform.

omo/lazycodex: The coding agent for tokenmaxxers;the one and only agent harness for complex codebases. For your Codex, for your OpenCode

GG - Gui for JJ

Jujutsu (jj) VCS support for VS Code

Subset of Lerna in a smaller & more modular project. Help manage and publish multiple packages in a monorepo/workspace structure

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured