PaperBanana: Automating Academic Illustration For AI Scientists

Reverse engineer clean behavioral specs from any codebase

Iterative development methodology plugin for Claude Code — extracts requirements, defines walking skeleton, loops through audited sprints autonomously

Rust CLI that converts EPUBs to YAML-headed markdown with byte/line offsets per chapter, for token-efficient agent reading

An experimental agentic tool

Self-hosted bridge that lets you interact with AI coding agents (Claude Code, Codex, etc.) from messaging platforms (Telegram, Discord, etc.) via the Agent Client Protocol (ACP).

Agent harness to make your slop code well-engineered and beautiful.

Safest and fastest Python library for secp256k1 elliptic curve operations

Cloud-synced dashboards for OpenCode and Claude Code. Track sessions, search with semantic lookup, export eval datasets.

The best-benchmarked open-source AI memory system. And it's free.

TeachOpenCADD: a teaching platform for computer-aided drug design (CADD) using open source packages and data

Repository for the NodeMedic-FINE tool (NDSS'25).

RF Genesis: Zero-Shot Generalization of mmWave Sensing through Simulation-Based Data Synthesis and Generative Diffusion Models (SenSys'23)

Open-source Environment toolkit of claw-like agents, support task/harness generation and evaluation

stripe-mock is a mock HTTP server that responds like the real Stripe API. It can be used instead of Stripe's testmode to make test suites integrating with Stripe faster and less brittle.

Skills for the Gemini API, SDK and model/agent interactions

Tool for making it easy to work with lots of AI agents

Repository of Stargazer: A Scalable Model-Fitting Benchmark Environment for AI Agents under Astrophysical Constraints

Foundation for an open strong-agent platform: controllers, operators, skills, A2A, runtime, and graph execution.

Unite the knowledge of the world's top experts across every domain — to accelerate AI-driven scientific discovery.

Official repository for the General Robust Image Task (GRIT) Benchmark

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

Open-source implementation of AlphaEvolve

A benchmark for evaluating LLMs on open-ended CS problems. Exploring the Next Frontier of Computer Science.

kubernetes, reimplemented in Rust

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

Gas Town - multi-agent workspace manager

Ready-to-use harnesses for OpenReward environments