An autonomous multi-agent system for 24/7 vulnerability discovery that uses LLMs to orchestrate security tools and filters results through an AI reviewer for human approval.

A collection of 18 plugins for Claude Code that extend its functionality with tools for bypassing web blocks, extracting design systems, and automating product research and planning.

An open-source compliance platform that automates evidence collection and policy management for frameworks like SOC 2, ISO 27001, HIPAA, and GDPR.

Mamba is a linear-time sequence modeling architecture based on selective state space models (SSMs) that provides a high-performance, subquadratic alternative to Transformers.

Claude Code Harness is a Go‑native plugin that orchestrates Claude‑based (or compatible) AI agents through a disciplined loop—plan, work, review, sync, release—while enforcing strong guardrails and human approvals at each step. It supports Claude Code, Codex CLI, Cursor, and Grok, generating specs, running AI‑driven implementations, independently reviewing changes, and packaging verified releases.

A Codex Plugin installation entry point that provides AI agents with the tools and methods needed to perform video editing via the chengfeng-videocut runtime.

Open Island is a free, native macOS app that lives in the notch or menu bar and provides a live dashboard for AI coding agents (Claude Code, Codex, Cursor, Gemini‑CLI, etc.). It shows session status, handles permission prompts, displays usage stats, and lets you jump back to the exact terminal or IDE pane with a click. Integration is hook‑based: agents emit JSON events, a tiny CLI forwards them via Unix socket to the app, which updates its UI. Supports 13 agents and 15+ terminals/IDEs, runs locally with no telemetry, and is distributed as a signed DMG or Homebrew cask.

Empryo is a graph-powered AI coding agent that maps entire codebases to understand dependencies and blast radius, enabling precise AST-level edits with lower token costs.

A powerful workflow system for OpenClaw that provides over 100 prebuilt, deterministic automation routines to turn an AI agent into a proactive personal assistant.

An open-source observability and self-improving layer for AI agents that detects production failures, root-causes them to source code, and opens verified fix PRs.

A comprehensive Python library for anomaly detection across multiple data modalities, featuring an agentic workflow for AI-driven outlier investigation.

A fast, rootless, daemonless container runtime and sandbox designed for executing AI agent tool-calls and generated code with kernel-enforced isolation in under 4ms.

A ready-to-use desktop client for DeepSeek Harness that bundles a standalone Node.js runtime, providing a native application experience for Windows and macOS without requiring manual environment setup.

AssetOpsBench is an open‑source benchmark/framework for building, orchestrating, and evaluating LLM‑based AI agents that operate on industrial asset‑management data (sensors, work orders, failure modes, etc.). It provides domain‑specific MCP tool servers, several ReAct‑style agent back‑ends, 141+ realistic scenarios, and a multi‑dimensional evaluation pipeline used in KDD/AAAI/NeurIPS competitions.

A local personal memory engine for AI coding agents that records conversations verbatim and provides persistent, context-aware recall without relying on cloud APIs.

An all-atom biomolecular foundation model that uses co-folding for structure prediction, design, and optimization in drug discovery.

An interactive coding platform for practicing PyTorch implementations of operators and architectures from scratch to prepare for ML engineering interviews.

A tool that simulates DLSS Upscaling and Frame Generation on any DirectX 12 compatible GPU for games that natively support DLSS2 and DLSS3.

A typeface and encoding system that protects written work by serving decoy text to AI scrapers while rendering the original words for human readers.

A high-performance multi-model DBMS that supports graph, document, key-value, time-series, and vector data in a single ACID-compliant engine.

A cloud infrastructure and deployment platform that allows users to provision servers and deploy apps across multiple clouds, featuring an MCP server for AI-agent managed DevOps.

A framework for designing the structural topology of AI agents, combining a 9-stage knowledge graph pipeline for memory and task-graph patterns for execution orchestration.

An open-source humanoid robot project providing the CAD, simulation models, and software needed to build and customize a 1.2m bipedal robot.

A comprehensive benchmarking tool for generative AI models that measures throughput and latency across various inference solutions using real-world workloads and production traces.

An AI-native remote desktop tool with a built-in MCP server that enables AI agents to view and control remote computers globally.

An open-source hybrid scientific research agent that combines JSON orchestration with persistent Python and R kernels for complex scientific computation and analysis.

A system that turns an Obsidian vault into a persistent, external memory for AI agents, allowing them to remember information across sessions without context limits.

A tool that converts text corpora into interactive knowledge graphs of concepts using local LLMs, enabling advanced text analysis and Graph RAG.

SuperMew is a self‑hosted, audit‑first RAG/agent platform. It persists threads, runs, events and document versions, offers hybrid Milvus+BM25 retrieval, supports HITL checkpoints, versioned skills/tools, a frozen model control plane, and a built‑in evaluation framework. The stack uses FastAPI, PostgreSQL, Redis, Milvus, and a Vue 3 frontend, and can be run locally with Docker‑Compose or deployed in production with systemd/K8s.

An open-source, multi-provider terminal coding agent built in Rust that provides a high-performance AI pair programmer with editor integration via the Agent Client Protocol.

A secure, personal AI assistant that stores data locally and uses WASM sandboxing to run tools safely and privately.

A TypeScript-Go toolchain that integrates type-checking, linting, and compiler-powered plugins to streamline builds and provide AI agents with a structured knowledge graph of the code.

A collection of ComfyUI custom nodes that provide API-based access to a wide array of frontier AI models for image, video, audio, and 3D generation.

DocsGPT is an open‑source, privacy‑focused platform that lets you ingest many document types (PDF, Word, spreadsheets, web pages, audio, etc.) and query them with any LLM. It provides a Flask backend, a React UI, speech‑to‑text, citation‑backed answers, pre‑built chat widgets, and enterprise‑grade deployment options (Docker, Kubernetes, RBAC, OIDC).

A full-stack toolkit for building and deploying AI agent services, combining LangGraph for agent logic, FastAPI for the API, and Streamlit for the chat interface.

A collection of open-source Claude Code skills for automating B2B cold email infrastructure, lead sourcing, copywriting, and campaign operations.

A comprehensive skill set for AI assistants that automates the entire MCU firmware development lifecycle, including building, flashing, and debugging across various toolchains.

A collection of structured AI agent skills for founders and indie operators to automate business strategy, research, and personal productivity workflows.

A large-scale simulation framework for training and benchmarking generalist robots to perform everyday kitchen tasks using diverse scenes, objects, and extensive demonstration data.

A high-efficiency communication protocol that unifies publish/subscribe, geo-distributed storage, and computation for distributed systems.

A Zotero plugin and MCP server that allows AI assistants to search, extract content from, and manage your local reference library for enhanced academic research.

A Codex image generation skill that transforms photos or text into retro illustrations with the aesthetic of early CRT computer interfaces.

A native macOS app that provides a graphical interface for managing, creating, and booting virtual iPhones for iOS research using vphone-cli.

Sokuji is a cross‑platform desktop app and browser extension that provides real‑time two‑way speech translation for meetings. It can run fully offline using on‑device ASR, translation, and TTS models (WASM + WebGPU) or connect to cloud providers like OpenAI, Gemini, and Soniox. Supports 99+ languages for recognition, 55+ for translation, and 53 for TTS, works on Windows/macOS/Linux and Chrome/Edge, and offers privacy‑first local inference.

An open-source Python framework to evaluate, test, and monitor ML and LLM-powered systems, helping developers detect data drift and ensure output quality.

A MySQL-compatible state store for AI agents featuring hybrid vector and full-text search, high-concurrency streaming writes, and copy-on-write sandboxes for safe state exploration.

A modular, data-driven research simulator for autonomous driving that enables closed-loop testing of end-to-end AV policies with high-fidelity sensor simulation.

The XeSS 3 SDK is a set of AI-based technologies for real-time rendering that boosts frame rates and reduces input lag through super resolution and frame generation.