Nano-vLLM is a lightweight, from-scratch implementation of a vLLM-style inference engine designed for fast offline inference with a highly readable codebase.

An open-source design for the SO-100 and SO-101 low-cost robot arms, designed for seamless integration with the LeRobot library to enable accessible AI robotics.

An open-source multimodal AI workbench that integrates image, video, and audio generation into a node-based infinite canvas for iterative visual creation.

An AI-powered persistent memory system for Obsidian that allows AI assistants to read, write, and automatically maintain a self-evolving knowledge base.

Redis is a fast, in-memory data structure server and vector query engine used for caching, real-time analytics, and as a vector store for GenAI applications.

An orchestration layer for AI agents that automatically discovers, selects, and routes local specialized skills to execute complex, multi-step tasks with verifiable results.

An open protocol that enables communication and interoperability between AI agents built on different frameworks and servers, allowing them to collaborate without exposing internal logic.

A local AI-powered PR review and management tool that uses isolated git worktrees to analyze, fix, and manage GitHub pull requests using Claude or Codex.

An open-source SASE platform that provides zero-trust networking, a reverse proxy, and an identity-aware AI gateway for secure resource access.

NOFX is an open‑source, self‑hosted trading terminal that lets large language models generate crypto‑perpetual trades. A Go runtime enforces strict risk limits, stores every model‑generated reasoning, and supports nine exchanges. Users fund an on‑chain AI fee wallet, start “Autopilot” to let the model trade automatically, and can compare multiple traders on a public leaderboard. Installation is available via a one‑click script, Docker, Railway, or manual build.

An AI-powered life operating system that adds persistent memory, personal context, and specialized skills to AI coding harnesses to help users achieve personal and goal-oriented outcomes.

A collection of role-specific plugins for Claude Cowork and Claude Code that integrate professional tools and domain expertise to turn the AI into a specialized coworker.

OpenCV is an open-source computer vision library that provides tools and algorithms for AI and visual perception development.

A set of skills for programming agents to automate the mathematical modeling process, from problem analysis and real code execution to the generation of a formal, verified competition paper.

A framework that assembles a multi-modal AI agent featuring persistent text-based memory, voice interaction, visualizers, and webcam-based gesture control.

A Claude Code plugin that adds a real-time status display to the terminal, showing context usage, active tools, and agent progress.

An AI co-author suite that automates the research lifecycle, from turning vague directions into defensible research ideas to generating posters, videos, and blogs from finished papers.

ViMax is an open‑source, agent‑driven framework that turns a text idea, screenplay, or novel excerpt into a complete AI‑generated video. It handles scriptwriting, storyboarding, character consistency, and final rendering via configurable LLM, image, and video APIs. Use a terminal TUI or a browser‑based Web UI; install with `uv sync`, configure API keys in `configs/agent.local.yaml`, and run `vimax tui` or `npm run dev` for the UI.

An open-source SQL interface for deploying, managing, and querying cloud resources and SaaS APIs across multiple providers.

A tiny, educational autograd engine that implements backpropagation over a scalar-based DAG to help users understand the internal mechanics of neural networks.

An open-source 2D and 3D deep face analysis toolbox providing state-of-the-art algorithms for face recognition, detection, and alignment.

OpenAlice is a locally‑run AI orchestrator for individual traders. It lets you plug in LLM agents (Claude, Codex, Pi, etc.) and connect them to market data, research workspaces (Git‑backed folders), and broker accounts. Agents can fetch data, run quantitative analyses, generate reports, and even draft trade orders, which you review and commit via a Git‑style interface. The product ships as a desktop app (macOS/Windows) with CLI/Docker options, and includes scheduling, issue tracking, and a central Inbox for follow‑up. Trading execution is marked as beta and intended for paper or test accounts first.

An autonomous security research framework that chains static analysis, binary analysis, and LLM-powered validation to discover and patch vulnerabilities.

A browser extension that adds folder organization, a prompt library, and advanced navigation tools to Gemini, Claude, and ChatGPT.

A vision-driven GUI agent for E2E testing that allows users to automate and verify user interfaces across web, mobile, and desktop using natural language instructions.

An open agent skill and prompt standard designed to eliminate defensive writing and excessive hedging in academic and professional prose to make it more authoritative and direct.

A terminal-based AI coding agent that understands codebases, performs multi-file edits, and executes commands with a focus on speed and remote SSH efficiency.

Mnemosyne is a local-first, SQLite-backed memory layer for AI agents. It gives assistants persistent memory across sessions via a three-tier architecture (working memory, episodic memory, temporal knowledge graph), with hybrid semantic/keyword search, heavy vector compression, a Python SDK, CLI, and built-in MCP server. It's privacy-focused: no telemetry, local by default, with optional client-side-encrypted sync.

A framework for building stateful AI agents with persistent memory that allows them to learn and improve over time.

An open-source ChatGPT alternative that lets users run LLMs locally for privacy or connect to cloud AI services via a unified desktop interface.

Milvus is a high-performance, distributed vector database built for scaling AI applications that require efficient search and organization of massive amounts of unstructured data.

A library and CLI tool to remove visible labels, invisible pixel watermarks, and AI provenance metadata from AI-generated images and videos.

Raven is an open-source, self-improving agent harness that integrates long-term memory, proactivity, and local tracing for long-running AI agent workflows.

A delegation framework for Pi that enables a parent session to spawn specialized child agents for tasks like code review, research, and parallel implementation.

A coordination framework that manages AI agents in isolated git worktrees and tmux sessions, using a durable handoff protocol to exchange work.

An open-source, local-first AI research workbench that enables reproducible science by combining AI agents, Python/R execution, and traceable provenance for all research artifacts.

An open-source AI coding agent for VS Code, JetBrains, and the CLI that provides access to 500+ models for code generation, debugging, and autonomous CI/CD operations.

A collection of Agent Skills that provide AI coding assistants with best practices and specialized commands for building videos with Remotion.

Dress AI Service is an open‑source, self‑hosted FastAPI application that lets you upload photos of your clothes, auto‑tags them with CLIP, generates outfit recommendations using rule‑based logic plus optional LLM reasoning, and visualises the looks with Stable Diffusion/FLUX. It runs via Docker or a local Python environment, stores data in SQLite/PostgreSQL, and includes weather‑aware styling, analytics, and a lightweight HTML/Tailwind UI.

A local-first observability and debugging tool for TypeScript AI agents that turns execution traces into readable trees and deterministic trajectory checks for CI.

A lightweight agentic RL framework that allows developers to train AI agents using reinforcement learning with zero changes to their existing agent harnesses.

A framework that extends vLLM to provide high-performance serving for omni-modality models, supporting text, image, audio, video, and action outputs across various hardware backends.

A set of plain-text rules and instructions that enable AI agents to write in a clear, concise style and remove unnecessary complexity from their responses.

A readable terminal-based coding agent that can edit code and run commands, designed both as a functional tool and a teaching example for building agentic systems.

A unified real-time search engine skill for AI agents that supports general web search, vertical domain search, and full-page content extraction.

A terminal-based mission control for AI coding agents that provides persistent workspaces, agent status tracking, and workflow orchestration.

An AI-driven pipeline that converts text descriptions into game-ready, animated 3D creatures in GLB format using a multi-stage design and validation process.

An agent-project workbench for DeepSeek Harness that provides a dockable multi-window workspace and a real-time control room for monitoring AI projects.