An embedded SQLite state reconciliation tool for AI agents and workers that recovers stuck tasks and manages delivery states after service restarts.

A tool that gives AI coding agents a live feedback loop to inspect, control, and verify mobile, TV, and desktop apps across iOS, Android and other platforms.

Khoj is an open-source personal AI assistant that serves as a second brain, allowing users to chat with their own documents and the internet using various LLMs.

An open-source AI engine that lets you run LLMs, vision, audio, and image models locally on any hardware with drop-in OpenAI-compatible APIs.

An on-device hybrid search engine that indexes local markdown notes and documentation using BM25, vector search, and LLM reranking for high-precision retrieval.

A Claude Code skill that enables AI to generate professional boardroom-quality presentation decks using a 110-rule design book, a 62-part HTML slide library, and automated validation scripts.

An automated screenshot and preview video generator for App Store and Google Play that integrates with coding agents to create professional store assets.

A universal morphing library for stroke-based icons that uses spring physics and mathematical alignment to create smooth transitions between any two icons.

An open-source AI presentation generator that creates fully editable PowerPoint decks from prompts or documents using self-hosted or BYOK AI models.

An open-source evaluation framework for physical AI that lets you run any robotics policy against any compatible robot or simulator with auditable logs and live visualization.

A high-performance Rust-based statusline HUD for Claude Code that displays real-time model info, reasoning effort, Git status, and context window usage.

ccteam is an orchestration layer that turns separate AI coding CLIs into a coordinated team, allowing agents to operate across different vendors and machines from a unified console.

BossConsole is an open‑source, JVM‑native desktop console that lets any LLM agent work with a real browser, terminal, editor, git, Docker/Kubernetes, and more. It exposes ~100 tools via a Model Context Protocol, offers fine‑grained RBAC and per‑tool kill‑switches, and supports hot‑reloading plugins so agents can evolve their own capabilities.

A unified platform for AI development and deployment featuring the Mojo programming language and the MAX framework for high-performance model serving.

An open‑source, AI‑assisted video‑editing kit that lets you edit footage via natural‑language prompts to Codex or Claude Code. It ships with 14 agent‑driven “skills”, 400+ motion‑graphics cards, scene templates, transcription helpers (ElevenLabs, Whisper), and demo projects. Install Node 22+, Git, FFmpeg, then run `npm run demo` and use commands like `$edit-video` or `/short-form-edit` to cut silences, fix mistakes, and produce reels or Shorts. Optional API keys unlock cloud transcription and asset generation; otherwise it works locally with synthetic data.

A local-first AI memory system that stores conversation history verbatim and uses semantic search for high-accuracy retrieval without needing cloud APIs.

A beautiful, Claude Code-style terminal user interface plugin for DeepSeek Harness that adds advanced session management and real-time performance monitoring.

An open-source desktop app and MCP server that allows users to share and reuse AI workflows, skills, and connected services across different AI agents and machines.

A professional video editor designed for AI agents that treats video compositions as code, allowing agents to and humans to collaboratively edit videos via a bidirectional JSX-based workflow.

A remote access plugin for DeepSeek Harness that lets users control their AI agents from a mobile device via LAN or public Cloudflare tunnels.

A library of 73 AI‑agent “skills” (engine‑specific code guides, discipline, genre and workflow templates) plus a router that auto‑detects your game engine and loads only the needed pieces, enabling agents like Claude, Cursor, Gemini‑CLI, etc., to generate game code on demand.

A GPU-optimized library and reference framework for training massive transformer models at scale, supporting advanced parallelism strategies and mixed-precision training.

TrueForge is an open-source agent harness that provides the runtime layer for LLM-based agents, managing session state, tool execution, sandboxing, and user interfaces.

A local NVR with real-time AI object detection for IP cameras, designed for tight integration with Home Assistant.

An AI-guided toolkit for authorized security testing that provides a curated library of 215 tools and translates plain English into specific commands and execution plans.

A comprehensive A-share data toolkit with 54 endpoints and 11 layers of architecture, designed as an AI-ready skill file to provide zero-authentication financial data for AI agents and developers.

A local-first multi-agent development platform that automates the building, optimization, and deployment of AI agent applications, featuring a native self-evolution engine.

An open-source platform for building and deploying AI agents that automate complete workflows through plain-English descriptions or a visual builder.

A from-scratch C++/CUDA inference engine optimized for the NVIDIA RTX 5090 to deliver maximum single-GPU performance for Qwen models.

Project NOMAD is an offline-first knowledge and education server that bundles local AI chat (with RAG), offline Wikipedia, courses, maps, and data tools into a self-contained Docker-orchestrated system, keeping critical information available without internet.

An open-source WebRTC infrastructure for scalable, multi-user real-time video, audio, and data communication.

LogoCreator is an open‑source web app that generates brand‑ready logos using the FLUX‑2 image model via Together AI. Built with Next.js, TypeScript, Radix, and Tailwind, it runs without an account—just a Together AI key. Features include instant generation, FLUX‑1 edits, PNG/SVG export, optional rate‑limiting and auth, and a history dashboard. The repo provides clear setup steps and lists future tasks such as size selection, cost preview, reference‑logo uploads, and a showcase of redesigned famous logos.

Plannotator is a local, browser‑based (and terminal) review UI that integrates with many AI coding agents. It lets you annotate plans, specs, markdown, HTML, and code diffs, then sends the feedback back to the agent. Installation is a one‑line script that auto‑detects agents; the tool works offline, stores everything locally, and only contacts the network for fetching URLs, PR data, or optional link‑sharing. It includes VS Code, Obsidian, and GitHub/GitLab integrations, and provides secure binary distribution with SLSA provenance.

A Python package that supplies a wide‑range of ready‑made tools (file I/O, shell, web search, AWS, image/video generation, memory stores, browser/desktop automation, multi‑agent orchestration, etc.) for LLM‑driven agents built with the Strands Agents SDK. Install with `pip install strands-agents-tools` (optional extras for extra capabilities) and call tools via `agent.tool.<name>(…)`. Many tools are experimental and some older ones are deprecated in favor of native SDK features.

RPent is an open framework for building embodied agents that use recursive interaction and memory to evolve their capabilities and improve success rates in long-horizon physical manipulation tasks.

A comprehensive skill bundle for Claude Code and other AI agents that provides specialized knowledge and methodologies for bug hunting and external red-team engagements.

A plugin providing 35 AI coding skills that implements a structured loop of brainstorming, planning, and reviewing to capture and compound engineering knowledge within a codebase.

A framework for building real-time, multi-modal voice agents that can see, hear, and understand, featuring integrated job scheduling and flexible model integrations.

A deep learning framework built in Java that supports a wide range of neural network architectures from CNNs to LLMs and Diffusion models with CUDA acceleration.

A provider-neutral, stateful control plane for long-running AI agents that preserves objectives, evidence, and handoffs across different agent harnesses and sessions.

An open-source AI agent for the terminal that provides direct access to Gemini models for code analysis, automation, and system integration.

A CLI and TypeScript SDK for defining security policies and using AI to find, validate, and fix security vulnerabilities in codebases.

An agent skill that forces LLMs to write in plain, disciplined English based on the ASD-STE100 aerospace standard to eliminate AI verbosity and jargon.

DojoAgents is an open‑source AI‑agent framework for personal investing. It runs a large‑language‑model‑driven “Agent Loop” that fetches market data, parses news, executes Python‑based calculations, and stores reusable analysis skills. A FastAPI backend and React dashboard let users view portfolio metrics, get daily market overviews, run news‑impact analyses, and even diagnose a portfolio from a screenshot. Installable via `uv pip install dojoagents`, it works with any LLM API (OpenAI, Gemini, Anthropic, local Ollama, etc.) and can push automated insights to chat apps.

A Model Context Protocol (MCP) server that connects AI agents and chatbots to GitHub, enabling them to manage repositories, issues, and pull requests via natural language.

An SDK for browser agents that enables reliable web automation using natural language, self-healing actions, and token-efficient page context.

A workflow and runtime layer for OpenAI Codex CLI that adds structured planning, durable state tracking, and specialized roles for complex coding tasks.

An autonomous game development generator that uses AI agents to build, asset-generate, and visually verify games for Godot, Bevy, and Babylon.js.