orca: an AI orchestrator for running multiple CLI agents in parallel isolated worktrees
An AI orchestrator that lets developers run multiple CLI agents in parallel isolated worktrees with a unified desktop and mobile interface.
pentagi: an autonomous multi-agent system for automated security testing and penetration testing
An autonomous AI-powered penetration testing platform that uses a multi-agent system to automate security vulnerability research and exploitation in isolated environments.
n8n-skills: expert Claude Code skills for building and deploying production-ready n8n workflows
A collection of 14 specialized Claude Code skills and an enforcement layer that teach AI assistants how to build, validate, and deploy production-ready n8n workflows using the n8n-mcp server.
CloakBrowser: a stealth Chromium binary with source-level C++ patches that bypasses advanced bot detection
A stealth Chromium browser binary with source-level C++ patches that bypasses advanced bot detection systems while remaining compatible with Playwright and Puppeteer.
TencentDB-Agent-Memory: TencentDB Agent Memory
System for AI agents to retain/reuse experience (chat memory, skills, wiki, codegraph) to reduce repetitive work.
semantica: a graph-native infrastructure layer for accountable AI agents with deterministic reasoning and full decision provenance
A graph-native infrastructure layer for AI agents that provides deterministic reasoning, decision provenance, and auditable context graphs for regulated industries.
OpenBidKit_Yibiao: an open-source AI bidding assistant for generating technical proposals and commercial bids
An open-source AI-powered bidding assistant that helps users generate technical and commercial proposals using corporate knowledge bases and flexible AI model integrations.
open-design: an open-source alternative to Claude Design that turns coding agents into a design engine for prototypes and motion graphics
An open-source, agent-native design platform that allows coding agents to generate prototypes, dashboards, decks, and motion graphics based on a shared design system.
NemoClaw: a reference stack for running AI agents safely inside sandboxed environments
A reference stack for running AI agents safely inside NVIDIA OpenShell sandboxes, providing security controls and lifecycle management via a CLI.
dagu: a local-first workflow engine for ops automation and AI-assisted operations
A local-first, single-binary workflow engine that turns existing scripts and containers into observable DAG pipelines with scheduling, retries, and AI agent integration.
DeepTutor: an agent-native learning workspace for personalized tutoring and lifelong mastery
An agent-native learning workspace that integrates personalized tutoring, deep research, and mastery practice using a three-layer memory system and advanced RAG.
zvec: a lightweight in-process vector database for low-latency similarity and hybrid search
Zvec is an open-source, in-process vector database that provides low-latency similarity search and hybrid search capabilities embedded directly into applications.
video-shotcraft: an agent skill for crafting cinematic product videos with a library of 104 shot recipes and a production-ready template
An AI agent skill that enables AI coding agents to storyboard, animate, and sound-design cinematic product promo videos using Remotion.
agenta: an open-source workspace for building and running agents with background execution and human-in-the-loop permissions
An open-source workspace for building and running AI agents that can automate work through chat, background schedules, and integrations with external apps.
plannotator: a browser-based review surface for AI coding agents to annotate plans and code diffs
A browser-based review surface for AI coding agents that allows users to annotate plans, HTML artifacts, and code diffs to provide structured feedback to the agent.
openui: a renderer-agnostic Generative UI framework for streaming interactive components with high token efficiency
A full-stack Generative UI framework that uses a compact, streaming-first language to let LLMs render interactive components with high token efficiency.
paseo: a unified cross-device interface for orchestrating multiple self-hosted AI coding agents
A unified, self-hosted interface for orchestrating multiple AI coding agents like Claude Code and Copilot across desktop, mobile, and CLI.
SurfSense: an open-source research platform providing AI agents with live structured web data via REST API and MCP server
An open-source research platform and NotebookLM alternative that provides AI agents with live, structured web data via REST API and MCP server.
agents: a framework for building real-time programmable multi-modal voice agents with integrated job scheduling
A framework for building real-time, programmable multi-modal AI agents that can see, hear, and speak, featuring integrated job scheduling and telephony support.
wisp-science: Wisp Science
Wisp Science is an open-source, local-first AI research workbench that provides a desktop AI assistant and scientific computing environment. It connects to AI models (OpenAI-compatible and Anthropic), runs persistent Python/R environments, and accesses bioinformatics databases via MCP servers while keeping data local.
strix: an autonomous AI pentesting tool that validates vulnerabilities with real proofs-of-concept
An autonomous AI penetration testing tool that uses multi-agent orchestration to find, validate with PoCs, and fix security vulnerabilities in applications.
maxun: Maxun
An open-source no-code platform that turns any website into structured data via scraping, crawling, search, and LLM-powered extraction.
sim: a workspace to build, deploy and manage AI agents and workflows
A workspace to build, deploy, and manage AI agents and workflows, featuring a visual builder, 1,000+ integrations, and integrated knowledge management.
openless: OpenLess: Open-source voice input that turns speech into AI-ready prompts at your cursor
OpenLess is an open-source voice input tool for macOS and Windows that uses AI to transcribe and polish speech into structured text—optimized for creating AI prompts—while eliminating repetitive coordination between thought and written output through features like style packs, streaming insertion, and bring-your-own-cloud flexibility.
Unity-MCP: an MCP server that bridges AI agents with Unity for automated game development and runtime AI interaction
An AI-powered game development assistant that connects AI agents to Unity via the Model Context Protocol to automate editor workflows and enable in-game AI behavior.
vllm-ascend: a hardware plugin for running vLLM seamlessly on Huawei Ascend NPUs
A hardware plugin that allows the vLLM inference engine to run on Huawei Ascend NPUs, supporting a wide range of open-source LLMs and multimodal models.
opensquilla: OpenSquilla – a microkernel AI agent that auto‑routes to the cheapest LLM, with CLI, desktop, and chat‑channel interfaces.
OpenSquilla is a locally‑run, token‑efficient AI‑agent framework that routes each turn to the cheapest LLM that can handle it. It offers a unified turn loop for CLI, desktop (Electron‑based) and chat channel integrations, persistent memory, sandboxed tool execution, built‑in web search, and on‑device embeddings. Install via a desktop installer, a quick `uv`‑based wheel, or from source; configure with `opensquilla onboard` and start the agent with `opensquilla gateway run`.
MaiBot: a lifelike digital companion agent that prioritizes human-style social authenticity over task efficiency
An LLM-based interactive agent designed to be a lifelike digital companion rather than a task-oriented assistant, focusing on natural, human-style social interaction.
Vibe-Trading: Vibe-Trading: AI‑powered personal trading agent for automated research, backtesting, and strategy execution across equities, A‑shares, KRX, options, and more.
Vibe-Trading is an open‑source personal trading agent that leverages AI/LLM models to automate research, backtesting, and trading across multiple markets. It offers a one‑command install, live model discovery, multi‑market data, options analytics, sentiment and technical tools, scheduled jobs, a shadow/paper trading account, a React‑based web UI, and an API/MCP interface for extensibility.
oh-my-pi: a high-performance coding agent with integrated LSP and DAP for precise editing and native debugging
A high-performance coding agent with a Rust core that integrates LSP, DAP, and native system tools to provide precise code editing and real-time debugging.
Auto-claude-code-research-in-sleep: a high-integrity automated research framework that uses cross-model adversarial audits to prevent AI fabrications
A high-integrity AI research methodology and CLI tool that uses a multi-model audited spiral workflow to prevent fabrications and ensure self-consistency in automated research.
airllm: a memory-efficient inference engine that runs massive LLMs on consumer GPUs by loading one layer at a time
AirLLM is a library that enables running massive LLMs (up to 671B parameters) on low-end GPUs by loading only one model layer at a time into VRAM.
DeepSeek-Reasonix: Reasonix – a DeepSeek‑native AI coding agent for your terminal, desktop, or VS Code
Reasonix is a Go‑based, config‑driven AI coding assistant that talks to DeepSeek or any OpenAI‑compatible LLM. It runs as a single static binary and can be used via CLI/TUI, a native desktop app, or a VS Code extension. Features include multi‑model pipelines, a JSON‑RPC plugin system, cache‑aware context handling to keep token usage low, and easy cross‑platform installation (npm, Homebrew, pre‑built archives, or source build).
MaxKB: an open-source platform for building enterprise-grade agents with RAG pipelines and agentic workflows
An open-source platform for building enterprise-grade AI agents that integrates RAG pipelines and agentic workflows to create intelligent knowledge bases and customer service tools.
promptfoo: a CLI and library for automated LLM evaluation and red-teaming to ensure secure and reliable AI apps
A CLI and library for evaluating and red-teaming LLM applications to replace trial-and-error prompt engineering with data-driven testing and security scanning.
agentscope: a production-ready agent framework with built-in multi-tenancy and secure sandboxing for scalable AI applications
A production-ready agent framework that provides essential abstractions for multi-tenancy, secure sandboxing, and flexible memory to build scalable AI agent applications.
FastGPT: a visual AI agent building platform with integrated RAG and workflow orchestration
An AI Agent building platform that provides visual workflow orchestration and integrated knowledge base capabilities for creating complex AI applications.
headroom: a context compression layer that reduces LLM token usage for AI agents via content-aware compressors and a local proxy
A context compression layer for AI agents that reduces input and output tokens by 15-95% using content-aware compressors and a local-first proxy.
deer-flow: DeerFlow 2.0: Open-Source Super Agent Harness
DeerFlow 2.0 is an open-source super agent harness that orchestrates sub-agents, memory, and sandboxes to perform tasks using extensible skills and LLMs.
OpenHands: a self-hosted developer control center for managing and automating coding agents
A self-hosted developer control center for managing and automating coding agents across local, remote, and cloud backends.
LocalAI: a composable local AI engine supporting multi-modal models across any hardware with drop-in API compatibility
An open-source AI engine that allows you to run LLMs, vision, voice, image, and video models locally on any hardware with a drop-in OpenAI-compatible API.
skills: a catalog of portable instruction sets that teach AI coding agents to use NVIDIA software and hardware optimally
A catalog of portable instruction sets that teach AI coding agents how to optimally use NVIDIA software, hardware libraries, and robotics workflows.
open-webui: an extensible self-hosted AI platform for managing local and API-based LLMs with built-in RAG
A feature-rich, self-hosted AI platform that provides a user-friendly interface for local and API-based LLMs, featuring built-in RAG and extensive plugin support.
TurboOCR: a high-performance GPU document parser that extracts text, layout, tables, and formulas into Markdown at extreme speeds
A high-speed GPU document parser that converts images and PDFs into structured Markdown, HTML tables, and LaTeX formulas using TensorRT and PP-OCRv6.
open-science: Open Science: a local‑first AI agent workbench for reproducible scientific discovery.
Open Science is a self‑hosted AI research workbench that lets scientists run natural‑language tasks with an agent that can execute code, call scientific tools, and produce reproducible, provenance‑tracked results.
avoid-ai-writing: a portable writing skill for AI agents that audits and rewrites content to remove robotic AI-isms
A portable writing skill for AI agents that audits and rewrites content to remove robotic AI writing patterns and "AI-isms" using a structured, multi-pass detection system.
jcodemunch-mcp: a token-efficient MCP server for precise GitHub source code retrieval via AST parsing
An MCP server that uses tree-sitter AST parsing to provide precise, symbol-level code retrieval for AI agents, reducing token costs by up to 99%.
destructive_command_guard: a high-performance command guard that blocks destructive AI agent actions across multiple IDEs and CLIs
A high-performance hook for AI coding agents that intercepts and blocks destructive commands like recursive deletions or database drops before they execute.
AI-Infra-Guard: an AI red teaming platform for scanning infrastructure vulnerabilities, agent risks, and LLM jailbreak robustness
An AI red teaming platform that provides automated security scanning for AI infrastructure, agent workflows, and LLM jailbreak evaluation to identify vulnerabilities and safety risks.
radar: a lightweight Kubernetes UI with real-time topology and built-in MCP context for AI agents
An open-source Kubernetes UI provided as a single binary that offers real-time topology, resource management, and GitOps visibility without requiring cluster-side installation.