| mcp-server-kubernetes | ★ 1.6K | MCP | TypeScript | kubernetes · kubectl · helm · cluster-management · MCP server · observability · troubleshooting · security | An MCP server that lets AI clients manage Kubernetes clusters through kubectl and Helm tools. Includes pod troubleshooting prompts, non-destructive mode, secret masking, and optional OpenTelemetry tracing. | View Project → |
| mcp-windbg | ★ 1.6K | MCP | Python | MCP server · WinDbg · crash dumps · debugging · Windows · kernel debugging · remote debugging · CDB · KD | A Python MCP server that lets AI clients operate WinDbg, CDB, and KD for Windows crash-dump analysis, remote debugging, and kernel debugging. Supports multiple sessions and stdio or HTTP transport. | View Project → |
| MemoryOS | ★ 1.6K | AI Agents | Python | memory · long-term-memory · agent-memory · personalization · rag · mcp · chromadb · vector-database · embeddings · hierarchical-memory · context-management · llm · python · locomo · retrieval · user-profile | MemoryOS is a hierarchical memory operating system for personalized AI agents, with short-, mid-, and long-term memory plus storage, update, retrieval, and generation modules. Ships a PyPI package, MCP server, ChromaDB and Playground integrations, and reports SOTA results on the LoCoMo benchmark. | View Project → |
| oxideterm | ★ 1.6K | AI Tools | Rust | ssh-client · terminal · ai-assistant · mcp · rag · agent-skills · tool-calling · byok · local-first · rust · gpui · sftp · port-forwarding · remote-desktop · cli · plugins | Native Rust/GPUI SSH and remote-ops workspace with a BYOK AI assistant (OxideSens) that inspects live sessions and executes approved actions. Bundles SSH/Mosh/Telnet/RDP/VNC/SFTP, port forwarding, mini-IDE, MCP, RAG and agent skills with no Electron, telemetry or subscription. | View Project → |
| ADR | ★ 1.6K | AI Agents | Python | agent-security · ai-agents · prompt-injection · threat-detection · observability · benchmark · mcp · llm-security · enterprise-security · telemetry · claude-code · cursor · codex · ai-security · red-teaming · detection | Uber's Agentic AI Detection and Response (ADR) secures enterprise AI agents via endpoint discovery, telemetry collection, a 300+ task security benchmark, and a dual-agent detector for prompt injection and risky tool use. Open source covers Discovery, Sensor, Bench and Detector. | View Project → |
| deepagentsjs | ★ 1.6K | AI Agents | TypeScript | agent-harness · langgraph · langchain · typescript · sub-agents · planning · filesystem-tools · context-management · multi-agent · mit · streaming · checkpointing · tool-calling · monorepo · pnpm · browser-support | Deep Agents JS is LangChain's batteries-included TypeScript agent harness built on LangGraph. It ships planning (write_todos), filesystem tools, and sub-agents so you get a working, customizable tool-calling agent out of the box. | View Project → |
| magpie | ★ 1.6K | AI Coding | Go | coding agents · model routing · LLM gateway · model management · provider management · OpenAI-compatible · Anthropic API · CLI · menu bar · profiles | Magpie is a desktop, terminal, and CLI tool for managing models across coding agents such as Claude Code, Codex, and Gemini CLI. Its local gateway exposes configured providers and signed-in subscriptions through compatible APIs, with shared catalogs and routing groups. | View Project → |
| PrismerCloud | ★ 1.6K | AI Agents | TypeScript | agent-runtime · agent-memory · agent-evolution · multi-agent · agent-communication · MCP · RAG · skills · self-hosted · Claude Code · Cursor · Windsurf | Prismer Cloud provides runtime infrastructure for AI agents, including persistent memory, shared learning from task outcomes, context retrieval, messaging, and task orchestration. It offers SDKs, Claude Code and OpenCode plugins, and an MCP server with 47 tools. | View Project → |
| user-research-skill | ★ 1.6K | Skills | Shell | agent-skill · user-research · ux-research · ai-interviews · synthetic-users · surveys · qualitative-research · quantitative-research · report-synthesis · participant-recruitment · claude-code · codex · cursor · cli · personas · transcript-analysis | MIT-licensed agent skill that lets Claude Code, Codex, Cursor and other agents plan, run, and synthesize user research: interview guides, AI-moderated interviews with real or synthetic participants, quant surveys, and report synthesis with personas and codebooks. | View Project → |
| female-portrait-director | ★ 1.5K | Skills | — | agent-skill · codex-skill · prompt-engineering · ai-image-generation · portrait-prompts · text-to-image · prompt-templates · style-registry · negative-constraints · image-workflows · character-portraits · e-commerce-imagery | A Codex/Agent Skills pack that turns short portrait inputs into locked, directed AI image prompts across 20 style routes, with optional direct image generation and authorized reference-image workflows. | View Project → |
| pi-mcp-adapter | ★ 1.5K | MCP | TypeScript | mcp · model-context-protocol · mcp-adapter · coding-agent · pi · token-efficiency · context-window · lazy-loading · oauth · tool-discovery · cli · extension · agent-plugins · tui · typescript | A Pi coding agent extension that fronts all your MCP servers with one ~200-token proxy tool. Servers stay lazy, tool metadata is cached for on-demand search/describe, and it reads standard .mcp.json, host configs, Claude plugins, and OAuth flows. | View Project → |
| dsh-im | ★ 1.5K | AI Agents | JavaScript | im-bot · chatbot · deepseek-harness · multi-channel · dsh-plugin · cordis · feishu · wechat · dingtalk · wecom · qq · slack · telegram · discord · whatsapp · imessage | DSH-IM is a DeepSeek Harness plugin that connects 11 IM channels (Feishu, WeChat, DingTalk, WeCom, QQ, Slack, Telegram, Discord, WhatsApp, iMessage) via QR code or bot credentials. It streams agent replies, handles image input and file return, and manages per-bot workspaces, models and session bindings. | View Project → |
| gemma-translator | ★ 1.5K | AI Tools | JavaScript | offline translation · voice translation · on-device AI · speech-to-text · text-to-speech · Raspberry Pi · kiosk | An offline voice-translation app for Raspberry Pi that transcribes speech with Moonshine, translates it using Gemma 4 E2B through LiteRT-LM, and speaks the result. Includes a small-screen web UI and kiosk deployment scripts. | View Project → |
| amical | ★ 1.5K | AI Tools | TypeScript | dictation · speech-to-text · whisper · asr · local-first · offline · privacy · ollama · transcription · voice · electron · mcp · productivity · self-hosted · context-aware · meeting-notes | Amical is a local-first AI dictation desktop app (Electron) using Whisper for offline speech-to-text and Ollama-hosted LLMs for context-aware formatting per active app. Includes voice notes, hotkey workflows, and planned MCP voice control. | View Project → |
| devops-ai-guidelines | ★ 1.5K | AI Agents | Python | DevOps · AI agents · MCP · SRE · observability · monitoring · incident response · runbooks · agent evaluation · learning path | A structured DevOps AI learning path covering MCP, agent development, monitoring, SRE runbook retrieval, and agent evaluation. Includes tutorials, team guidelines, prompts, and AWS-focused examples. | View Project → |
| row-bot | ★ 1.5K | AI Agents | Python | local-first · personal-assistant · multi-agent · langgraph · react-agent · knowledge-graph · mcp · ollama · voice · computer-use · browser-automation · skills · workflows · privacy · self-hosted · desktop-app | Row-Bot is a local-first desktop AI assistant built on LangGraph ReAct agents with durable memory, a personal knowledge graph, 30+ tools, MCP/plugin/skill discovery, scheduled workflows, voice, browser and computer use, and multi-channel messaging. Runs on Ollama locally or optional cloud providers, keeping data on you | View Project → |
| ClaudeCode-Portable | ★ 1.5K | AI Coding | JavaScript | claude-code · portable · usb-drive · ai-coding-agent · multi-provider · no-install · browser-dashboard · local-models · ollama · lm-studio · openrouter · offline-inference · provider-switching · agent-sdk · cross-platform · terminal-interface | Portable AI coding workspace bundling the official Claude Code CLI and Agent SDK with a browser dashboard. Runs from a USB drive on Windows/Linux/macOS and connects to Anthropic, OpenAI, Gemini, OpenRouter, NVIDIA NIM, Ollama, and LM Studio. | View Project → |
| DEEIX-Chat | ★ 1.5K | AI Tools | Go | ai-chat · model-routing · mcp · rag · self-hosted · multimodal · enterprise · llm-gateway · chat-ui · billing · sso · openai-compatible · vector-search · ocr · audit-logs · golang | DEEIX Chat is a self-hosted Go + Next.js enterprise AI workspace that unifies multi-provider model routing, multimodal chat, file RAG, MCP tools, billing, identity and admin audit in one deployable stack. | View Project → |
| npcpy | ★ 1.5K | AI Frameworks | Python | LLM · multimodal · agents · multi-agent · tool calling · MCP · knowledge graphs · model providers | Python framework for building LLM applications with agent, tool-use, and multi-agent orchestration primitives. Supports local and cloud model providers, multimodal workflows, MCP, and knowledge graph pipelines. | View Project → |
| minutes | ★ 1.5K | MCP | Rust | mcp · transcription · meeting-notes · local-first · speech-to-text · whisper · rust · privacy · on-device · markdown · voice-memo · claude-code · agent-memory · cli · parakeet · claude-skills | Local-first conversation memory app: records and transcribes meetings, calls, and voice memos on-device into Markdown you own, then exposes them to Claude Code, Codex, Cursor and any MCP client via an MCP server (34 tools), CLI, and Claude Code plugin. | View Project → |
| connectonion | ★ 1.5K | AI Frameworks | Python | AI agents · multi-agent · agent framework · agent CLI · tool calling · agent skills · browser automation · agent debugging · agent deployment · approval workflows · persistent memory | Python framework and CLI harness for building, debugging, and deploying tool-using AI agents. Includes browser, shell, email, and file integrations, reusable skills, approval controls, and support for hosting agents that other agents can call. | View Project → |
| rulesync | ★ 1.5K | AI Coding | TypeScript | cli · ai-rules · config-management · mcp · skills · subagents · agent-hooks · claude-code · cursor · github-copilot · codex-cli · agents-md · multi-tool-sync · typescript · nodejs | Node.js CLI that manages a single .rulesync source of truth and generates or imports config files (rules, MCP, commands, subagents, skills, hooks, permissions) for 40+ AI coding tools such as Claude Code, Cursor, Copilot and Codex CLI. | View Project → |
| lime | ★ 1.5K | AI Agents | TypeScript | desktop-agent · coding-agent · CLI · TUI · multi-agent · MCP · skills · multimodal · terminal · research · file-operations · workflows | Lime is an open-source desktop and CLI/TUI AI agent that works across code, files, terminals, research, and content. It supports configurable model providers, MCP tools, reusable skills, multimodal workflows, and multi-agent task delegation. | View Project → |
| ros-mcp-server | ★ 1.5K | MCP | Python | mcp · mcp-server · model-context-protocol · ros · ros2 · ros1 · robotics · rosbridge · robot-control · llm · sensor-monitoring · fastmcp · python · simulation · natural-language-control | MCP server that connects LLMs (Claude, GPT, Gemini) to robots over ROS/ROS 2 via rosbridge, with no robot code changes. LLMs can discover topics, services and actions, publish/subscribe, call services and read sensor data for control and diagnostics. | View Project → |
| dust | ★ 1.5K | AI Agents | TypeScript | ai-agents · multi-agent · agent-platform · llm · self-hosted · typescript · rust · mcp · connectors · knowledge-base · rag · assistants · workflow-automation · enterprise · monorepo · cloud | Dust is a TypeScript/Rust platform for building and deploying custom AI agents on top of your company data. It ships 80+ connectors, MCP support, and a web UI plus API so teams can create, share, and self-host assistants with retrieval over internal knowledge. | View Project → |
| kotlin-sdk | ★ 1.5K | MCP | Kotlin | MCP · Kotlin · Kotlin Multiplatform · client SDK · server SDK · stdio · Streamable HTTP · SSE · WebSocket | Official Kotlin Multiplatform SDK for building MCP clients and servers. Supports tools, prompts, resources, sampling, and stdio, SSE, Streamable HTTP, and WebSocket transports across JVM, Native, JS, and Wasm. | View Project → |
| burrow | ★ 1.5K | MCP | Swift | macos · swift · swiftui · system-monitor · disk-usage · cleaner · uninstaller · menubar · mcp · cli · winui3 · dotnet · disk-analyzer · maintenance · homebrew | Burrow is a native macOS (plus Windows preview) system utility for cleanup, app uninstall, disk analysis, maintenance and live status, with a long-range metrics history and a built-in MCP server so agents can query and act on Mac health. It is primarily an OS maintenance app rather than an AI product. | View Project → |
| ffmpeg-skill | ★ 1.4K | Skills | Python | ffmpeg · video-editing · agent-skill · mcp · claude-code · cursor · codex · audio-processing · captions · subtitles · video-processing · hdr-to-sdr · loudness · multicam · batch · python | Agent Skill that gives Claude Code, Cursor and Codex a local FFmpeg video editor: 42 typed Python tools covering cut, join, captions, audio, reframe, loudness and platform delivery, plus a contract-derived MCP server. Runs offline with no API keys or Python dependencies. | View Project → |
| claude-code-skills | ★ 1.4K | Skills | Python | claude-code · agent-skills · skill-marketplace · claude-plugin · prompt-engineering · skill-creator · workflow-automation · mcp · llm-eval · deep-research · codex · developer-productivity · plugin-manager · document-automation · meta-skill | A Claude Code plugin marketplace of production-ready skills spanning dev workflows, docs, research, evals and FinOps data. Its core meta-skill, skill-creator, guides building, validating and packaging your own skills with security and concurrency safeguards. | View Project → |
| pm-claude-skills | ★ 1.4K | Skills | HTML | agent-skills · prompt-library · product-management · professional-workflows · Claude · ChatGPT · Gemini · Cursor · Codex · MCP · CLI · decision-support | A library of more than 1,100 Markdown agent skills for professional and everyday tasks, installable across Claude, ChatGPT, Gemini, Cursor, Codex, and other assistants. Includes a CLI, MCP server, skill discovery, and typed decision workflows. | View Project → |
| agor | ★ 1.4K | AI Coding | TypeScript | coding agents · multi-agent · agent orchestration · git worktrees · MCP · team collaboration · self-hosted · agent sessions · AI teammates · developer tools | A self-hosted collaborative workspace for running coding agents such as Claude Code, Codex, and Gemini CLI on isolated Git branches. It provides agent sessions, a shared board, persistent AI teammates, and an MCP interface agents can use to manage work. | View Project → |
| tavily-python | ★ 1.4K | AI Tools | Python | web-search · search-api · rag · content-extraction · web-crawling · site-mapping · research-api · python-sdk · async · llm-grounding · agents · web-scraping · grounding · developer-tool | Python SDK for the Tavily API: web search, URL extraction, crawling, site mapping, and cited research, with sync and async clients. Commonly used to ground LLM/agent answers and build RAG context in one line of code. | View Project → |
| NeuroSploit | ★ 1.4K | AI Agents | Rust | penetration-testing · red-team · offensive-security · multi-agent · llm · rust · cli · autonomous-agents · owasp-llm-top10 · mitre-attack · sast · jailbreak · cve · tui · security-automation · grounded-findings | Rust CLI harness that drives a pool of LLMs (API key or local subscription/Ollama) to run autonomous pentest engagements: recon, agent selection, exploitation, cross-model validation and evidence-grounded reporting across black/white/grey-box, host, cloud and LLM red-team modes. | View Project → |
| haft | ★ 1.4K | AI Coding | Go | AI coding agents · project memory · engineering decisions · MCP · agent skills · evidence tracking · decision staleness · spec-driven development · local-first | Haft adds local project memory and engineering-decision governance to coding agents. It provides MCP integrations and skills for framing problems, comparing options, recording decisions, and checking evidence or specifications for staleness. | View Project → |
| ouroboros | ★ 1.4K | AI Agents | Python | autonomous-agent · self-modifying · persistent-memory · multi-agent-swarm · computer-use · desktop-agent · coding-agent · local-llm · mcp · self-evolving · skills-marketplace · background-consciousness · task-orchestration · headless-cli · git-versioned-evolution | Ouroboros is a self-hosted general-purpose AI agent with persistent identity and memory that works on external Git projects, runs a swarm of specialist subagents, and edits its own code, prompts, tools and deps under a reviewed Git history. Ships as a native desktop app or headless CLI, with remote APIs or local GGUF m | View Project → |
| generative-ai-use-cases | ★ 1.4K | AI Tools | TypeScript | generative AI · business applications · chat UI · RAG · AI agents · image generation · video generation · voice chat · MCP · AWS | A deployable AWS application showcasing business generative AI workflows, including chat, RAG, agents, media generation, and voice interaction. Built on Amazon Bedrock, it includes authentication and configuration options for adapting use cases to an organization. | View Project → |
| codedb | ★ 1.4K | MCP | Zig | code intelligence · MCP server · coding agents · code search · symbol navigation · dependency graphs · repository indexing · callpath tracing · Zig | A Zig-based code intelligence server that exposes repository search, symbol navigation, call tracing, and context tools to AI agents over MCP. Supports local indexing and remote GitHub repository queries; it provides context, not code editing. | View Project → |
| hermex | ★ 1.4K | AI Agents | Swift | ios · swiftui · swift · self-hosted · agent-client · chat-ui · mobile-cockpit · privacy · offline-cache · live-activity · app-intents · push-notifications · tailscale · sessions · skills · cron-tasks | Hermex is a native SwiftUI iOS 18+ client for a self-hosted hermes-webui AI agent. Your server does the compute; the phone is the control plane for streaming chat, sessions, skills, memory, cron tasks and model switching, with no analytics and no backend. | View Project → |
| fyagent | ★ 1.4K | AI Agents | Rust | agent management · AI assistant · desktop app · model management · MCP management · agent skills · prompt management · local-first · cross-platform | FyAgent is a local desktop control center for configuring AI agents and coding tools. It manages their models, accounts, skills, MCP servers, prompts, and memory across supported applications. | View Project → |
| xiaozhi-esp32-server-java | ★ 1.4K | AI Frameworks | Java | esp32 · voice-assistant · stt · tts · mcp · spring-ai · websocket · mqtt · rag · iot · smart-home · ota · function-calling · voice-cloning · device-management · knowledge-base | Java enterprise server plus Vue admin console for Xiaozhi ESP32 voice hardware. Multi-LLM (OpenAI/ZhiPu/Ollama/Dify/Coze), local and cloud STT/TTS with voice cloning, WebSocket/MQTT realtime audio, MCP tools, RAG, OTA and device monitoring. | View Project → |
| Tracely-ai | ★ 1.4K | AI Tools | Python | agent-observability · llm-evals · ci-cd · regression-testing · tracing · opentelemetry · llm-as-judge · failure-clustering · replay · alerts · monitoring · llmops · self-hosted · clickhouse · github-action · agents | Trace-native CI/CD for AI agents: ingests OTLP traces, grades runs with LLM judges, clusters failures, freezes bad runs into hermetic replayable regression cases, and blocks the PR that would ship them again at $0 replay cost. Self-hosted stack with MCP endpoint and alerts. | View Project → |
| keeper.sh | ★ 1.4K | MCP | TypeScript | calendar · caldav · ical · ics · google-calendar · outlook · icloud · fastmail · mcp-server · calendar-sync · self-hosted · rest-api · api-tokens · typescript · bun · docker | Self-hostable calendar sync engine that pulls from Google, Outlook, iCloud, Fastmail, CalDAV and ICS and pushes to destination calendars, plus a universal calendar MCP server and REST API so agents can manage all calendars. | View Project → |
| cli-agent-orchestrator | ★ 1.4K | AI Agents | Python | multi-agent · orchestration · tmux · claude-code · codex · kiro · cli-agents · mcp · agent-profiles · workflows · self-learning · memory · web-ui · python · developer-tools · fleet-coordination | CAO is a Python server that orchestrates multiple AI coding CLIs (Claude Code, Codex, Kiro, Copilot, Cursor, and more) as supervisor/worker agents inside isolated tmux sessions. It adds agent profiles, MCP/HTTP control planes, scheduled flows, memory, and self-learning. POSIX-only; requires tmux 3.3+ and an authenticat | View Project → |
| commonly | ★ 1.3K | AI Agents | TypeScript | multi-agent · agent-workspace · agent-memory · agent-skills · agent-identity · orchestration · self-hosted · mcp · task-board · litellm · agent-marketplace · human-in-the-loop · websocket · containerization · collaboration · openclaw | Self-hostable workspace where humans and cross-vendor AI agents (Claude Code, Codex, Cursor, OpenClaw) work together in pods. Each agent keeps its own name, memory, skills, workstation, and task queue; connect runtimes via MCP, CLI, or HTTP. Apache-2.0, Docker one-command install. | View Project → |
| PanWatch | ★ 1.3K | AI Agents | Python | self-hosted · stock-market · multi-agent · trading · portfolio-management · price-alerts · a-share · us-stocks · hk-stocks · quant · notifications · deepseek · langgraph · mcp · pwa · fastapi | PanWatch is a self-hosted AI stock monitoring assistant that combines scheduled LLM agents with the TradingAgents multi-agent framework to produce technical/news/fundamental analyses, bull-bear debate and portfolio decisions. It tracks A-share, HK and US markets, manages holdings, runs alerts and pushes reports to IM c | View Project → |
| mirobody | ★ 1.3K | AI Agents | Python | health-data · ai-agents · mcp-server · loinc · ucum · fhir · wearables · lab-reports · genomics · ocr · self-hosted · ehr · apple-health · terminology · embeddings · python | Python health data engine that ingests labs, wearables and genomics, maps names and units to LOINC/UCUM offline, and lets AI agents answer trend questions over the coded, self-hosted record. Also exposes every tool over MCP. | View Project → |
| Numerologist_skills | ★ 1.3K | Skills | Python | AI skills · Chinese astrology · Qimen Dunjia · Zi Wei Dou Shu · Ba Zi · hallucination reduction · prompt engineering · deterministic calculation | A set of auditable AI skills for Qimen Dunjia, Zi Wei Dou Shu, and Ba Zi. Skills constrain question gathering, terminology, calculation workflows, and output; a Python CLI handles fixed Qimen calculations. | View Project → |
| xmcp | ★ 1.3K | MCP | TypeScript | mcp · model-context-protocol · typescript · framework · mcp-server · file-system-routing · hot-reload · middleware · stdio · http · vercel · nextjs · express · developer-experience · monorepo · serverless | xmcp is a TypeScript framework for building and deploying MCP servers, with file-system routing for tools and prompts, hot reloading, middleware support, and zero-config Vercel deployment. It scaffolds new servers or adds MCP to existing Next.js/Express apps. | View Project → |
| saiku | ★ 1.3K | MCP | Java | MCP server · AI agents · semantic layer · OLAP · analytics · business intelligence · MDX · XMLA · typed API | Saiku is an OLAP semantic layer with a bundled stdio MCP server and typed APIs that let AI agents discover schemas and query cubes without writing MDX. It also provides browser-based analytics and dashboards. | View Project → |
| jobsync | ★ 1.3K | AI Tools | TypeScript | job search · resume review · job matching · job discovery · AI assistant · MCP · self-hosted · Ollama | Self-hosted job-search manager with AI resume reviews, job matching, cover-letter drafting, and scheduled job discovery. Includes an MCP server for agents to add jobs and interview questions with user approval; supports local Ollama or cloud providers. | View Project → |
| Easel | ★ 1.3K | AI Agents | Python | social-media · content-automation · agent · agent-skills · multi-platform-publishing · trend-discovery · content-calendar · xiaohongshu · douyin · zhihu · bilibili · video-generation · text-to-speech · image-generation · persona-memory · mcp | Easel is an open-source social-media AI agent (OpenClaw-powered) that runs a discover-plan-create-publish-attribute workflow across Xiaohongshu, Douyin, Zhihu and Bilibili, backed by 113 executable content skills and per-account persona memory. Python CLI plus a FastAPI/React workbench handle media generation and real | View Project → |
| agentkit | ★ 1.3K | AI Agents | TypeScript | crypto-wallet · onchain · web3 · agent-toolkit · action-providers · wallet-providers · stablecoin-payments · agents · evm · solana · base · tool-calling · typescript · python · monetization · framework-agnostic | Coinbase's framework- and wallet-agnostic toolkit that gives AI agents a crypto wallet and onchain actions. Ships TypeScript and Python packages with 50+ action providers, wallet providers (CDP, Privy, viem), and integrations for LangChain, Vercel AI SDK, MCP, and OpenAI Agents SDK. | View Project → |
| Wake | ★ 1.3K | AI Coding | Rust | coding agents · session manager · conversation search · transcript viewer · session resume · MCP server · local-first · multi-agent | A native desktop app for browsing, searching, and resuming coding-agent sessions across tools such as Claude Code, Codex, Cursor, and OpenCode. Includes a read-only MCP server and CLI for accessing indexed session history. | View Project → |
| tutor-skills | ★ 1.3K | Skills | Shell | claude-code · agent-skills · skill-pack · obsidian · study-notes · quiz-generation · flashcards · active-recall · pdf-parsing · codebase-onboarding · knowledge-base · learning · wiki-links · documentation-generation · shell-installer · prompt-pack | Two Claude Code skills: /tutor-setup converts PDFs, docs, or a codebase into an interlinked Obsidian study vault with notes and practice questions; /tutor then quizzes you and tracks concept-level progress. Shell installer, MIT licensed. | View Project → |
| smart-second-brain | ★ 1.3K | RAG | TypeScript | obsidian · obsidian-plugin · semantic-search · rag · embeddings · knowledge-graph · ai-agents · local-first · mcp · skills · hybrid-search · note-taking · privacy · chat-interface · typescript · vector-search | Open-source Obsidian plugin adding hybrid semantic search, an auto-generated topic knowledge graph, and an agent that reads/writes notes with skills, memory and MCP. Search and graph work without an AI provider; embeddings unlock semantic mode. | View Project → |
| iot-dc3 | ★ 1.3K | MCP | Java | industrial IoT · physical AI · MCP gateway · AI agents · device control · edge computing · telemetry · protocol drivers · Modbus · OPC UA · MQTT · audit trails | Java-based industrial IoT runtime with 36 protocol drivers, edge-to-cloud telemetry, and an MCP gateway for governed agent access to devices. Supports natural-language queries, device operations, alarm analysis, and audited tool calls. | View Project → |
| jupyter-mcp-server | ★ 1.3K | MCP | Python | mcp · mcp-server · jupyter · notebooks · code-execution · jupyterlab · code-sandboxes · python · oauth · opentelemetry · multimodal · jupyterhub · claude-code · streamable-http | MCP server that lets AI agents connect to and control Jupyter Notebooks in real time: browse files, manage notebooks/kernels, edit and run cells, and read multimodal outputs. Works with any MCP client and can execute code in local or cloud code sandboxes. | View Project → |
| Aegis | ★ 1.3K | Skills | Python | agent-skills · ai-coding · coding-agents · method-pack · spec-driven-development · architecture-driven · baseline-first · evidence-verified · tdd · plugin · claude-code · codex · opencode · multi-host · verification · drift-checking | Aegis is a host-agnostic method pack of skills/plugins that makes AI coding agents plan against a project's real architecture baseline, verify completion with fresh evidence, and avoid unsafe or ghost-code changes. Ships installers for Codex, Claude Code, OpenCode, Cursor and many other skill-aware hosts. | View Project → |
| langchat | ★ 1.3K | AI Agents | Java | AI agent platform · enterprise AI · multi-model · RAG · knowledge base · MCP · skills · intelligent data analysis · RBAC | Java-based enterprise AI application platform combining agents, multi-model support, RAG knowledge bases, skills, MCP, and natural-language data querying. Includes RBAC and a Vue 3 interface. | View Project → |
| ai-setup | ★ 1.3K | AI Coding | TypeScript | claude-code · cursor · codex · agent-skills · mcp · context-management · cli · developer-tools · ai-agents · github-copilot · opencode · agents-md · cursorrules · config-sync · compaction · typescript | Caliber is a CLI that keeps AI coding agent context in sync: it generates and refreshes CLAUDE.md, Cursor rules, AGENTS.md and Copilot instructions, mirrors skills/MCP config across Claude Code, Cursor, Codex, OpenCode and Copilot, scores config quality, and offers lossless transcript compaction. | View Project → |
| tools | ★ 1.3K | AI Tools | Python | agents · agent-tools · multi-agent · mcp · memory · browser-automation · computer-use · function-calling · python · aws-bedrock · swarm · web-search · image-generation · opentelemetry · ollama · openai | Python tool library for Strands Agents that gives LLM agents ready-made capabilities: file/shell/Python execution, memory backends, web search and scraping, image/video/audio generation, browser and desktop control, MCP client, and multi-agent swarm/graph orchestration. Experimental and security-sensitive. | View Project → |
| Agents-Anywhere | ★ 1.3K | AI Agents | TypeScript | agent-workbench · remote-control · cross-device · self-hosted · multi-agent · sessions · workspaces · terminal · file-management · ACP | A self-hostable, cross-device workbench for monitoring and controlling Codex, Claude Code, and DeepSeek Harness running on connected work machines. Desktop, mobile, and web clients support session management, approvals, files, and remote terminals. | View Project → |
| k-dense-byok | ★ 1.3K | AI Agents | TypeScript | scientific-research · research-assistant · bioinformatics · drug-discovery · multi-agent · local-first · BYOK · MCP · scientific-skills · lab-notebook · data-analysis · Ollama | A desktop AI research agent that can inspect project files, write and run analysis code, search scientific sources, and delegate work to specialist agents. Includes scientific skills, workflow templates, file previews, and a lab notebook; supports hosted providers and local Ollama models. | View Project → |
| mcp-searxng | ★ 1.3K | MCP | TypeScript | mcp · mcp-server · searxng · web-search · privacy · self-hosted · url-reader · pdf-reading · search-api · claude · cursor · oauth · docker · caching · typescript · nodejs | MCP server that exposes SearXNG (self-hosted or trusted instance) web search to Claude, Cursor and other MCP clients. Adds pagination, URL/PDF reading, suggestions, caching, proxies, OAuth and STDIO or HTTP transports — no paid search API key required. | View Project → |
| SkillNet | ★ 1.3K | Skills | Python | AI skills · agent skills · skill discovery · skill creation · skill evaluation · skill routing · semantic search · knowledge graph · skill composition · CLI · Python SDK | SkillNet provides a Python SDK, CLI, and browser interface for discovering, creating, evaluating, analyzing, and routing reusable AI agent skills. It builds searchable skill indexes and relationship graphs to help select capabilities for a task. | View Project → |
| heym | ★ 1.3K | AI Agents | Python | agent orchestration · multi-agent · workflow automation · self-hosted · human-in-the-loop · MCP · RAG · agent evaluation · observability · browser automation · coding agents · visual workflow builder | A self-hosted platform for visually building, orchestrating, and operating agent workflows. It includes human approval checkpoints, RAG, MCP integration, evaluations, execution observability, and REST/SSE interfaces. | View Project → |
| whiteboard | ★ 1.3K | AI Coding | TypeScript | AI coding agents · code review · software design · desktop app · semantic diff · agent workspace · diagrams · decision logs | A desktop workspace for humans and coding agents to review code changes and collaborate on software design. Agents can draw diagrams, present semantic diffs, and record decisions linked to code. | View Project → |
| openpets | ★ 1.2K | MCP | TypeScript | desktop-pet · mcp · agent-integrations · claude-code · opencode · cursor · plugin-sdk · electron · typescript · local-first · sandboxed-plugins · tts · hooks · tamagotchi · notifications · ipc | Local-first Electron desktop companion with animated pets. Ships an MCP stdio server plus hooks for Claude Code, OpenCode, Cursor and Pi so coding agents can trigger pet reactions, and a sandboxed plugin SDK v3 for custom pet abilities. | View Project → |
| openinference | ★ 1.2K | AI Tools | Python | observability · tracing · opentelemetry · llmops · instrumentation · telemetry · evals · monitoring · span-attributes · ai-observability · debugging · aiops · semantic-conventions · agent-tracing · multimodal · python | OpenInference is an OpenTelemetry-based spec plus Python/JS/Java instrumentation packages that trace LLM and agent calls. It emits standardized spans for models, tools, retrievals, and MCP, exportable to any OTel-compatible backend such as Arize Phoenix. | View Project → |
| AWorld | ★ 1.2K | AI Agents | Python | multi-agent · agent-harness · agent-framework · agent-runtime · cli · skills · self-evolution · evaluation-loop · context-management · deep-search · rl-training · benchmarks · code-generation · world-model · python | Python agent harness that runs a multi-agent CLI (orchestrator, developer, evaluator) to build, evaluate and self-improve agents and apps. Includes skills, MCP support, deep-search browsing, RL training and benchmark harnesses like GAIA and BrowseComp. | View Project → |
| openpets | ★ 1.2K | AI Tools | TypeScript | desktop-pet · mcp · plugin-sdk · electron · typescript · claude-code · opencode · coding-agents · local-first · agent-integrations · sandboxed-plugins · desktop-companion · reminders · cli · cross-platform · notifications | Electron desktop-companion platform where sandboxed JS/TS plugins and coding agents (Claude Code, OpenCode, Cursor) or a local MCP stdio server drive animated pet reactions, reminders, timers and HUDs. Agent hooks stay local and sanitize code, paths and secrets. | View Project → |
| thClaws | ★ 1.2K | AI Agents | Rust | agent-harness · multi-agent · agent-teams · mcp · skills · plugins · rust · cli · desktop-gui · tauri · multi-provider · local-llm · ollama · knowledge-base · browser-automation · scheduler | thClaws is a native-Rust AI agent harness shipping as one binary with desktop GUI, CLI, headless and webapp surfaces. It supports 27+ providers, MCP servers, skills, plugins, subagents and multi-process agent teams, plus knowledge bases, scheduling and media generation. | View Project → |
| aegra | ★ 1.2K | AI Agents | Python | langgraph · self-hosted · agent-backend · fastapi · postgresql · redis · agent-protocol · streaming · human-in-the-loop · observability · opentelemetry · cron · pgvector · docker · python · no-vendor-lock-in | Self-hosted LangGraph/LangSmith Deployments alternative: an Apache-2.0 FastAPI + PostgreSQL agent backend that runs your existing LangGraph code unchanged, with streaming, cron, human-in-the-loop, auth, and OTLP tracing. | View Project → |
| omnigraph | ★ 1.2K | AI Agents | Rust | graph-database · knowledge-graph · context-graph · agent-memory · multi-agent · lakehouse · lance · datafusion · apache-arrow · rust · mcp · vector-search · hybrid-search · git-style-branching · s3 · cedar-policy | Rust lakehouse graph engine storing agent memory and context graphs on object storage (Lance/Arrow), with git-style branching so many agents write in isolation and merge on review. Bundles vector ANN, full-text and RRF retrieval, Cedar policy as code, plus CLI/server, TS SDK and MCP server. | View Project → |
| Gym | ★ 1.2K | AI Frameworks | Python | agent-evaluation · LLM-evaluation · reinforcement-learning · benchmarks · training-environments · rollouts · tool-calling · verifiers · agent-training · model-training · scalable-evaluation | Python library for building environments to evaluate and train LLMs and agents. It provides benchmark environments, agent harnesses, verifiers, rollout collection, and scalable execution for evaluation and reinforcement-learning workflows. | View Project → |
| jevlike | ★ 1.2K | AI Frameworks | Python | one-pass scorer · system-one model · text ranking · attention pooling · training toolkit · evaluation metrics · calibration · byte encoder · frozen encoder · PyTorch · CLI · research starter · vision scorer | Python starter for training a small one-pass scorer that turns text plus a changing list of options into one probability per option, an independent alternative to TypeSafe's Jev. Ships train/eval/predict CLIs, byte and frozen Hugging Face encoder paths, and Doom/chess vision-scoring examples. | View Project → |
| OpenContext | ★ 1.2K | MCP | JavaScript | context-management · agent-memory · mcp-server · knowledge-base · cli · desktop-app · tauri · skills · slash-commands · cursor · claude-code · codex · opencode · vector-search · local-first · developer-tools | OpenContext gives AI coding agents persistent memory: an `oc` CLI + MCP server + user-level Skills/slash commands for Cursor/Claude Code/Codex, plus Tauri desktop and web GUIs to capture, vector-search and reuse project knowledge across agents and repos. | View Project → |
| reverse-api-engineer | ★ 1.2K | AI Agents | Python | ai-agents · web-scraping · api-client-generation · browser-automation · reverse-engineering · har-capture · mcp · playwright · codegen · cli · openapi · claude · llm · python · typescript | CLI agent that browses a site (autonomously via Playwright/Chrome MCP, or manually) and turns captured HAR traffic into a working typed API client in Python, TypeScript, Go, Java, C#, PHP, Ruby or C. | View Project → |
| agentic-soc-platform | ★ 1.2K | AI Agents | Python | agentic SOC · cybersecurity · security operations · threat detection · incident response · SIEM · SOAR · alert triage · threat intelligence · playbooks · private deployment | An open-source agentic security operations platform for alert triage, incident investigation, threat-intelligence enrichment, and SOAR playbooks. Integrates SIEM sources such as Splunk and ELK, supports private deployment, and exposes SOC capabilities to coding agents through a CLI and plugins. | View Project → |
| free4chat | ★ 1.2K | AI Agents | TypeScript | multi-agent · mcp · human-agent-collaboration · webrtc · voice-chat · cloudflare-workers · durable-objects · serverless · realtime · ephemeral · agent-runtime · sfu · acp · tasks · nextjs · typescript | Experimental temporary collaboration Rooms where humans and independently running agents meet over WebRTC voice/text, files and tasks. Agents join via a stateless MCP Room API or a Go runtime; Free4Chat owns only ephemeral rendezvous, transport and bounded shared state, not your models or credentials. | View Project → |
| magic | ★ 1.2K | AI Agents | C# | AI agents · MCP server · code generation · full-stack app builder · natural language programming · self-hosted · Hyperlambda · sandboxing · RBAC · API generation | A self-hosted .NET platform for generating full-stack apps, APIs, and AI agents from natural language. Its MCP plugin exposes endpoints as agent tools, while Hyperlambda sandboxing and role-based permissions control execution. | View Project → |
| open-reverselab | ★ 1.2K | AI Agents | Python | reverse engineering · binary analysis · MCP server · autonomous agent · malware analysis · CTF · Android analysis · PE analysis · Ghidra · Frida · x64dbg · Rizin | An AI reverse-engineering agent platform with 100+ MCP tools for Ghidra, Frida, x64dbg, and Rizin. Includes runnable knowledge-base workflows for binary and Android analysis, malware research, and CTF challenges. | View Project → |
| Awesome-Journal-Skills | ★ 1.2K | Skills | Stata | agent-skills · Claude Code · Codex · academic research · journal-specific · academic writing · econometrics · causal inference · peer review · scholarly publishing | A collection of journal-specific agent skill packs for Claude Code and Codex, covering research planning, empirical methods, manuscript and table conventions, and reviewer responses across hundreds of journals and conferences. | View Project → |
| wisp-science | ★ 1.2K | AI Agents | Rust | local-first · desktop-app · scientific-computing · bioinformatics · mcp · agent-skills · python · r · ssh · gpu · wsl · rust · tauri · research-assistant · reproducible-research · acp | Local-first desktop AI research workbench (Rust/Tauri) where an agent runs Python and R, queries ~80 scientific databases through bundled MCP servers, and executes jobs on local, WSL, SSH or GPU hosts. Bring your own OpenAI-compatible or Anthropic model; data, keys and history stay on your machine. | View Project → |
| ref-tools-mcp | ★ 1.2K | MCP | TypeScript | documentation search · API docs · coding agents · context optimization · token-efficient · stdio · HTTP | An MCP server that lets coding agents search technical documentation and fetch relevant URL content as Markdown. Session-aware search and page filtering aim to provide useful context with fewer tokens. | View Project → |
| GPT-RAG | ★ 1.2K | RAG | Python | agentic-rag · enterprise-rag · Azure · Foundry IQ · zero-trust · multi-source retrieval · MCP · IaC · observability | An Azure solution accelerator for deploying secure agentic RAG applications. It combines Microsoft Agent Framework orchestration with Foundry IQ retrieval across enterprise data sources, with Azure AI Search as an alternative backend. | View Project → |
| ai | ★ 1.2K | AI Agents | Python | autogen · crewai · pydanticai · smolagents · langchain · mcp · claude-skill · tutorials · multi-agent · agentops · ollama · lmstudio · n8n · openai-agents · crawl4ai · youtube | Tutorial hub of runnable AI agent examples covering AutoGen, CrewAI, PydanticAI, Smolagents, OpenAI Agents and AgentOps, plus MCP/n8n integrations and a Claude Code skill for scaffolding agent projects. Good for developers learning agents by running code. | View Project → |
| coding-tools-mcp | ★ 1.2K | MCP | Python | coding · workspace tools · file search · patching · command execution · Git · sandboxing · model-neutral · stdio · Streamable HTTP | A model-neutral MCP server that gives AI clients workspace-confined file, search, patch, command-execution, and Git tools. Supports stdio and Streamable HTTP, with permission modes and optional sandboxing. | View Project → |
| jevgrep | ★ 1.2K | AI Coding | TypeScript | coding agents · code search · semantic search · context retrieval · CLI · repository exploration · agent skill · SWE-bench | A CLI that helps coding agents find relevant files and source context by asking repository questions. It uses Jev to rank folders, files, and declarations, then returns evidence for the agent to use. | View Project → |
| fess | ★ 1.1K | RAG | Java | enterprise-search · self-hosted · opensearch · crawler · full-text-search · semantic-search · ai-search · llm · mcp · rest-api · multilingual · faceted-search · sso · docker · java · site-search | Java-based self-hosted enterprise search server on OpenSearch. Crawls web, file, DB and cloud sources with a browser admin UI, REST API, 20+ language analysis, and AI/RAG semantic search plus MCP support. | View Project → |
| mongodb-mcp-server | ★ 1.1K | MCP | TypeScript | mongodb · mcp-server · mongodb-atlas · database · typescript · read-only-mode · atlas-api · vector-search · mongodb-assistant · oauth · stdio · agent-plugins | Official MongoDB MCP server exposing database and Atlas tools, resources, and an assistant to MCP clients like Cursor, VS Code, Claude, and Codex. Supports stdio/local and remote OAuth Atlas connections with a read-only mode by default. | View Project → |
| doc7 | ★ 1.1K | AI Tools | Go | document AI · multimodal · document conversion · PDF · Office files · vision-language models · Markdown · local AI · CLI · MCP · Go SDK · HTTP API | A Go CLI, SDK, MCP server, and HTTP service that converts PDFs, Office files, scans, and images into AI-ready Markdown using an OpenAI-compatible multimodal model. Supports local endpoints such as Ollama and LM Studio. | View Project → |
| elastic-labs | ★ 1.1K | RAG | Jupyter Notebook | rag · vector-search · semantic-search · hybrid-search · elasticsearch · langchain · embeddings · question-answering · chatbot · notebooks · genai · elser · rrf · document-chunking · inference · openai | Collection of Jupyter notebooks and example apps showing AI-powered search with Elasticsearch as a vector database. Covers RAG, hybrid/semantic search, LangChain and OpenAI integrations, and document chunking for LLM applications. | View Project → |
| agentrq | ★ 1.1K | AI Agents | Go | agent-supervision · human-in-the-loop · mcp-server · acp-gateway · task-management · self-hosted · claude-code · agent-orchestration · real-time · task-scheduler · kanban · live-terminals · desktop-app · workflow-graph · webmcp · multi-agent | AgentRQ is a self-hosted human-in-the-loop platform for supervising AI agents: agents see and update workspace tasks over MCP, while you approve tool calls, watch live terminals on enrolled machines, and trigger work via schedules, events and workflows. | View Project → |
| stride-gpt | ★ 1.1K | AI Tools | Python | threat-modeling · security · STRIDE · MITRE-ATT&CK · DREAD · attack-trees · OWASP-LLM-Top-10 · SARIF · data-flow-diagrams · agentic-AI-security · cli · litellm · drawio · streamlit · secops | AI-powered threat modeling CLI and Streamlit app that uses LLMs to generate STRIDE threat models, attack trees, DFDs and mitigations from app descriptions, codebases or architecture diagrams. Supports MITRE ATT&CK/ATLAS mapping, DREAD scoring, and SARIF/Markdown/HTML reports. | View Project → |
| CloudBase-AI-Toolkit | ★ 1.1K | MCP | TypeScript | mcp · mcp-server · agent-skills · cloudbase · backend · database · auth · cloud-functions · deployment · hosting · vibe-coding · ai-coding · ide-plugin · typescript · tencent-cloud · postgresql | Tencent CloudBase AI Toolkit is the backend integration layer for AI coding agents: an MCP server (@cloudbase/cloudbase-mcp) plus plugins and agent skills that let Cursor, Claude Code, Codex and others create databases, configure auth, deploy functions/hosting and read logs from chat. Requires your own CloudBase enviro | View Project → |
| kong | ★ 1.1K | AI Agents | Python | reverse-engineering · binary-analysis · ghidra · deobfuscation · decompilation · agentic-ai · llm-orchestration · type-recovery · symbol-recovery · symbolic-execution · cli · tui · evals · cost-tracking · pyghidra · call-graph-analysis | Kong is an agentic reverse-engineering pipeline that drives Ghidra in-process and orchestrates Claude/GPT-4o to recover function names, types and structs from stripped, obfuscated binaries. Includes agentic deobfuscation, signature matching, eval harness and cost tracking. | View Project → |
| awesome-deepseek-harness | ★ 1.1K | AI Agents | Python | DeepSeek Harness · agent plugins · multi-agent orchestration · coding assistants · plugin ecosystem · agent tools · skills · MCP · curated list | A curated directory of DeepSeek Harness plugins, tools, and infrastructure, organized by areas such as agent orchestration, search, memory, IDE clients, and runtime operations. Includes installation guidance and a generated catalog. | View Project → |
| ai-engineering-from-scratch-zh | ★ 1.1K | Skills | Python | agent-skills · AI-engineering · AI-agents · LLM · MCP · coding-agents · Chinese · tutorial · learning-paths · AI-education | A Simplified Chinese AI engineering curriculum with 523 lessons spanning ML foundations, LLMs, MCP, and agent systems. Includes installable AI tutor skills for personalized study, quizzes, and focused MCP or agent-skills learning paths. | View Project → |
| nebula | ★ 1.1K | AI Agents | Python | pentesting · cybersecurity · ai-agents · recon · vulnerability-assessment · langgraph · security-automation · local-first · claude-agent-sdk · evidence-management · report-generation · oci-isolation · scope-enforcement · note-taking · chromadb · desktop-workbench | Nebula is a local-first AI security workbench where agents assist recon, note-taking, and vulnerability analysis while the operator controls scope, approvals, and isolated execution of pentest tools. | View Project → |
Vibe Coding Discover