| mcp-toolbox | ★ 16K | MCP | Go | mcp · mcp-server · database · sql · postgresql · mysql · bigquery · spanner · nl2sql · agent-tools · connection-pooling · opentelemetry · authentication · go · gemini-cli · claude-code | Google's open source MCP server that connects AI agents and IDEs to databases. Ships prebuilt tools for Postgres, MySQL, BigQuery, Spanner and more, plus a tools.yaml framework for custom secure SQL, semantic-search and NL2SQL tools. | View Project → |
| ai-berkshire | ★ 16K | Skills | HTML | claude-code · codex · agent-skills · prompt-packs · multi-agent · value-investing · equity-research · financial-analysis · stock-screening · portfolio-management · investment-checklist · report-generation · anthropic · earnings-analysis · china-stocks | A pack of 20 Claude Code / Codex skills that turns a coding agent into a value-investing research team: four-master methodologies (Buffett, Munger, Duan Yongping, Li Lu), multi-agent parallel and adversarial analysis, financial-data verification tools, and reproducible report workflows. | View Project → |
| text-to-cad | ★ 16K | Skills | Python | agent-skills · cad · cae · cam · 3d-printing · gcode · urdf · robotics · step · stl · dxf · opencascade · build123d · mechanical-engineering · slicer · text-to-cad | A library of installable agent skills that let coding agents generate, inspect and hand off CAD/CAE/CAM artifacts: CAD geometry (STEP/STL/3MF/GLB), DXF drawings, URDF/SRDF/SDF robot files, G-code slicing and Bambu Lab print jobs. Installs via the Skills CLI or Claude Code/Codex plugins. | View Project → |
| trigger.dev | ★ 16K | AI Agents | TypeScript | durable-workflows · ai-agents · background-jobs · task-orchestration · queues · retries · cron-schedules · observability · tracing · human-in-the-loop · llm-streaming · realtime · typescript-sdk · self-hosting · mcp-server · serverless | Open-source TypeScript platform for building and deploying durable AI agents and workflows: long-running tasks with no timeouts, retries, queues, cron schedules, human-in-the-loop waits, realtime LLM streaming, and full tracing. Self-hostable via Docker or Kubernetes. | View Project → |
| learn-harness-engineering | ★ 16K | AI Coding | TypeScript | harness engineering · AI coding agents · agent reliability · verification workflows · agent state management · context engineering · agent loops · graph engineering · multi-agent workflows · tutorial | A multilingual, project-based course on making AI coding agents more reliable through harness design. Covers instructions, tools, environment, state, verification, automated loops, and graph-based workflows, with lectures, projects, templates, and a harness-creator skill. | View Project → |
| coder | ★ 16K | AI Coding | Go | cloud-development-environments · remote-development · self-hosted · ai-coding-agents · ai-gateway · llm-proxy · mcp · terraform · devcontainers · kubernetes · docker · wireguard · ide-integration · model-governance · audit-logging · go | Self-hosted platform that provisions Terraform-defined cloud dev environments over a secure tunnel and runs AI coding agents in its control plane, with an AI Gateway for model auth, cost tracking, and audit logs. Useful if you want agent-driven coding on your own infra without LLM keys in workspaces. | View Project → |
| SurfSense | ★ 16K | RAG | Python | local-first · air-gapped · privacy · document Q&A · citations · knowledge base · document generation · podcasts · web scraping · self-hosted | A local-first NotebookLM alternative for indexing documents and answering questions with citations. It can generate study materials, reports, slides, and podcasts on your machine, with local models and air-gapped use supported. | View Project → |
| xiaohongshu-mcp | ★ 16K | MCP | Go | mcp · mcp-server · xiaohongshu · rednote · social-media-automation · browser-automation · content-publishing · headless-browser · golang · http-api · claude-code · cursor · docker · cookies-auth · search · comment-automation | A Go MCP server that drives a headless browser to access Xiaohongshu (RED): login, publish image/video posts, search notes, read feeds and note details, and like, favorite, or comment. Connect it to Claude Code, Cursor or any MCP client over HTTP at /mcp. | View Project → |
| unstructured | ★ 16K | RAG | HTML | document-parsing · etl · rag · ocr · pdf · chunking · embeddings · mcp · data-ingestion · nlp · preprocessing · pdf-to-json · langchain · vector-database · document-conversion · unstructured-data | Python library that partitions 60+ document types (PDF, HTML, DOCX, email, images) into structured elements for LLM and RAG pipelines, with chunking, enrichment, and an MCP server for agent workflows. | View Project → |
| huobao-drama | ★ 15K | AI Tools | Vue | AI video generation · short drama · script generation · storyboarding · image generation · video editing · multi-agent · desktop app | An AI-powered short-drama production tool that automates script rewriting, asset extraction, storyboard creation, image and video generation, and episode compositing. Includes four Mastra agents, configurable model providers, and a desktop app. | View Project → |
| OpenMetadata | ★ 15K | AI Tools | TypeScript | data-catalog · metadata · context-layer · mcp-server · semantic-search · knowledge-graph · agent-memory · data-lineage · data-governance · data-quality · data-contracts · ontologies · column-level-lineage · rag-context · openlineage · data-discovery | OpenMetadata is an open metadata and data-catalog platform that unifies lineage, quality, governance, glossaries, data contracts and agent memory into a knowledge graph. It ships an MCP server, semantic search, REST APIs and a Python AI SDK so LLMs and agents can read and write governed data context. | View Project → |
| hypit | ★ 15K | AI Tools | TypeScript | ai-video · video-generation · video-clone · text-to-video · agentic-ai · ai-agents · video-editing · dsl · ffmpeg · captions · b-roll · monorepo · plugin-system · skill · automation · generative-ai | Hypit is a TypeScript video-authoring DSL and skill that lets AI coding agents clone a reference video's full workflow (footage, captions, B-roll, effects) or write one from scratch, then batch-render many variants via FFmpeg and headless Chromium. Generation models are optional. | View Project → |
| awesome-claude-skills | ★ 15K | Skills | — | claude-skills · claude-code · awesome-list · agent-skills · anthropic · skill-discovery · progressive-disclosure · prompt-engineering · curated-list · claude-desktop · skill-creator · marketplace · community-skills · documentation | Curated awesome-list of Claude Skills plus install instructions, official and community skill collections, creation guides, and best practices for Claude Code, Claude Desktop, and the Skills API. | View Project → |
| Skill_Seekers | ★ 15K | Skills | Python | claude-skills · mcp-server · rag · documentation-scraping · web-scraping · pdf · knowledge-base · embeddings · code-analysis · ast-parsing · conflict-detection · multi-source · vector-databases · ai-coding-assistants · automation · python | CLI and MCP server that turns docs sites, GitHub repos, PDFs and 15+ other sources into Claude AI skills, RAG chunks and IDE context files, exporting to 22 targets such as Claude, LangChain, Pinecone and Cursor. | View Project → |
| botpress | ★ 15K | AI Agents | TypeScript | chatbots · agents · LLM · conversational-AI · SDK · CLI · integrations · low-code · deployment · TypeScript · OpenAI · GPT-4 · chatbot-platform · hub | Botpress is an open-source platform and TypeScript SDK/CLI for building, deploying, and managing GPT/LLM chatbots and agents. It ships integrations, a CLI, and example bots-as-code for the Botpress Cloud runtime. | View Project → |
| cc-haha | ★ 15K | AI Coding | TypeScript | claude-code · coding-agent · multi-agent · mcp · computer-use · electron · desktop-app · skill-marketplace · git-worktree · diff-review · multi-model · im-integration · local-first · typescript · react · scheduled-tasks | Local-first Electron desktop workspace for Claude Code and coding agents: multi-session GUI, Agent Teams, Git worktree/diff review, visual MCP and SubAgent managers, skill marketplace, Computer Use, multi-model support and H5/IM remote access. | View Project → |
| unity-mcp | ★ 15K | MCP | C# | unity · game-development · mcp-server · unity-editor · llm · ai-integration · automation · csharp · python · 3d · claude · cursor · scene-management · asset-management · unity3d · gamedev | MCP server bridging AI assistants (Claude, Cursor, VS Code, local LLMs) to the Unity Editor. Exposes ~47 tools to create scenes, edit C# scripts, manage assets, run tests, and automate game dev workflows. | View Project → |
| ai-goofish-monitor | ★ 14K | AI Tools | Python | xianyu · goofish · playwright · web-scraping · monitoring · multimodal · llm · notifications · fastapi · cron-scheduler · proxy-rotation · price-tracking · automation · docker · e-commerce · python | AI-powered Xianyu/Goofish marketplace monitor: Playwright scrapes listings and a multimodal LLM judges which products match your criteria, with a web admin UI, cron scheduling, multi-account/proxy rotation, and push notifications. | View Project → |
| palmier-pro | ★ 14K | AI Tools | Swift | AI video editor · video generation · image generation · MCP · macOS · timeline editing · AI agents | A Swift-native macOS video editor with built-in AI video and image generation, an in-app agent, and an MCP server that lets external agents edit projects on the timeline. Current binary releases are proprietary; published source covers versions through v0.7.6. | View Project → |
| memU | ★ 14K | RAG | Python | agent-memory · cross-agent-memory · session-retrieval · embeddings · vector-search · skill-extraction · coding-agents · MCP · SQLite · PostgreSQL | memU captures knowledge from agent sessions, stores it as searchable memory, and retrieves relevant context across agents and devices. It provides host adapters for coding agents, local SQLite or PostgreSQL storage, and automatic skill extraction. | View Project → |
| FreeToken | ★ 14K | AI Frameworks | Python | LLM inference · MoE serving · local inference · edge AI · GPU · CPU offloading · OpenAI-compatible API · Anthropic-compatible API · model serving | FreeToken is a local MoE inference and serving engine that runs large open-weight models across GPU, CPU, and host memory. It provides OpenAI- and Anthropic-compatible APIs, plus a desktop app and CLI. | View Project → |
| instructor | ★ 14K | AI Frameworks | Python | Python · Structured Output · Pydantic | Structured LLM outputs validated by Pydantic, with retries and streaming. | View Project → |
| instructor | ★ 14K | AI Tools | Python | structured-outputs · pydantic · json-schema · function-calling · validation · retries · streaming · llm-extraction · type-safety · multi-provider · python · openai · anthropic · ollama · data-extraction · llm-ops | Python library that turns any LLM into a validated structured-output client: define a Pydantic model, call create(response_model=...), and get typed objects with automatic retries, streaming, and nested-object support across OpenAI, Anthropic, Google, Ollama and more. | View Project → |
| E2B | ★ 14K | AI Agents | Python | sandbox · code-execution · ai-agents · code-interpreter · computer-use · secure-execution · sdk · python · typescript · llm · cloud-infrastructure · firecracker · self-hosting · agent-tools | E2B is open-source infrastructure plus JS/Python SDKs for running AI-generated code in secure isolated sandboxes. It provides code interpreter and desktop/computer-use APIs so agents can execute code and control real tools safely. | View Project → |
| Open-LLM-VTuber | ★ 14K | AI Tools | Python | live2d · voice-interaction · ai-companion · vtuber · tts · asr · local-llm · offline · desktop-pet · voice-interruption · cross-platform · mcp · speech-recognition · voice-cloning · chatbot · visual-perception | Cross-platform voice-interactive AI companion with a Live2D avatar and desktop pet mode. Runs locally with pluggable LLM (Ollama, OpenAI, Claude, Gemini...), ASR and TTS backends, supporting voice interruption, visual perception and MCP tool servers. | View Project → |
| agent-framework | ★ 14K | AI Frameworks | Python | agents · multi-agent · orchestration · workflows · python · dotnet · sdk · middleware · observability · human-in-the-loop · agent-skills · declarative-agents · opentelemetry · hosting · checkpointing · llm-providers | Microsoft's open multi-language SDK for building, orchestrating and hosting production AI agents and multi-agent workflows in Python and .NET. Ships graph workflows, middleware, OpenTelemetry observability, declarative YAML agents and Foundry hosting. | View Project → |
| opencode | ★ 14K | AI Coding | Go | terminal · tui · cli · ai-coding-agent · code-assistant · multi-provider · mcp · lsp · session-management · sqlite · shell-execution · non-interactive-mode · go · archived | Archived Go terminal AI coding agent, continued as charmbracelet/crush. Bubble Tea TUI that chats with Claude, GPT, Gemini, Groq, Bedrock or local models; runs shell commands, edits files, uses LSP and MCP servers, and supports non-interactive -p mode. | View Project → |
| typescript-sdk | ★ 13K | MCP | TypeScript | mcp · typescript · sdk · mcp-server · mcp-client · streamable-http · stdio · oauth · json-rpc · tool-calling · middleware · monorepo · nodejs · bun · deno · standard-schema | Official TypeScript SDK implementing the Model Context Protocol, split into @modelcontextprotocol/server and /client packages. Provides stdio and Streamable HTTP transports, OAuth helpers, framework middleware, and runnable examples for building MCP servers and clients. | View Project → |
| semantica | ★ 13K | AI Frameworks | Python | knowledge-graph · context-graph · graph-rag · provenance · ai-governance · decision-intelligence · ontology · agent-memory · explainable-ai · semantic-search · reasoning-engine · entity-resolution · mcp · sparql · shacl · python | Semantica is a Python graph-native context and knowledge-graph layer for AI systems: ingest data, build context graphs, and run deterministic graph reasoning with W3C PROV-O provenance. Adds graph RAG, decision audit trails, ontology governance, and MCP/LangChain/CrewAI integrations on top of your existing LLM stack. | View Project → |
| EverOS | ★ 13K | RAG | Python | agent-memory · long-term-memory · local-first · markdown · lancedb · hybrid-search · vector-search · bm25 · knowledge-base · reflection · embeddings · mcp · multimodal-ingestion · sqlite · self-evolving-memory · python | EverOS is a local-first memory runtime for AI agents: memories are stored as plain Markdown with SQLite + LanceDB indexes for hybrid keyword/vector retrieval. It adds reflection, skill extraction, a Knowledge Wiki, and MCP/plugin integrations, requiring only Python 3.12 and one LLM API key to start. | View Project → |
| pr-agent | ★ 13K | AI Coding | Python | Python · PR Review · Git | AI agent that reviews, describes, and improves pull requests automatically. | View Project → |
| langchain4j | ★ 13K | AI Frameworks | Java | java · jvm · llm · rag · agents · tool-calling · mcp · embeddings · vector-store · chat-memory · prompt-templating · spring-boot · quarkus · embeddings-store · guardrails · ai-orchestration | LangChain4j is an idiomatic Java library for building LLM-powered JVM apps, with a unified API over 20+ model providers and 30+ embedding stores. It covers tool calling (incl. MCP), agents, RAG pipelines, chat memory and prompt templating, with Spring Boot and Quarkus integrations. | View Project → |
| eino | ★ 13K | AI Frameworks | Go | golang · llm-framework · agent-development-kit · multi-agent · orchestration · graph-workflows · streaming · tool-calling · react-agent · human-in-the-loop · interrupt-resume · callbacks · rag · chatmodel · langchain-alternative · byteDance | Eino is ByteDance's Go LLM application framework, modeled on LangChain and Google ADK. It offers component abstractions (ChatModel, Tool, Retriever), a graph/compose orchestration layer with automatic streaming, an agent development kit with ReAct and multi-agent patterns, and interrupt/resume for human-in-the-loop. | View Project → |
| pr-agent | ★ 13K | AI Coding | Python | code-review · pull-request · ai-code-review · github-action · gitlab · bitbucket · azure-devops · cli · devtools · automation · self-hosted · pr-description · code-suggestions · llm-agnostic · webhooks · docker | PR-Agent is an open-source AI agent that reviews pull requests: /describe, /review, /improve and /ask commands run via GitHub Action, CLI, or webhooks on GitHub, GitLab, Bitbucket, and Azure DevOps, using any LiteLLM-reachable model. | View Project → |
| InsForge | ★ 13K | MCP | TypeScript | mcp · agentic-coding · backend-as-a-service · postgres · pgvector · auth · storage · edge-functions · ai-gateway · openai-compatible · cli · skills · realtime · websockets · docker · self-hosted | InsForge is a self-hostable backend platform (Postgres, auth, storage, edge functions, AI gateway) exposed to coding agents mainly through an MCP server, plus a CLI with Skills. Agents can read schema/logs and configure backend resources directly. | View Project → |
| LEANN | ★ 13K | RAG | Python | rag · vector-search · vector-database · hnsw · graph-index · embeddings · semantic-search · on-device · privacy · offline-first · local-first · storage-efficient · personal-ai · mcp · faiss · diskann | LEANN is a local, privacy-first vector database for RAG that uses graph-based selective recomputation to cut embedding storage by ~97% versus traditional vector DBs, with no accuracy loss. It indexes documents, emails, browser history, chat logs, and code, and ships an MCP server for agent use. | View Project → |
| voice-pro | ★ 13K | AI Tools | Python | tts · voice-cloning · speech-to-text · whisper · asr · translation · subtitles · dubbing · gradio · webui · vocal-isolation · karaoke · audiobook · podcasts · multilingual · voice-conversion | Gradio WebUI that chains YouTube download, Demucs vocal isolation, Whisper ASR, multilingual translation, and TTS/zero-shot voice cloning (F5-TTS, E2-TTS, CosyVoice, kokoro, Edge-TTS) into one dubbing studio. Windows + NVIDIA GPU focused, installs via uv. | View Project → |
| note-gen | ★ 13K | AI Tools | TypeScript | AI notes · local-first · Markdown · knowledge management · RAG · semantic search · MCP · agent mode · skills · multimodal | A local-first Markdown knowledge app with configurable AI chat, writing tools, semantic and hybrid search, and agent features. It can turn captured text, links, files, images, and recordings into notes while keeping files in your workspace. | View Project → |
| needle | ★ 13K | AI Frameworks | Python | on-device-ai · edge-ai · tinyml · tool-calling · function-calling · llm · embeddings · structured-extraction · quantization · 2-bit · lora · fine-tuning · foundation-model · microcontrollers · wearables · offline-inference | Needle is an 8-29 MB 2-bit foundation model and Python toolkit for on-device tool calling, structured JSON extraction and text embeddings. It ships inference, LoRA fine-tuning and per-platform builds for phones, wearables, robots, cars and microcontrollers. | View Project → |
| corsair | ★ 13K | AI Tools | TypeScript | AI agent integrations · API integrations · function calling · MCP · OAuth · unified API · multi-tenant | Open-source integration platform for connecting agents and applications to third-party services through a unified REST API, with OAuth and MCP support. Also supports backend services and customer-facing connection dashboards. | View Project → |
| ViMax | ★ 12K | AI Agents | Python | agentic video generation · multi-agent · video generation · storyboarding · scriptwriting · novel adaptation · image generation · AI filmmaking · character consistency · Web UI · TUI | An agentic video-creation system that coordinates story planning, scriptwriting, storyboarding, image and video generation, and final assembly. Supports idea-, screenplay-, and novel-to-video workflows, with interactive TUI and Web UI controls. | View Project → |
| mcp-chrome | ★ 12K | MCP | TypeScript | browser automation · Chrome extension · browser control · semantic search · web scraping · local-first · MCP server | A local Chrome extension and MCP server that lets AI clients control your existing browser, including its tabs, sessions, page content, network activity, and bookmarks. Includes semantic search across browser tabs and supports HTTP or stdio connections. | View Project → |
| ida-pro-mcp | ★ 12K | MCP | Python | mcp-server · reverse-engineering · ida-pro · binary-analysis · decompilation · idalib · headless · ida-plugin · malware-analysis · hex-rays · claude-plugin · codex-plugin · python · stdio-http-transports · ai-agent · security-tooling | IDA Pro MCP server that exposes IDA/idalib decompilation, disassembly and annotation tools to LLM clients, enabling agent-driven "vibe reversing". Supports GUI plugin, headless idalib workers, HTTP/SSE and stdio transports, with Claude/Codex/Kimi plugin packaging. | View Project → |
| OpenCreator | ★ 12K | AI Agents | TypeScript | ai-agents · codex · agent-workspace · skills · mcp · video-translation · dubbing · tts · subtitles · image-generation · video-generation · multimodal · local-first · desktop-app · creator-tools · localization | OpenCreator is a local-first AI workspace and agent app built on Codex CLI, combining reusable Skills, MCP and a runtime with visual creator tools for video translation, dubbing, subtitles, TTS, image/video generation and writing. | View Project → |
| reader | ★ 12K | RAG | TypeScript | url-to-markdown · web-scraping · llm-context · web-search · pdf-parsing · headless-chrome · readability · content-extraction · rag-ingestion · token-budget · markdown-chunking · screenshots · reader-api · jina-ai · curl-impersonate · office-docs | Open-source engine behind r.jina.ai and s.jina.ai: prepend a URL to get LLM-ready markdown from web pages, PDFs, Office files and images, or a search query to get the top results already fetched. Runs stateless or with S3/MinIO caching. | View Project → |
| LMCache | ★ 12K | AI Frameworks | Python | kv-cache · llm-inference · inference-optimization · vllm · prefix-caching · cache-offloading · ttft · throughput · long-context · observability · pd-disaggregation · tiered-storage · cuda · rocm · vendor-neutral · serving-engine | LMCache is a vendor-neutral KV cache management layer for LLM inference. It stores and reuses KV cache across CPU RAM, disk and remote backends, cutting TTFT and boosting throughput for long-context, multi-turn agentic and RAG workloads on engines like vLLM. | View Project → |
| cocoindex | ★ 12K | RAG | Rust | incremental indexing · RAG · agent context · data pipelines · semantic search · knowledge graphs · change data capture · codebase intelligence | CocoIndex is a Python-facing, Rust-backed framework for declaratively building incremental data and RAG pipelines. It recomputes only data affected by source changes and supports continuously refreshed search indexes and agent context. | View Project → |
| phoenix | ★ 12K | AI Tools | Python | observability · llm-evaluation · tracing · opentelemetry · llmops · evals · datasets · prompt-management · experiments · playground · ai-monitoring · mcp-server · self-hosted · openinference · debugging · agents | Arize Phoenix is an open-source, OpenTelemetry-based AI observability platform for tracing, evaluating, and debugging LLM and agent applications, with datasets, experiments, prompt management, and a built-in MCP server. Self-hostable via pip or Docker. | View Project → |
| UI-TARS | ★ 12K | AI Agents | Python | gui-agent · computer-use · vision-language-model · multimodal · ui-automation · grounding · reinforcement-learning · desktop-automation · mobile-automation · browser-automation · screen-understanding · action-parsing · bytedance · research | ByteDance's UI-TARS is an open-source native GUI agent built on a vision-language model that perceives screenshots and emits mouse/keyboard actions for desktop, mobile, and browser automation. The repo ships deployment guides, prompt templates, and action-parsing utilities (pip install ui-tars). | View Project → |
| fireworks-tech-graph | ★ 12K | Skills | Python | agent-skill · claude-code · codex · diagrams · svg · png-export · uml · flowchart · sequence-diagram · architecture-diagrams · cli · developer-tools · gif-animation · interactive-html · agent-workflows · python | Agent Skill for Claude Code and Codex that turns natural-language system descriptions into geometry-checked SVG/PNG technical diagrams. Ships 12 visual styles, 14 diagram types with full UML, built-in AI/Agent patterns (RAG, Mem0, multi-agent, tool-call), plus GIF motion and offline interactive HTML export. | View Project → |
| MemOS | ★ 12K | AI Agents | TypeScript | long-term-memory · agent-memory · memory-os · hybrid-retrieval · rag · mcp · self-evolving · skill-evolution · vector-database · knowledge-base · multi-agent · token-savings · context-management · local-first · sqlite · neo4j | Memory OS for LLMs and AI agents: unified add/retrieve/edit/delete of long-term and multi-modal memory as an inspectable graph, with hybrid retrieval (vector + FTS5), async ingestion, skill evolution, and plugins for OpenClaw, Hermes and DeepSeek Harness. | View Project → |
| loop-engineering | ★ 11K | AI Coding | TypeScript | loop-engineering · ai-coding-agents · agent-orchestration · claude-code · codex · grok · mcp · cli · github-actions · automation · prompt-engineering · state-persistence · verification · cost-tracking · pattern-library · devops | Pattern library plus TypeScript CLI tools (loop, loop-audit, loop-init, loop-cost) for designing and operating autonomous AI coding agent loops on a repo: triage, PR babysitting, dep updates, changelog. Includes MCP server, pattern registry, and staged L1-L3 safety rollout. | View Project → |
| no-ai-slop | ★ 11K | Skills | Python | skill · writing · ai-slop · editing · prompt-engineering · style-guide · claude-code · codex · chatgpt · content-quality · detection · satire | Agent skill that scans writing for 20+ AI slop patterns (binary contrasts, faux-insight openers, puffery) and rewrites them while keeping the author's voice. Installs via npx as a /no-ai-slop skill for ChatGPT, Claude Code, or Codex. | View Project → |
| camofox-browser | ★ 11K | AI Tools | JavaScript | browser-automation · stealth-browser · anti-detection · headless-browser · web-scraping · cloudflare-bypass · ai-agent · playwright · puppeteer · mcp · proxy · cookie-import · screenshots · youtube-transcripts · session-isolation · javascript | Anti-detection headless browser server for AI agents, built on the Camoufox Firefox fork with C++-level fingerprint spoofing. Exposes REST, MCP and OpenClaw tools with accessibility snapshots, element refs, cookie import and proxies as a stealth Playwright/Puppeteer replacement. | View Project → |
| inspector | ★ 11K | MCP | TypeScript | mcp · inspector · debugging · testing · cli · tui · web-ui · developer-tools · mcp-servers · oauth · ci · smoke-testing · typescript | Official MCP Inspector from the Model Context Protocol project: a TypeScript tool for testing and debugging MCP servers via a web UI, scriptable CLI, or terminal UI, all driven by one mcp-inspector binary. Useful for interactive debugging and CI smoke tests of MCP servers. | View Project → |
| codex-chatgpt-web | ★ 11K | AI Coding | TypeScript | codex · chatgpt-web · browser-automation · mcp · responses-api · model-bridge · playwright · streaming · subagents · cli · typescript · quota-saving | Local bridge that exposes user-authenticated ChatGPT Web models (including Pro) as native models inside Codex, with streaming, images and MCP tool harness. It enables coding with tools without consuming Codex quota; unofficial browser automation, not an OpenAI API. | View Project → |
| voltagent | ★ 11K | AI Agents | TypeScript | typescript · ai-agents · multi-agent · llm · mcp · rag · workflow-engine · memory · guardrails · evals · observability · voice · openai · nodejs · agent-framework · tools | VoltAgent is an open-source TypeScript framework for building AI agents with memory, tools, MCP, RAG, workflows, voice and guardrails, plus multi-agent supervisor routing. It pairs with the VoltOps console for observability, evals and deployment. | View Project → |
| mcp-use | ★ 11K | MCP | TypeScript | mcp · mcp-server · mcp-client · mcp-apps · mcp-inspector · typescript · react-views · chatgpt-apps · claude-connectors · zod · tool-calling · agentic-framework · tunneling · fullstack · framework | mcp-use is a TypeScript fullstack framework for building MCP servers and MCP Apps, with typed Zod tool schemas, React views bound to tools, a built-in Inspector, tunneling, headless CLI, and deployment. Useful for shipping ChatGPT apps, Claude connectors, and MCP servers for agents. | View Project → |
| cangjie-skill | ★ 10K | Skills | Python | agent-skills · knowledge-distillation · skill-generator · prompt-engineering · book-to-skill · content-distillation · agent-workflows · methodology-extraction · zettelkasten · pressure-testing · skill-pack · automation · claude-code · cli-toolchain | Python CLI toolchain that distills books, long videos, podcasts and other high-value content into callable, testable Agent Skills. Runs a 7-stage RIA-TV++ pipeline (extract, verify, build capability bundles, pressure-test, compile) and outputs installable skill packs or a single router skill. | View Project → |
| Amphion | ★ 10K | AI Tools | Python | text-to-speech · speech-synthesis · voice-conversion · singing-voice-conversion · singing-voice-synthesis · text-to-audio · music-generation · audio-generation · neural-audio-codec · vocoder · zero-shot-tts · multilingual-speech · reproducible-research · speech-dataset · evaluation-metrics · pytorch | OpenMMLab toolkit for audio, music and speech generation: TTS, singing voice synthesis/conversion, voice conversion and text-to-audio, with neural codecs, vocoders and evaluation metrics. Ships reproducible PyTorch recipes, pretrained checkpoints and the Emilia dataset. | View Project → |
| astrid | ★ 10K | AI Agents | Rust | agent-runtime · wasm · sandbox · capability-security · mcp · rust · microkernel · wasmtime · ipc · llm · audit-log · ed25519 · content-addressed-storage · cli · multi-agent · os | Astrid is a Rust user-space runtime (heading toward an OS) that runs LLM agents and tools as sandboxed WASM capsules with cryptographic, per-principal capability grants. The kernel is a dumb event router with no LLM or tool state; use it to compose secure agent systems, MCP tools, and services. | View Project → |
| YuE | ★ 10K | AI Tools | Python | music-generation · audio-generation · text-to-music · symbolic-music · abc-notation · music-editing · zero-shot-covers · style-transfer · agents · agent-skill · inference · llm · transformer · flow-matching · vae · pytorch | YuE2 is a music generation stack: lyrics plus a style prompt become an editable symbolic score (ABC), then a full 48kHz stereo song via an AR-NAR mixture-of-transformers and flow-matching VAE. Ships Python API, CLI, and a yue2-music agent skill for covers and agentic score editing. | View Project → |
| omnigent | ★ 10K | AI Agents | Python | multi-agent · agent-orchestration · agent-framework · meta-harness · claude-code · codex · cursor · agent-governance · policies · sandboxing · session-sharing · coding-agents · mcp · yaml · self-hosted · python | Omnigent is an open-source meta-harness and Python framework that orchestrates Claude Code, Codex, Cursor, and custom YAML agents under one session, with policy enforcement, sandboxing, and real-time multi-device collaboration. | View Project → |
| a-stock-data | ★ 10K | Skills | Python | a-share · china-stocks · financial-data · market-data · quantitative-finance · claude-code · ai-skill · llm-tools · kline · fund-flow · research-reports · news · options · futures · macro · convertible-bonds | A self-contained Claude Code / Codex skill (SKILL.md) that wraps 87 endpoints across 34 keyless data sources covering 15 layers of A-share and adjacent Chinese market data: quotes, K-lines, ticks, research reports, fund flow, news, financials, filings, limit-up pools, options, macro rates, futures, events, and converti | View Project → |
| PixelRAG | ★ 10K | RAG | Python | visual-rag · pixel-native-search · screenshot-retrieval · multimodal · embeddings · faiss · vector-search · qwen3-vl · vlm · document-rendering · pdf-search · web-screenshots · agent-memory · claude-code-plugin · qdrant · searchengine | PixelRAG renders web pages and PDFs to screenshot tiles and retrieves over the images with a LoRA-tuned Qwen3-VL embedding model, so tables, charts and layout survive retrieval. Includes a pixelshot CLI, FAISS/Qdrant indexing, a FastAPI search server, a hosted 8.28M-page Wikipedia index, and a Claude Code screenshot sk | View Project → |
| OpenRLHF | ★ 10K | AI Frameworks | Python | RLHF · reinforcement-learning · PPO · GRPO · REINFORCE++ · agentic-RL · distributed-training · Ray · vLLM · DeepSpeed · multi-turn-agents · VLM · async-RL · LoRA · reward-model · fine-tuning | OpenRLHF is a Ray + vLLM distributed RLHF framework with an agent-based execution pipeline, supporting PPO, GRPO, REINFORCE++, DAPO, async RL, and VLM/multi-turn agent training for LLMs up to 70B+ parameters. | View Project → |
| inkos | ★ 10K | AI Agents | TypeScript | ai-agent · creative-writing · novel-generation · ai-writing · interactive-fiction · storyboard · translation · multi-agent · cli · tui · studio-ui · skills · memory · llm-routing · openclaw · typescript | InkOS is a TypeScript story-creation AI agent system for novels, shorts, scripts, storyboards, interactive open worlds and translation. It ships a shared pi-agent harness, 15 built-in SKILL.md skills, SQLite FTS5 story memory, review/revision pipelines, and Studio/TUI/CLI surfaces with multi-provider model routing. | View Project → |
| awesome-gpt-image-2 | ★ 10K | Skills | TypeScript | image-generation · prompt-library · prompt-engineering · GPT Image 2 · OpenAI · multilingual · text-rendering · illustration · image-design | A multilingual collection of curated GPT Image 2 prompts with preview images, organized by use case, style, and subject. Useful for finding and adapting prompts for illustration, product visuals, typography, and other image-generation tasks. | View Project → |
| visual-explainer | ★ 9.9K | Skills | HTML | agent-skill · claude-code-plugin · mcp · html · diagrams · mermaid · slide-decks · diff-review · plan-review · visualization · pptx · codex · cursor · antigravity · opencode · project-recap | Agent skill that turns verbose terminal output into self-contained styled HTML pages: Mermaid diagrams, diff reviews, plan audits, data tables, slide decks, and recaps. Installs into Claude Code, Pi, Codex, Cursor, OpenCode, and Antigravity, with optional MCP and PPTX export utilities. | View Project → |
| OpenShell | ★ 9.8K | AI Agents | Rust | agent runtime · sandbox · security · isolation · access policies · credential protection · network controls · kernel enforcement · policy verification · gateway | A runtime for running autonomous AI agents in isolated sandboxes. It enforces filesystem, system-call, and network policies, protects credentials, and supports reviewing policy changes before they take effect. | View Project → |
| AutoAgent | ★ 9.8K | AI Agents | Python | multi-agent · zero-code · natural-language · agent-builder · deep-research · self-improving · workflow-orchestration · tool-generation · llm · cli · docker · agent-framework · research-assistant · code-generation · python | AutoAgent is a zero-code framework that builds and orchestrates LLM agents, tools, and workflows from natural language alone. Includes a Deep Research-style multi-agent mode, agent editor, workflow editor, and CLI, with model-agnostic provider support via LiteLLM. | View Project → |
| utopia | ★ 9.8K | RAG | Rust | rag · graphrag · knowledge-graph · bitemporal · agent-memory · mcp · ontology · pgvector · postgresql · rust · self-hosted · semantic-search · hybrid-search · entity-resolution · knowledge-base · temporal-knowledge-graph | Rust + Postgres knowledge platform combining a bitemporal knowledge graph, GraphRAG hybrid search, ontology-driven reasoning and an MCP server so agents can read governed enterprise knowledge. Self-hosted, air-gappable, with review queues and an append-only decision ledger. | View Project → |
| drawio-skill | ★ 9.8K | Skills | Python | agent-skill · drawio · diagrams-as-code · architecture-diagram · terraform · kubernetes · mermaid · uml · c4-model · image-to-diagram · sql · openapi · protobuf · graphql · ci-architecture-tests · mcp-server | Agent skill that turns prompts, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested .drawio architecture diagrams, with incremental sync, multi-view projection, CI architecture tests and HTML/PPTX/Mermaid exports. Ships a CLI plus optional MCP server for Claude Code, Cursor, | View Project → |
| DesktopCommanderMCP | ★ 9.7K | MCP | TypeScript | mcp · mcp-server · terminal-automation · file-editing · filesystem · claude · process-management · code-search · ripgrep · diff-editing · docker · vibe-coding · typescript · excel · pdf · docx | Desktop Commander is an MCP server that gives Claude and other MCP clients terminal execution, streaming process control, filesystem search, and diff-based file editing. It handles code, Excel/PDF/DOCX files, and long-running commands with blocklists and optional Docker isolation. | View Project → |
| mcp | ★ 9.7K | MCP | Python | mcp · mcp-servers · aws · model-context-protocol · stdio · cloud · infrastructure · devops · agent-tools · bedrock · cli · python · serverless · observability | Official AWS Labs suite of production-grade MCP servers that expose AWS documentation, APIs, IaC, databases, cost, and observability to MCP clients like Kiro, Cline, Cursor, and Claude Desktop. Ships shared Python toolkit, samples, migration guides, and a test harness for building your own AWS MCP servers. | View Project → |
| BabelDOC | ★ 9.6K | AI Tools | Python | pdf-translation · document-translation · bilingual-pdf · layout-analysis · ocr · glossary · scientific-papers · openai · onnx · cli · python-api · self-hosted · zotero · batch-processing · formula-preservation · pdf | LLM-powered document translation library that turns PDFs (especially scientific papers) into bilingual or translated PDFs. Uses OpenAI-compatible models plus ONNX layout analysis, OCR and glossaries; ships a CLI and Python API. | View Project → |
| claude-ads | ★ 9.5K | Skills | Python | claude-code · agent-skills · claude-code-skill · paid-media · advertising · ppc · google-ads · meta-ads · marketing-automation · audit · reporting · deterministic-scoring · multi-platform · read-only-safety · evals | Claude-first paid-media operations skill for Claude Code covering 12 ad platforms. It runs source-grounded, deterministic audits and plans, emits versioned JSON reports, and keeps account writes disabled behind capability and approval gates. | View Project → |
| video-shotcraft | ★ 9.5K | Skills | TypeScript | agent-skills · claude-code · codex · remotion · video-generation · motion-design · motion-graphics · product-video · promo-video · video-production · storyboarding · sound-design · beat-sync · skill-pack | An agent skill for Claude Code and Codex that storyboards, animates, and sound-designs cinematic product promo videos with Remotion. Ships 152+ shot recipe cards, motion previews, a full promo template, CapCut export, and a browser motion workbench. | View Project → |
| scroll-world | ★ 9.4K | Skills | JavaScript | agent-skill · claude-code · codex · scroll-animation · 3d-landing-page · ai-video-generation · image-to-video · scroll-scrubbing · vanilla-js · ffmpeg · marketing-site · brand-kit · portrait-mobile · prompt-templates · skill-md | An agent skill (SKILL.md) for Claude Code, Codex, and compatible agents that builds scroll-scrubbed 3D 'fly through the world' landing pages: it interviews you for brand and scenes, generates AI stills and image-to-video camera flights with frame-locked seams, then wires a portable vanilla-JS scroll engine. Costs money | View Project → |
| computer | ★ 9.3K | AI Agents | TypeScript | computer-use · agent-workspace · virtual-filesystem · sandbox · code-execution · durable-storage · Cloudflare Workers · FUSE | A TypeScript toolkit for giving agents a durable workspace and execution environment on Cloudflare. It combines a SQLite-backed virtual filesystem with container, shell, and JavaScript runtimes. | View Project → |
| modelcontextprotocol | ★ 9.3K | MCP | TypeScript | mcp · specification · protocol · json-schema · seps · documentation · typescript · standard · tool-calling · sampling · elicitation · oauth · streamable-http · conformance-tests · extensions · governance | Official specification, protocol schema, and documentation for the Model Context Protocol. Use it as the authoritative reference for building MCP clients and servers, tracking SEPs, schema changes, and conformance requirements. | View Project → |
| specification | ★ 9.3K | MCP | TypeScript | MCP · Spec · Protocol | Canonical MCP specification: protocol, transports, tools, prompts, and resources. | View Project → |
| XianyuAutoAgent | ★ 9.3K | AI Agents | Python | customer-service · multi-agent · chatbot · llm · prompt-engineering · e-commerce · xianyu · context-memory · negotiation · intent-routing · python · websockets · openai-compatible · automation · expert-routing | Python LLM agent that runs a 24/7 automated Xianyu (Idle Fish) customer-service bot: it classifies buyer intent, routes to price/tech/default expert prompts, keeps conversation context, and negotiates prices with tiered discounts via an OpenAI-compatible API (default Qwen). | View Project → |
| artemis | ★ 9.2K | AI Agents | Python | ai-agents · android · mobile-automation · test-automation · computer-use · mcp · ui-automation · multimodal · androidworld · adb · logcat · cli · python-sdk · web-console · benchmark | Google's ARTEMIS is an AI agent that executes natural-language instructions on real Android devices, driving apps end-to-end and capturing logs and screenshots. It ships an MCP server for IDE assistants, a CLI, Python SDK, and 99%+ AndroidWorld success. | View Project → |
| Graft | ★ 9.2K | AI Coding | TypeScript | claude-code · mcp-server · code-graph · context-engineering · knowledge-graph · tree-sitter · codebase-context · cursor · codex · gemini-cli · cli · developer-tools · token-savings · monorepo · blast-radius · code-visualization | Graft is a TypeScript CLI that builds a linked-markdown context graph of your codebase with tree-sitter, then feeds it to Claude Code, Cursor, Codex and other agents via hooks or an MCP server. It aims to cut agent token cost, latency and tool calls while improving multi-file correctness. | View Project → |
| improve | ★ 9.2K | Skills | — | agent-skill · codebase-audit · implementation-plans · code-review · security-audit · performance-audit · multi-agent · task-execution | An agent skill that audits a codebase, verifies findings, and writes self-contained implementation plans for other agents to execute. It can also dispatch execution to a cheaper agent, review the result, and reconcile plans as the codebase changes. | View Project → |
| mcp-go | ★ 9.1K | MCP | Go | mcp · go · model-context-protocol · sdk · server · client · llm-integration · tools · resources · prompts · stdio · sse · streamable-http · oauth · session-management · json-schema | mcp-go is a Go SDK implementing the Model Context Protocol, with server and client packages for exposing tools, resources and prompts to LLM applications over stdio, SSE or HTTP. It handles protocol details, sessions, OAuth metadata and task-augmented tools so you write minimal boilerplate. | View Project → |
| morphic | ★ 9.1K | AI Tools | TypeScript | AI search · generative UI · cited answers · web search · chat · self-hosted · file uploads · multi-provider | Morphic is a self-hostable AI search and chat application that combines web search providers with LLMs to produce cited answers. Its generative UI renders streamed responses as rich components, and it supports multiple model providers. | View Project → |
| autoclip | ★ 9K | AI Tools | Python | video-clipping · highlight-extraction · video-editing · subtitles · speech-recognition · llm · youtube · bilibili · fastapi · celery · tauri-desktop · mcp-server · asr · content-repurposing · whisper · docker | AutoClip is an LLM-driven video clipping system that downloads YouTube/Bilibili videos, transcribes them, scores highlight segments with Qwen, and outputs clips and compilations through a FastAPI+Celery backend, React UI and Tauri desktop app. It also exposes CLI and MCP entry points. | View Project → |
| apify-mcp-server | ★ 9K | MCP | TypeScript | mcp-server · apify · web-scraping · data-extraction · actors · oauth · streamable-http · stdio · agentic-payments · x402 · skyfire · automation · crawlers · typescript · model-context-protocol · tools | Official Apify MCP server that exposes thousands of Apify Store scrapers, crawlers, and automation Actors as callable tools for AI agents. Supports hosted OAuth (mcp.apify.com) and local stdio, plus agentic payments via AGI, x402, and Skyfire for paid Actor runs. | View Project → |
| claude-code-action | ★ 9K | AI Coding | TypeScript | GitHub Actions · coding agent · code review · issue triage · PR automation · code changes · Claude Code · CI automation | A GitHub Action that runs Claude Code on issues and pull requests to answer questions, review code, and implement changes. Supports workflow-driven automations and Anthropic API, Amazon Bedrock, Google Vertex AI, and Microsoft Foundry. | View Project → |
| adk-go | ★ 8.8K | AI Frameworks | Go | Go · AI agents · multi-agent systems · agent orchestration · tool integration · agent evaluation · MCP · A2A · cloud-native | Google's code-first Go framework for building, orchestrating, evaluating, and deploying AI agents. It supports multi-agent workflows and tool integrations, is optimized for Gemini, and can use other model providers. | View Project → |
| openwhispr | ★ 8.8K | AI Tools | JavaScript | speech-to-text · voice dictation · meeting transcription · local AI · AI assistant · speaker diarization · cross-platform · privacy-first · MCP | Cross-platform desktop voice dictation and transcription app with local Whisper and Parakeet models or cloud providers. Also includes meeting transcription, a voice AI assistant, searchable notes, and an MCP server. | View Project → |
| ai-memory | ★ 8.6K | AI Tools | Rust | agent-memory · long-term-memory · mcp-server · markdown-wiki · cross-agent-handoff · session-continuity · lifecycle-hooks · full-text-search · knowledge-graph · embeddings · rust · multi-user · audit-log · git-backed · self-hosted · zero-llm | Rust binary + MCP server giving AI coding agents (Claude Code, Codex, Cursor, Gemini CLI) shared long-term memory. Lifecycle hooks capture sessions into a git-backed markdown wiki; retrieval fuses FTS, entities, graph, and optional vectors, with typed cross-agent handoffs and zero-LLM default. | View Project → |
| harness-sdk | ★ 8.6K | AI Agents | Python | agents · agent-framework · multi-agent · mcp · sdk · llm · python · typescript · streaming · structured-output · guardrails · observability · evals · memory · model-agnostic · tools | Strands Agents is an Apache-2.0 SDK for building and running AI agents in Python and TypeScript. It provides an in-process agent loop with tools, MCP, multi-agent patterns, memory, streaming, guardrails, tracing and evals, and is model-agnostic across Bedrock, Anthropic, OpenAI and Gemini. | View Project → |
| mcp-agent | ★ 8.6K | AI Frameworks | Python | mcp · ai-agents · llm · python · agent-framework · workflows · durable-execution · temporal · orchestrator · multi-agent · mcp-servers · oauth · observability · fastmcp · human-in-the-loop · sdk | Python framework/SDK for building agents on the Model Context Protocol. Fully implements MCP lifecycle (tools, resources, prompts, OAuth, sampling) and composes Anthropic's effective agent patterns, with optional Temporal-backed durable execution and cloud deployment. | View Project → |
| LongCat-Video | ★ 8.4K | AI Tools | Python | text-to-video · image-to-video · video-generation · diffusion · avatar · audio-driven · lip-sync · long-video · dit · pytorch · streamlit · flash-attention · distillation · int8-quantization · world-models · inference | LongCat-Video is Meituan's 13.6B video generation foundation model, unifying text-to-video, image-to-video and video-continuation plus audio-driven avatar animation. Ships PyTorch inference demos (Streamlit, multi-GPU/context-parallel, FlashAttention-2/3, INT8) and open weights. | View Project → |
| kimi-k3-in-c | ★ 8.3K | AI Frameworks | C | llm-inference · cpu-inference · c99 · zero-dependencies · quantization · mxfp4 · mixture-of-experts · moe · avx2 · simd · memory-efficient · linear-attention · kv-cache · streaming-weights · from-scratch · safetensors | A portable C99 inference engine that runs the 2.78T-parameter Kimi K3 MoE model on one CPU with 8.24 GB peak RAM, streaming a 1.56 TB checkpoint from disk with no BLAS, framework, GPU or runtime dependencies. | View Project → |
| bifrost | ★ 8.2K | AI Tools | Go | ai-gateway · llm-gateway · model-router · load-balancing · guardrails · semantic-cache · mcp · observability · llmops · failover · multi-provider · openai-compatible · go · governance · budget-management · streaming | Bifrost is a high-performance Go AI gateway exposing one OpenAI-compatible API over 23+ providers, with automatic failover, key load balancing, semantic caching, MCP tool support, guardrails and budget governance at low overhead. | View Project → |
| superpowers-zh | ★ 8.2K | Skills | JavaScript | agent-skills · ai-coding · chinese · localization · claude-code · cursor · gemini-cli · codex · tdd · code-review · debugging · prompt-engineering · npm-package · cli · multi-tool · workflow | Chinese community edition of obra/superpowers: 20 agent skills (14 translated + China-specific ones) installable via `npx superpowers-zh` into 26 AI coding tools such as Claude Code, Cursor, Codex, Gemini CLI, Windsurf and Kiro. Covers brainstorming, planning, TDD, debugging, code review, MCP building and workflow orch | View Project → |
Vibe Coding Discover