Discover top AI open source — Agents, MCP, Skills, RAG, Tools and Frameworks. Vibe Coding Discover helps you find the right project so you can code faster.Today (09/30/2026 UTC): +47 projects, +255 use casesToday's Recommendations1Fully local, open-source ElevenLabs alternative for voice cloning, voice design, dubbing, dictation, transcription and audiobooks in 646 languages. Ships a desktop app (Electron/Tauri), model manager, local API and an MCP server for agent integration.AI Frameworks | Python · voice-cloning · text-to-speechView Project →2Hindsight is a self-hostable memory system for AI agents, with APIs and SDKs to retain, recall, and reflect on information over time. It integrates with agent frameworks and coding assistants and supports a range of hosted and local LLM providers.AI Agents | Python · agent memory · long-term memoryView Project →3Java-based PDF parser with Python and Node.js SDKs. Extracts Markdown, JSON with bounding boxes, and HTML; hybrid mode supports OCR and complex layouts, and it can auto-tag PDFs for accessibility.RAG | Java · PDF parsing · document extractionView Project →A TypeScript project-memory tool for Claude Code, Cursor, and Codex. It records decisions, constraints, bugs, and failed approaches, retrieves relevant notes for later prompts, and can check tool calls against saved rules.AI Coding | TypeScript · coding-agent-memory · Claude CodeView Project →A weekly updated, categorized ranking of 400 MCP servers. Browse projects by use case and compare quality scores based on metrics collected from GitHub and package managers.MCP | MCP servers · curated listView Project →An open-source visual environment for building, testing, and deploying AI agents. Provides drag-and-drop workflows, custom-code extensions, and a runtime for deploying agents as chatbots, APIs, and integrations.AI Agents | TypeScript · visual builder · drag-and-dropView Project →An MCP server that lets AI assistants manage WordPress sites through 71 tools for content, media, users, SEO, and site operations. Supports multiple sites and integrates with clients such as Claude Desktop.MCP | JavaScript · WordPress · CMSView Project →An MCP server for AI-assisted SAP CAP development. It exposes tools to search CAP documentation using local embeddings and find definitions in compiled CDS models, for clients such as Claude Code, VS Code, and Codex.MCP | JavaScript · MCP server · agentic codingView Project →A read-only MCP server that exposes WHOOP recovery, sleep, HRV, strain, and workout data to Claude, Codex, and GitHub Copilot. Includes tools, resources, and prompt templates for querying personal health trends.MCP | TypeScript · WHOOP · health dataView Project →awesome-deepseek-harness★ 1.1KA 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.AI Agents | Python · DeepSeek Harness · agent pluginsView Project →An open-source Chromium-based browser that lets AI agents automate tasks in your logged-in accounts through MCP. Runs locally, supports parallel agent sessions, and provides live monitoring and replay.AI Agents | TypeScript · browser agent · computer useView Project →Explore CategoriesOpenClaw is a self-hosted, open-source AI assistant gateway that runs on your own devices and meets you in 20+ chat channels (Discord, Slack, WhatsApp, iMessage) plus native desktop and mobile apps. Models and agent harnesses are swappable plugins, with extensible tools, skills and a plugin SDK.AI Agents | TypeScript · ai-assistant · multi-channelView Project →A cross-agent skills library and development methodology for coding agents, packaged as installable plugins. Skills auto-trigger brainstorming, plan writing, TDD, subagent-driven execution and code review across Claude Code, Codex, Cursor, Gemini CLI and others.Skills | Shell · agent-skills · skills-libraryView Project →A set of small, composable agent skills for real software engineering with Claude Code, Codex, and other agents: grilling/alignment, spec-to-tickets, TDD, debugging, code review, triage, and architecture improvement. Installed via Claude Code plugin or npx skills, editable in-repo.Skills | Shell · agent-skills · claude-codeView Project →A cross-platform collection of agent skills, specialized agents, hooks, rules, and memory workflows for coding assistants. It adds structured development, review, security, and learning practices to Claude Code, Codex, Cursor, OpenCode, and other harnesses.Skills | JavaScript · agent skills · coding agentsView Project →Hermes Agent is Nous Research's self-improving personal AI agent with tool calling, a built-in learning loop that writes and refines its own skills, persistent cross-session memory, and a messaging gateway for Telegram, Discord, Slack and more. Runs on CLI, VPS or serverless backends and is model-agnostic via Nous PortAI Agents | Python · ai-agent · self-improvingView Project →DeepSeek Harness (dsh) is DeepSeek AI's open-source agent harness built on an everything-is-a-plugin architecture via Cordis. It ships a local Web UI and desktop app, plus extensive docs on agent lifecycle, capability seams and plugin extension points. MIT, TypeScript, developer preview with breaking changes.AI Agents | TypeScript · agent-harness · plugin-architectureView Project →Open-source AI coding agent available in the terminal and as a desktop app. Includes build and read-only planning agents, plus a general subagent for complex searches and tasks.AI Coding | TypeScript · coding agent · terminalView Project →n8n is a fair-code, self-hostable workflow automation platform with native AI: a visual canvas plus code for building multi-step AI agents, tool use, human approvals, and RAG, connected to 1500+ integrations and MCP servers/clients.AI Agents | TypeScript · workflow-automation · no-codeView Project →VIBECDVIBECD is a commemorative memecoin celebrating vibe coding on the Base network.Fixed Supply: 10,000,000,000Community supply: 80% reserved for daily claim, 20% for rewards claimDaily claim cap: 10,000 VIBECD once per wallet once per IP per day.Rewards claim cap: Up to 200,000 VIBECD once per wallet once per IP per day.Global daily cap: 100,000,000 VIBECD.This is not financial advice.Claiming does not imply investment value or future returns.Claiming VIBECD is free. You pay the network gas fee for the on-chain transaction.Have an AI Open Source Project?Submit a GitHub repository or an X recommendation. No login required.Submit Project