Open source. Open possibilities.

Obsidian plugin that embeds the DeepSeek Harness native Web UI, giving each vault its own isolated DSH instance for AI-assisted note work, with selection/file linking, model config sync, and optional portable runtime.

Hello-Agents is a systematic intelligent agent learning tutorial launched by the Datawhale community, covering core agent principles, classic paradigm construction, framework development, memory and retrieval, context engineering, communication protocols, Agentic-RL training and comprehensive project practice, suitable for AI developers and self-learners to build AI-native agents from scratch.

Curated archive of leaked system prompts from ChatGPT, Claude, Gemini, Grok, Copilot, Cursor, Perplexity and others, captured verbatim and organized by vendor with recent additions and change log.

AgentGuide is an open-source knowledge base for AI Agent development, research, and job hunting, offering systematic learning paths, hands-on projects, and interview question banks to guide learners from beginner to job offer.

Jano is a lightweight OpenAI-compatible router that enables multiple local LLMs to share one GPU by intelligently batching requests and minimizing model swaps.

ccu-mcp is an MCP server that connects to HomeMatic CCU smart home systems via JSON-RPC, exposing devices, rooms, programs, and system variables as tools for AI assistants like Claude and Cursor. It supports stdio and HTTP transports, Docker deployment, multiple CCU profiles, and security features like TLS pinning and token rotation.

Otaku is a free, local LLM frontend for roleplay, offering web and terminal interfaces. It supports local and cloud LLMs, manages long context via scene summaries, and imports SillyTavern chats and character cards.

PromiseLink is an AI-driven personal business relationship management assistant focused on ensuring data sovereignty through local storage and implementing closed-loop management from event entry to promise tracking.

Agentic OS is a self-hosted control plane for running business operations as a fleet of AI agents. It features a cost-aware LLM router, cross-module workflows, and human-in-the-loop approvals for finance, support, and compliance.

RAPID is a lean, spec-driven methodology for AI-assisted development, structuring workflows from requirements to delivery with human approval gates.

An animation-first React framework designed for high-fidelity visual websites, featuring persistent shells and live-tweakable motion tokens.

AI Gateway routes LLM requests intelligently by intent, cost, and provider health. Supports multi-tenant access, caching, failover, and observability — reducing costs and improving reliability for production AI apps.

Lexos is an event-driven AI document processing engine combining a Go gateway, Python workers, Redis queues and self-hosted models for offline RAG, summarization and speech transcription.

Build production-ready conversational AI apps in Python quickly. Supports tools like OpenAI, LangChain, and more. Community-maintained since May 2025.

An AI-powered Git toolkit and MCP server written in Rust, featuring intelligent commit message rewriting, PR generation, and integrations for Atlassian, Datadog, and Google services.

Read-only-by-default Model Context Protocol (MCP) server for Microsoft SQL Server, providing metadata discovery, parameterized SELECT-only queries, execution plan analysis for slow query diagnosis, profile-based multi-connection configuration, and optional per-profile write access, shipped as a .NET NuGet tool.

A community plugin that lets you control Blender 3D with any LLM via MCP, enabling prompt-based modeling, scene creation, asset import, and Python code execution in Blender.

An automated pipeline that scrapes GitHub Trending, enriches entries via the GitHub API, generates LLM-written summaries and trend analysis, then publishes Markdown reports plus JSON data through a Docusaurus site deployed by GitHub Actions.

TradingAgents is an open-source multi-agent LLM framework for financial trading research. It deploys specialized agents—analysts, researchers, traders, and risk managers—that collaboratively evaluate market conditions and generate trading decisions across global stock and crypto markets.

TrendRadar is a lightweight, AI-powered news and sentiment monitoring tool that aggregates hot topics from multiple platforms and RSS feeds, supports keyword filtering, AI-driven curation/translation/analysis, and delivers alerts via WeChat, Feishu, DingTalk, Telegram, etc., with MCP API support.