v0.13.1 · MIT
Task-specific React apps for DeepSeek Harness with state carried into the next Agent turn
v1.2.1 · MIT
Pluggable DeepSeek-colored TUI for DeepSeek Harness
v0.4.8 · MIT
A toolkit of skills, templates, and guides for bootstrapping AI-agent-friendly projects. Started from Anthropic's Claude Code engineering patterns, extended with a per-project self-improvement loop and more.
v3.0.2 · MIT
Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent Skills for Claude Code, Codex, Cursor, Copilot, Windsurf, OpenCode, Gemini CLI, and Antigravity.
— · MIT
Turn Claude Code into a 24/7 Agent
v0.1.0 · MIT
The living DeepSeek Harness plugin directory — refreshed hourly, compat-tested daily, with an in-app plugin store and scaffolder. DSH 插件活目录:每小时刷新,每日兼容实测,内置插件商店与脚手架。
v5.2.4 · MIT
Your AI can write the UI. This makes sure it writes your UI. A deterministic scanner scores your design system 0-100 against 34 public repos, writes rules for Claude, Cursor, Copilot and Windsurf with --apply, and runs as a local MCP server with --mcp.
v2.13.0 · MIT
Notion MCP server for Claude, Cursor, ChatGPT, and Claude Desktop — connect AI agents to Notion via the Model Context Protocol. Create pages, query databases, append blocks, upload files, and more in natural language.
v3.0.0 · MIT
A pixel-art whale desktop companion for DeepSeek Harness — it swims while your agents work and taps the glass when an approval is waiting.
v0.2.19 · MIT
BitFun combines a high-performance agent runtime written in Rust with a polished desktop application. It pairs the depth of a Code Agent with open, general-purpose capabilities for work beyond software development.
v13.1.0 · MIT
Neo.mjs is a self-evolving software organism: a professional end-to-end AI engineering team whose cross-model swarm inhabits live apps via Neural Link, Active Hybrid GraphRAG, DreamService, and self-healing loops.
— · MIT
Let your AI coding agent self-host any open-source app for you. 2,200+ verified recipes — provisioning, DNS, TLS, hardening. Works with Claude Code, Codex, Cursor, Aider, OpenClaw, Hermes.
v2.32.1 · MIT
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM with Codex CLI/App/SDK and Claude Code
v3.1.0 · MIT
Reverse engineer anything with agents, from app behavior down to native binaries.
v0.15.1 · MIT
The agent runtime for React Native and Expo: an MCP server that sees the app the way React sees it, knows which file produced each element, acts without coordinates, and proves it works. Local only, zero dependencies.
v0.1.2 · Apache-2.0
Give your AI agent the ability to respond with live, interactive apps that evolve.
v0.5.1 · MIT
Keyboard-oriented iKanban web application bundle for DeepSeek Harness
v0.15.1 · MIT
The Obsidian MCP server that needs no plugin, no running Obsidian app — and doesn't blow your context window. Filesystem-direct: single-digit-ms keyword search, ~14 ms local semantic search, ~2 KB payloads, 19 tools.
v0.14.3 · MIT
Dive is an open-source MCP Host Desktop Application that seamlessly integrates with any LLMs supporting function calling capabilities. ✨
v0.42.0 · no license
An MCP that lets AI tools securely connect to your infrastructure, write IaaS code, debug issues, and assist during incidents - without risking production stability. Built for security teams to approve and infrastructure teams to experience like magic.
v0.1.0 · MIT
CreationLoop is your Marketing Agent. Read the overview, offer, and FAQ; apply as a design partner.
v1.0.4 · MIT
Agent-first marketplace for real-world assets — agro and energy first; humans approve every write.
v1.2.0 · MIT License
Divination for AI agents: Hafez, Tarot, I Ching, Runes, and Geomancy. Plus the Pentamancy Council, all five oracles consulted in parallel and synthesized into one unified counsel. For when you need a new perspective on a current problem: a unique and pointed randomness for the stuck ones, genuine guidance for the heavy ones, or plain curiosity about what happens when an AI gets a reading from fiv
v1.2.0 · MIT
SRE thinking applied to Claude Code, based on Boris Cherny's Q&A. It enforces a strict 4-stage pipeline with gates between each step. You literally cannot skip verification. You cannot ship without approval.