Havuz

Don Cheli — SDD Framework. The most comprehensive Specification-Driven Development framework for AI agents. 88+ commands, 51 skills, 15 reas

Repo-local continuity runtime for AI coding agents. Helps them continue from the same inspectable work state instead of starting cold. Stop

Multi-Provider AI Gateway, "Because we have LiteLLM at home" No personal logs by design. Model autodiscovery, Failover groups, High availabi

Web search CLI for AI agents — 13 providers rank-fused into one Rust binary. Search, extract, verify, check credits.

不死鸟 Phoenix — Hermes Agent 插件：路由分档/风险防线/自愈/存档点提醒/审批策略自适应，官方钩子接入，不改 Hermes 核心代码

Connect Claude and ChatGPT to KDAN PDF — upload, edit, compress, protect, redact, and compare PDFs in chat.

观澜 / Guanlan：AI Agent 的中文互联网研究、阅读与信源路由工具。

Markdown-first Notion MCP server. ~6-7x fewer response tokens vs official Notion MCP. 43 tools.

Multi-agent Claude Code skill for building apps and stuff

Local-first MCP server that gives coding agents structured context packets, code/schema facts, and diagnostics - backed by a local SQLite st

The DeepSeek and OpenRouter Harness built on Elixir

Zettelkasten knowledge base template for Claude Code projects. Bootstrap + interactive interview.

⚡ Cut Claude token usage by 90%+ — free, open-source, local-first context compression for Claude Code. Hybrid RAG (BM25 + ONNX vectors), AST

Open-source alternative to Claude Artifacts for every coding agent. Any agent ships a self-contained page or app to a live URL — Claude Code

AI agent skills manager for Claude Code, Cursor, Codex and more — install, sync, and manage skills from one desktop app.

AI-Powered Offensive Security Research Engine - desktop-native security testing platform with native MCP integration. 90 tools, MITM proxy,

Vetix — Automated scanning, identification, and assessment of SKILL security risks, based on Golang.

llmBench is a high-depth benchmarking tool designed to measure the raw performance of local LLM runtimes (Ollama, llama.cpp) while providing

Give the agent "this" and he gets a real PC.

Enchant Version of 9Router. 304+ Providers (API-key, OAuth, free-tier, and 39 web-cookie providers), 6 combo strategies (fallback, round-rob

Interactive data-flow diagrams your AI agent can write. One SKILL.md — install in Claude Code, Cursor, Codex, and 11+ other clients via `npx

Tools for AI agents to test, fix and optimise your codebase

Open-source AI model evaluation and benchmarking framework for LLMs (OpenAI, Ollama, Claude, Gemini)

面向 WebMCP 标准的非侵入式前端集成套件：写一个普通 TS 函数加一段 JSDoc，即可被任意 MCP 客户端调用 —— 含 SDK、Vite/Webpack 插件与 AI 编码 Skill。

cn金融数据 MCP 服务器 — 工具包覆盖 A 股行情、财报、估值、板块、市场全景、新闻及宏观指标。

Wavelet-based multi-resolution context management for LLMs via MCP

On-device shell command generator for macOS Tahoe. Uses Apple's 3B model with dynamic few-shot retrieval from 21k tldr examples.

A CLI that extracts the useful structure from source files: signatures, imports, types, variables, comments, and Markdown sections.

Audit and shrink your Claude Code startup context. Measures what every skill, plugin, agent, and memory file costs in the system prompt, the

Fast, deterministic verifier and gate for AI agents: exact math, claim and citation checks, shell/write policy, hash-chained step ledger and

Context profiler for LLMs and AI agents - used to introspect context contents and reduce token costs

Open-source desktop AI agent that sees what you see — one hotkey over any window, it answers, acts, or guides you step-by-step.

通达信(TDX)A股金融数据 MCP 插件-v3— 6 个核心工具(实时行情/K线/F10基本面/智能选股/指标/代码检索)+ 45 个投资分析技能,适配 OpenClaw,经真实接口实测。

Curated Claude and Codex skill collection for local AI workflows, automation, research, and product-building.

Confine an AI coding agent to one directory with a BPF-LSM program, and watch every escape it tries.

Isometric games made easy — an agentic game kit. 12 agent skills over 9 zero-dependency TypeScript packages. Type one sentence, get a playab

MCP server connecting AI agents to ITASCA FLAC — run continuum simulations through natural conversation

Drive a real browser from the command line and from MCP. Stable element refs, zero dependencies.

local-first MCP discovery runtime for agents — search before invoke, reduce prompt bloat, and route to local MCP tools

"Does this actually work with my agent?" An open, versioned registry of AI-agent artifacts: skills, plugins, MCP servers, models, etc. with

Save conversations, search by idea, read the surrounding context. Memory for AI agents.

Django manage.py context for coding agents — and tab completion for you

Local MCP server that exposes classic Outlook desktop (mail, calendar, contacts, tasks, rules) to Claude and other MCP clients via COM. No A

Self-hosted intent radar — Reverse RAG for any input stream.

Fast dual-era framework-agnostic Model Context Protocol (MCP) runtime for Java and Kotlin. Streamable HTTP, native Netty transports, tools,

The best news MCP server — 150+ verified articles/day with confidence scores, Ed25519 provenance, and Ethics Engine ratings. Free, no auth.

An Automated project operating system, called PhanOS. It Combines Phanes as the Orchestrator, Cyphor(to be released) as the Documentation, C

BuildArena: Physics-grounded Besiege Building for LLMs

MCP server with 55 security intelligence tools — CVE/KEV, MITRE ATLAS+D3FEND, Sigma detection rules, email security posture (SPF/DMARC), dom

Use Cursor CLI from Claude Code to delegate coding tasks to Composer 2.5+ and other Cursor models.