Havuz

Production-grade MCP server for MikroTik RouterOS routers and SwOS switches, with secure AI-native network automation.

Observability for AI agents. See what your agent did, why it cost that much, and what to fix.

Production-grade design context for AI coding workflows. Extract a real design system from any URL — colors, typography, spacing, breakpoint

Recursive Self-Improvement for AI agents and models, helping your agents self-improve with every run

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

Experiential world memory to help AI when web search is not enough.

Any website, within reach of any agent. Captures a site's native WebMCP tools and generates the bridge from the live DOM when there are none

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

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

A semantic, transactional, replayable MCP control plane that lets autonomous AI agents operate Dwarf Fortress as a long-lived civilization.

AI agent orchestration kit for Windows, Linux/MacOS with Codex skills, hooks, routing rules and profiles for Claude, OpenCode, Cursor, Gemin

An automated, multi-turn LLM red-teaming pipeline that pits an Attacker model against a Target model to evaluate safety boundaries, featurin

DSH 插件：基于知乎开放平台官方 API 创建的站内搜索、全网索引搜索与直答三个工具。搜索不幻觉，引用有出处。（原生嵌入“设置-插件-插件配置”）

Control Virt-A-Mate from any MCP client: an in-process MCP server shipped as a BepInEx plugin (63 tools)

Make destructive AI-agent actions reversible by default — quarantine + audit + human escalation for rm/git destructive operations. Reliabili

A high-precision calculation & binary data MCP server with chained batch execution (batch_calc), bitwise logic, IEEE 754, crypto, and math.

Convert Hermes / OpenClaw agent memory (JSONL sessions, MEMORY.md) to markdown for gBrain ingest

One dashboard for all your AI agents — manage teams across Claude Code, Codex, Gemini, Aider, and more. No database required.

在系統匣同時盯著 Claude、Codex、Antigravity 三家 AI 用量的 Windows 免安裝小工具

A graph-native simulation engine for building composable engineering simulations and digital twins.

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

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

44 plug-and-play skills for OpenClaw — self-modifying AI agent with cron scheduling, security guardrails, persistent memory, knowledge graph

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。

The living armor an AI agent inhabits: eternal devouring, eternal evolution, eternal amplification.

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

Own your LLM's web search: a local search->fetch->rank pipeline that replaces hosted web-search tools. Measured: matches hosted accuracy at

BuildArena: Physics-grounded Besiege Building for LLMs

Checks every AI agent action against your company's real rules before it runs. Git-native, PR-reviewed.

Explore ideas, engineer real things, and find out what holds up. An AI engineering partner for grounded, evidence-driven design.

Build a secure, production-ready MCP server for any project — connect Claude, ChatGPT & any AI agent to your backend with a URL + API key. S

Open WebUI filter that defers MCP and builtin tool schemas until the model asks for them by name, cutting per-call prompt tokens

Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing

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 - No personal logs by design. Model autodiscovery, Failover groups, High availability, Android companion app, and

Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase

Stop re-explaining your research to your AI agent. Persistent, LLM-maintained wikis that compound over time. Drop PDFs, URLs, YouTube - your

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。

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

The linter for your agent harness. Works with Claude Code, Codex, and Cursor.

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

Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction

Let any MCP AI agent drive your real Chrome. Copy one prompt to pair — no confirmation page, no pairing code. 100% local.

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

MCPSafari: Native Safari MCP Server for AI Agents

A static performance model for LLM inference: given (model, GPU, interconnect, workload), instantly answer VRAM feasibility, latency(TTFT, T

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

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

Fast, idiomatic Go MCP server for web search, image search, and page scraping to Markdown. Runs locally, no API keys, free.

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