Havuz

A visual map for long AI conversations (ChatGPT / Claude / Gemini)

Git-versioned agent memory: agents that never make the same mistake twice. Anthropic-Skill folder standard, multi-runtime (Claude Code, Curs

A self-hosted knowledge broker for homelabs. Routes and fuses queries across Kiwix, FreshRSS, Open-Meteo, SearXNG, Uptime Kuma, and Home Ass

"Review Ducktective" is an automated code review platform based on an LLM: it takes a diff as input and outputs structured findings with sev

Open source LLM gateway with PII and secret detection built in. Runs on your infrastructure.

Auditable context capsules for LLM handoffs, coding agents, and OpenCode MCP workflows.

Keep your AI coding sessions named after what they actually became — Claude Code, Codex, Cursor and more. Auto-renames idle sessions, search

MCP server that lets Claude (or any Model Context Protocol client) drive the CODESYS V3.5 SP22 PLC IDE via its Python ScriptEngine - project

原神千星奇域 MCP 服务器：让 Claude、Cursor 等 AI 替你搭关卡、写节点图、自动试玩 | Unofficial MCP server for Genshin Impact's Miliastra Wonderland (UGC) editor: AI build

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”）

Adversarial LLM Reversal for hermes-agent

The first free, open-source, self-hosted MCP server for Google Merchant Center (GMC). 126 tools over Merchant API v1 — products, inventory,

Funes is a Git-based framework for LLM-managed knowledge work: an AI Librarian ingests raw sources, builds an interlinked Markdown knowledge

Scribo — free, AI-native EN 16931-compliant e-invoicing. ZUGFeRD/XRechnung (Germany) and US plain PDF live; Factur-X, Facturae, Peppol BIS U

Embedded code reviews directly directly within pi.

A local LLM router with OpenAI and Anthropic format translation, retry and fallback chains

Private, offline AI coding agent for local Qwen models via Ollama — zero dependencies, real tools, multi-agent. Your code never leaves your

Drive Blender from AI agents with a plain Python SDK (no MCP), grounded in REA/Ghidra reverse engineering of Blender 5.2.2

Mail for AI agents ( and humans). MCP server giving Claude (or any agent) safe, permission-controlled access to email (Microsoft Graph + IMA

Send messages from AI agents, CLI, and MCP tools - powered by one shared TypeScript core.

Mnemovela - Agent Cognition Runtime (typed memory, Git-like branches, hybrid retrieval, governed forgetting; embedded-first Python & Go). Op

MCP server that drives FMOD Studio live via its scripting terminal (TCP 3663) — one tool per Scripting API member, generated from the API re

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

Hosted Google Search / SERP MCP server from HasData, no Google Cloud project. Organic results, AI Overview, People Also Ask, AI Mode, news a

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

Kimi Code-style agent orchestration harness for the Pi coding agent — Swarm, Goal, Plan, Permission, Task, Hooks, Skills, TUI

Zaxy turns agent work into durable, auditable memory: a hash-chained Eventloom log as the source of truth, an embedded temporal knowledge gr

Passive LLM Conversation Capture & Sensitive Data Exposure Research

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

MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in dynamic and adaptive

Compact coding-agent context without summarizing it away. Verbatim, offline, with a receipt and recall for every cut. CLI, MCP server, Claud

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

SentinelX agent: outbound-only agent that exposes your Linux, macOS, and Windows servers as MCP tools to Claude.ai and ChatGPT

A high-performance, private, on-device AI chat client built with Flutter. AstraLM runs Large Language Models (LLMs) and Vision models 100% l

A self-correcting system of nested engineering loops: plan & execute repo work; safely implement audit findings; design greenfield & improve

Agent tools from many descriptions in a single integration. Authorize operations, not just tool calls, and approve them when a human is requ

High-performance full-text search across PDFs, Office documents, ZIP archives, email, media metadata and GGUF/LLM model files. ripgrep-compa

Hosted Instagram MCP server from HasData. Public profile and post-feed tools by handle, structured JSON, for Claude, Cursor and any MCP clie

Turn your repos into a team of Claude Code agents with persistent memory, coordinated tasks, and a live dashboard.

PWA chat with Gemini Nano running locally in Chrome using Prompt API, no server, no API key, works fully offline.

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

Real-time cross-machine MCP relay for Claude Code agents

Minimal harness-agnostic recursive language model layer — one binary, Python + llm()

dsh-model-master（模型选择大师）— model selector for DeepSeek Harness: search across providers, probe any model with a real streaming request to mea

Token-efficient facade and Codex skill for MCP for Unity: 96% smaller measured tool-schema surface, compact results, batching, and recovery.

Project-local agent harness skill for traceable AI workflows

MCP server: gives your AI agent the real sources, public API and KDoc of any Maven/Gradle-published Kotlin or Java library

Structural code intelligence for DeepSeek Harness (dsh) — gives the agent codegraph and codegraph_index tools to find where a symbol is decl

Progressive tool discovery for DeepSeek Harness — tiny stable surface, searchable catalog, real pipeline execution, context cache intact.