- Conduid
- Categories
- Agents
Agents MCP servers
Agents MCP servers indexed by Conduid, ranked by trust score. 10K live listings from GitHub, npm, PyPI and the official registry, each with a 0–100 score, security checks, and install commands.
Doro
基于 Claude Code 定制的个人终端 AI 编程助手，支持多模型接入、MCP 与语音输入。
Delentia OS
A governed AI agent runtime: risky actions wait for a signed human approval, and every episode goes into a signed, hash-chained audit log. Apache-2.0.
Claude Code
Explore Claude Code CLI source code for TypeScript, Bun, and Ink, with tools, commands, and services for AI coding automation
Claude Code
Use Claude Code CLI source to inspect, edit, and automate terminal-based software engineering workflows with AI assistance
Memilier
Hemilier 桌面智能体：对话 + 工具调用 + 文件/命令操作 + 联网搜索，由本地 Ollama 或云端 DeepSeek/OpenAI 兼容模型驱动。Electron + React + TypeScript。
AgentForge
AI software engineering platform that turns natural-language requests into working, tested, documented codebases. An 8-agent LangGraph pipeline (analysis, planning, architecture,…
AgentRank
The trust and reputation layer for AI agents. Protocols like MCP and A2A tell you how agents connect. AgentRank tells you whether you should connect.
Nex Code
The open-source agentic coding CLI. Focused on Ollama Cloud Models.
Agentanycast Ts
TypeScript SDK for AgentAnycast — connect AI agents across any network
Backthread
Backthread keeps the thread on what your AI coding agent ships — it captures the why behind every change and turns it into a living 'How it works' view of your codebase you can ac…
TakoAPI
One API to access all agents — an open directory + unified gateway for AI agents, plus thousands of OpenClaw skills for your coding agent.
AiNIR
Semantic trust layer that checks AI-agent actions and MCP tool calls before execution.
Multi LLM Review
Parallel adversarial code review by multiple LLMs for Claude Code — Claude + Gemini by default, optional Codex/GPT for a 3-model panel.
Pi
My custom Pi coding-agent harness: full-screen terminal workbench with agent workflows, subagents, an MCP hub, Codex usage windows, Arabic/RTL support, and one-command setup.
TAGA 1
Hands-on reference implementation of an agentic AI stack that includes ReAct loop, MCP, hooks, streaming, token budgeting. A forkable learning baseline, not a production service.
Openclaw Enterprise Platform
Enterprise platform architecture repository unifying cloud landing zones, GitOps, zero trust, SRE, platform engineering, and MCP agent infrastructure.
AI Agent Platform
A cloud-native AI agent orchestration platform using FastAPI, MCP, LangGraph, PostgreSQL, Docker, and GCP Cloud Run with tool-calling agents, conversational memory, and production…
Haldir Starter
Runnable starter template — governed AI agent in 60 seconds. Uses Haldir for identity, secrets, audit, and policy enforcement.
Agent Stack
Local multi-agent runtime for Codex, Cursor, Claude Code, and Antigravity with MCP sync, shared docs, and Keychain-backed secret loading
Datadoe MCP Codex
This repository is a minimal example of using the DataDoe MCP server from Codex for Amazon-focused workflows.
Theaiteam
Reusable, provider-agnostic AI team. Drop a project brief, get end-to-end delivery. 12 role agents + 112 skills + orchestrator + self-improvement. Works with Claude Code, Codex, o…
Txfence
Policy engine and execution SDK for autonomous agents on EVM, Solana, and Cosmos.
Agentlayer
Deterministic toolkit for making websites readable, trusted, and operable by AI agents.
Sentinel
Multi-agent red-teaming pipeline for evaluating LLM security and hardening AI tool calls.
Twin Protocol
Twins Protocol — Agent-to-Agent communication protocol. Two AIs collaborating through a shared JSONL file.
ZidoCode
Agent security & reliability tooling
Amoxi
Full-stack TypeScript framework for Node.js and AI agents: compile-time dependency injection, server-rendered pages with islands, durable streaming agents, MCP and A2A.
Crossfeed Chat
Your ChatGPT subscription as a tool for local agents, and your computer's tools for ChatGPT chats, on macOS and Linux.
Lastword
Pins the verdict of a finished Claude Code session — the final answer, changed files and command outcomes — machine-checks every claim, and renders it as one pinned HTML page.
Bytely
Bytely turns repo into context graph for AI coding agents. AI Coding agent find and scope code from the graph instead of grepping.
Mismcp
opencode agents talk to each other — a shared SQLite bus for questions and answers, no MCP server, no build step, no Node.
Flashgate
The agent can't claim the firmware works — until the board says so. Hardware-in-the-loop verification gate: build → flash → boot banner → exit code.
True Hands
An AI that really operates the computer — and can prove it. Built-in desktop driver, UI-only enforcement, project-scoped policy.
Openai Agents API Examples
Runnable Python and cURL examples for OpenAI Agents API sessions, hosted coding, subagents, MCP, web search, and SSE.
OpsMesh
Autonomous Incident Commander Multi-Agent Platform (LangGraph + Anthropic MCP + OpenAI Tools + PostgreSQL Serverless + HITL + Scalar Docs)
Developer Assistant Skills
Vendor-neutral, open-source developer plugin for Claude Code, GitHub Copilot, and Codex — 34 skills & 20 agents for the full software lifecycle with closed-loop, bounded autonomou…
Pekka Bot
Open-source AI workspace where bots do the work on their own cloud computers. A Chief of Staff bot delegates to specialist bots with memory, skills, schedules and plugins. Self-ho…
Agent Socials Skill
Agent Skill (SKILL.md) for agent-socials, a social network for AI agents. For Hermes, OpenClaw, Letta and other persistent agents.
Hookstack
Put agents on your production signals without handing them the keys. A pipe signs, routes and prices every signal; an investigator runs read-only and proves it at startup; what su…
A2a MCP Warehouse Demo
When to use MCP vs A2A: a measured data-warehouse demo (ADK, MCP, A2A, OpenTelemetry)
Highbury
AI football analyst for Arsenal's 2003-04 Invincibles and 2025-26 seasons. Ask in plain English; an agent queries Postgres, draws pitch charts, and verifies every number.
Marv
A terminal coding agent with a sandbox, subagents, MCP and any model (OpenRouter or Ollama). TypeScript on Bun.
Agent Bridge
Agent-to-Agent communication bridge supporting MCP, A2A, and HTTP protocols
DeepBridge
A local MCP/A2A bridge that enables Codex to delegate tasks to DeepSeek Harness with reusable conversation context.
Quesen SDK Py
Official Python SDK for Quesen — the deterministic AI decision engine for autonomous-agent risk evaluation.
Portal
Manage 100+ providers, APIs, models, memory engines through one skill/mcp/API
MCPTap
MCPTap is a lightweight LLM proxy for AI agents that intercepts traffic (currently OpenRouter/Requesty) and controls MCP tool calls / protects files from AI agent.
QuantumAgentGuard
Static analysis for AI agent codebases: agentic vulnerability patterns + quantum-readiness/PKI gaps, in one scan.
Code Atlas
Local-first change intelligence for coding agents.
Halo Agent Showcase
HALO Agent OS: a hosted operating system for a one-person business, staffed by AI agents. Showcase; source is private.