- 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.
Psibot
Always-on AI agent for Telegram, powered by Claude Agent SDK. Runs 24/7 on your Mac with your Max subscription. $0 API costs. Multimodal: voice, images, YouTube, browser automatio…
Bayesconsensus
Dawid-Skene consensus for multi-agent and multi-LLM disagreement: learn each agent's reliability and the true answer with calibrated confidence. Zero dependencies, node-free, Type…
Vibe Flow
Orchestration skills plugin for Vibe Kanban: plan -> ship -> review -> merge with wave-based dispatch and tier routing
Langgraph Forge
Initialise LangGraph-based agent architectures: pick a provider, a pattern, a deployment — get a runnable project.
Podsml
Self-hosted, one-click pods for AI agents. Your box, your data, your keys.
Bazaarmcp
Constraint-aware corporate procurement agent. Gemini 2.5 Flash function calling + WebMCP-style manifest discovery + server-side budget guardrails. Live supplier portal at the home…
Icu Triage Agent
3-agent A2A autonomous ICU triage system — SOFA/NEWS2 scoring, MCP tools, Groq/Llama 3 inference, Streamlit dashboard
Meta Harness Studio
Author one AI coding harness once, project it onto Claude Code, Codex, OpenCode, Cline, Kilo Code & Pi — then let it improve itself from execution traces (arXiv:2603.28052).
Olx4ai
A tool for ai to navigate OLX
RoshniAI
Multi-Agent AI University Guide built using Python, Flask, MCP, and Groq for the Google × Kaggle AI Agents Course.
Boundary Bench
Deterministic crash tests for agent control planes: paired worlds, hard stops, budgets, scopes, approvals, and hash-linked receipts.
Kimss Forge
Kimss Forge - MIT open-source agent harness. Any model free; gateway=kimss for production governance.
Zcode
Enterprise-first coding agent CLI written in Zig
Manifest Php
Manifest SDK for PHP. See every API call your app makes, heal the ones that fail, and know what will break next.
Growthgate
Empirical growth engineering skills, autonomous GTM playbooks, and GEO methodologies for AI agents
Ripieno
A self-hosted shared workspace where several people and several AI agents work on one codebase - every message and file change attributed to a named agent belonging to a named per…
Harness Delegation
Lightweight external coding-harness delegation for native Codex: Pi RPC, Grok ACP, CLI, Skill, and MCP.
Archbase
CLI open-source em Go para padronizar arquitetura e padrões de código entre desenvolvedores e agentes de IA, com registries, rules, scopes e MCP.
Atomicwork
Atomicwork — independent third-party profile of a public API surface, by API Evangelist. Atomicwork is an agentic service management (ITSM/ESM) platform that pairs an AI "coworker…
Patchwork Harness
The verifying harness for AI coding agents: test gates, independent cross-vendor review and grounded answers, with every action on the Patchwork audit trail.
AI Meeting Room
You, Claude, GPT and Gemini in one local meeting room. Each AI speaks for itself; you watch and interject in the browser. Uses your existing subscriptions, no API keys.
Leap Framework
🎓 LEAP Framework — a state-driven agentic tutoring runtime for AI agents, exposed over MCP. Server-side State Guard, evidence-based mastery, FSRS retention.
Whichrepo
Local-first task router for microservices, polyrepos, monorepos, and coding agents.
Xiocode
Local-first terminal coding agent: self-owned runtime, kernel-backed process layer, turn-by-turn rollbacks, worktree isolation.
Awesome Personal Agents
A curated list of open-source and commercial personal AI agents for life and work, with a selection guide comparing memory, autonomy, privacy, integrations, deployment, and costs.
Troupe
A coding-agent harness for Kubernetes and your own machine: a control plane and admin console for teams, a local daemon, a terminal UI and a desktop app, all over one public proto…
TerminalApp
Native Windows workspace for tiled coding-agent terminals and local worker orchestration
Awesome Wundercorp
A structured, searchable directory of WunderCorp products, open-source projects, packages, tools, and community links.
Vector Mind
Intelligent tool router for agentic AI applications
Agent Loop Guard
Local runtime guard for coding agents with loop detection and explainable policy decisions.
Book Agent Harness
《Agent Harness 工程》：对照 23 个真实 coding agent 的源码，讲清 agent 里模型之外那部分代码的设计决策。在线阅读 + PDF/EPUB。
Behavior Os
behaviorOS — Workflow Operating System for governed multi-agent development: DNA-driven rules, deterministic pipelines, autonomous missions with observable evidence
Fleet Os
Fleet OS · 舰队模式 — 生产级多 Agent 协同引擎：WS 黑板 + 事件溯源 + 盲评对抗 + 跨舰队接力 + 上下文压缩 + 多厂商负载均衡 + 自进化。36 模块，零运行时依赖，MCP 40 工具，48 项 e2e 全绿。
ChangeWarden
Governed GitHub changes for AI coding agents: policy, independent approval, one-time execution, and verifiable receipts.
Agentops AI
Evidence-grounded AI agent for business analytics, forecasting, anomaly detection, and decision intelligence.
Langgraph Copilotkit A2ui Product Assistant
Generative-UI product assistant: a LangGraph supervisor routes to catalog, compare, recommend and cart agents; a CopilotKit v2 runtime streams A2UI components into a Next.js app a…
Wechat AI Miniprogram Guide
微信 AI 小程序开发全流程实战：多智能体 + 高德地图 MCP + FastAPI + 微信云托管。一份从 0 到真机跑通的中文指南，配一个可运行的真实项目。
GreyWork
Desktop-first AI agent workspace for developers: ACP agents + local OpenAI-compatible models, authorized workspace with Git & file preview, plugin/MCP/skills market, scheduled tas…
ForgeLoop
ForgeLoop is a distributed software-engineering harness for autonomous coding agents. It decomposes feature specifications into parallel units of work, executes agents in isolated…
Claude Telegram Hook
Claude Code plugin: answer its questions, plan approvals and permission prompts from your phone via Telegram when you step away from your Mac or Linux desktop. Tap an option, Allo…
Allcode
One terminal workspace for Claude Code, OpenCode, and Codex.
Searchright
Contract-first Rust infrastructure for programmable and agentic systematic literature searches.
Deployarc Opencode Supertools
Free hosted-provider-first OpenCode AI coding setup: agents, MCP, model routing, one-command installer, provider templates, and safe handover docs.
Agentic Trading Orchestrator
Human-in-the-loop AI trading-agent orchestration with Claude Code, MCP, persistent state, expiring reviews, Gmail notifications, and PowerShell reliability tests.
C1417 Claude Code Masterclass
Non-WSQ Claude Code Masterclass (C1417), 1 day: courseware and four hands-on labs on the agentic loop, context engineering, custom commands, MCP, skills, sub agents and hooks.
Agent Reliability Toolkit
Test AI agents repeatedly, measure reliability, classify failures, and catch regressions before production.
Aevoren Bot
Open-source, local-first macOS workspace for persistent AI Bots and deterministic multi-Bot collaboration.
Agent Neutral Harness
Reliability, memory, and model-routing for AI coding agents — you keep your agent loop, pass it in as execute_fn(model, task). Local-first, MIT.
Sovereign Security Protocol
Full SSP v13.4.0 source in Portuguese, with bilingual community summaries for application security, secure SDLC, AI agents, MCP, and evidence-based adoption.
Praxeon
Runtime supervision for autonomous AI agents