- Conduid
- Marketplace
- #agent-harness
MCP servers tagged agent-harness
137 live MCP servers tagged "agent-harness", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with agent-harness.
Keelson
A self-evolving agent harness — permission-gated execution, context folding, and a gated skill-update pipeline, validated with real benchmarks (including one that caught a bug in…
The Ideal Harness
Agent harness / control-plane around a stateless LLM: deterministic policy floor on PreToolUse/PostToolUse hooks, secret redaction, injection fencing, tool-result compression, cod…
Mingbird Agent
Local-first agent harness (Windows + Ollama) for 2–9B models. Same 2B model: 0.017 → 0.821 across four agent harnesses — 48×. 288-cell benchmark, every cell public. One-click zero…
Jev Decision Layer
Open-source decision layer for AI agents. Typed task, tool, skill and review routing through TypeSafe Jev, with local policy gates and auditable receipts.
MendCode Legacy
MendCode: Customizable CLI for agents, teams, memory, reviews, and TUI.
Mira Harness
Mira Harness 是一款本地优先的个人 AI 工作台：Agent 工作台、AI 小说创作与微应用宿主，数据与模型密钥不出本机。基于 Vue 3 + TypeScript + Vite + Electron。
Canary Lab
Your AI agent implements the code. Canary Lab proves it works.
Polter
One Claude Code session supervises the agents in your other terminal tabs: which is stuck, which is done, which is still running. A fork of Ghostty.
Thursday
One day short of Friday — a realtime voice harness that runs on your own machine.
HarnessDesk
Open-source control plane for coding agents you own — run Codex, Claude Code, Gemini, Cursor and ACP agents side by side with shared history, permissions, handoffs and audit logs.
Terva
An agent harness — a coding agent out of the box, open to anything you can wire a tool to. One hardened Go core, many front ends, pluggable in any language.
Jev Engineering
The decision layer for AI agents. Typed, calibrated decisions in ~400ms for two hundredths of a cent: gate tool calls, route models, rank options. With the 300-call injection test…
Loopplane
Spec-first, embeddable agent harness runtime - a control plane for loop-engineered AI agents. Governed tool calls through one gateway, one normalized event stream, durable session…
Harness.WinUI
A lightweight, native Windows AI agent — WinUI 3 + .NET 9, works with any OpenAI-compatible endpoint.
Dsh Subagent MCP
Persistent DeepSeek subagents for Codex: parallel work, native completion callbacks, and no model polling.
Lemieux
An open-source coding agent you can take apart: a terminal app (lmx), and the Elixir runtime underneath it (Lemieux). Works with any ReqLLM provider or a local Ollama model, and k…
Harness Scouter
Scores a Claude Code harness from the transcripts already on your machine: 6 stats of what your agent actually did, computed locally with no LLM calls. Then it runs a reproducibil…
Issueops
IssueOps: issue-driven agent workflows for Codex, Claude Code, and Omo
C31
C31 — Agent Harness System. Memory that persists. Instincts that evolve. Context that stays healthy.
LLM Agent Harness Survey
模型决定上限，Harness 决定下限：LLM Agent 与 Harness 适配性研究综述 | A Survey on Model–Harness Adaptation (Agent = Model + Harness)
Sandbase Docs
Official SandBase developer documentation: one API for LLMs, image, video, audio, embeddings, real-world APIs, and reusable Agents.
Awesome Bio Agents
A curated collection of AI agents, harnesses, MCP servers, skills, tools and benchmarks for biological research.
Atlias
Agent harness for Claude Code, Codex, Antigravity, Gemini CLI: shared memory, guards, two-pass verification gate.
Duin Governed Agent Memory
Agents that earn your trust. A harness that keeps an agent's long-term memory, model of your world and permissions as Markdown you own, governed at every step: facts labelled by w…
Kimss Forge
Kimss Forge - MIT open-source agent harness. Any model free; gateway=kimss for production governance.
Orca Harness
Orcacode: a terminal coding agent in a single small Rust binary, and the harness kernel that runs it
Agentic Harness Engineering Workshop
Agentic-Harness-Engineering-Workshop
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…
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。
Reweave
🧵 Self-healing web data pipelines — an agent that detects scraper breakage, synthesizes validated selector repairs, and ships them only through a human approval gate. Built on Tru…
SwarmMojo
Full-fledged local-first AI agent harness combining ROMS (RAG, OKF, MCP, Skills), Decision AI, correction memory, and reviewable workflow preparation.
Codex Harness MCP
Local Codex MCP harness for contracts, persistent RAG memory, evals, natural-language specs, and Meta-Harness-lite promotion records.
Codelens MCP Plugin
Rust MCP server for bounded code intelligence, gated mutation, and auditable agent workflows.
Codex Source Analysis
OpenAI Codex 源码深度研究 (Rust + TS + Python)：2 总纲 + 25 章 + 3 附录, ~51 万字 + 149 张 Mermaid 架构图
Prime Silo
The canonical Sovereign AI Agent OS & runtime harness. Built for Model Context Protocol (MCP), Agent-to-Agent (A2A) swarms, and zero-token tax execution.
Deepseek Harness Handbook
Agent-first, multilingual handbook for DeepSeek Harness: quickstarts, architecture, safety, troubleshooting, and production recipes.
Memtomem Stm
Short-term memory proxy gateway with proactive memory surfacing for AI agents
Patter MCP
MCP server for the Patter Voice AI SDK — make and receive phone calls from any MCP-compatible client (Claude Code, Cursor, ChatGPT, OpenClaw, Hermes Agent, Codex). Streamable HTTP…
Neuroverseos Governance
Deterministic governance engine for AI agents. Enforce rules defined in .md governance files across AI systems.
Boss Skill
Build AI boss personas for worker protection, PUA detection, negotiation practice, and labor law checks.
Harneloop
Build self-evolving AI agent harnesses with portable harness units, artifact-aware testing, trace-backed diagnosis, and evidence-gated promotion.
Mini Agent Harness
A small native coding-agent harness with bounded tools, streaming REPL, Agent Skills/Plugins, MCP, and OpenAI-compatible Responses API support.
BuildYourOwnHarness
Generate, deploy, and evolve a personalized AI agent harness (Claude Code / Codex / Antigravity) from a user's tacit knowledge, data, genre, and goals — interview → synthesize → r…
AeroCode
Local-first Markdown notes × multi-model AI assistant × permission-gated agent harness — one .NET 9 + Avalonia 11 codebase for Windows & Android. 本地优先笔记 + AI 助手 + Agent 护栏，双端同源。
Edit AI
An AI harness for video editing. Describe the edit; an agent makes it on your real timeline through 16 MCP tools: remove silences, caption every clip with parallel sub-agents, cut…
Localflow
Safe execution harness for LLM agents operating on local workspaces.
Caliban
A from-scratch Rust agent harness that puts the operator in control of model routing, memory, skills, and prompt context.
Harness Creator
Portable agent skill for designing safe, layered, source-backed agent harnesses and orchestration workflows.
Tool.Agent Harness Deploy
Self-deploying cross-tool AI harness — one canonical source deployed to Claude Code, Codex, Cursor, Devin, Antigravity & 9 more. Loop engineering, three-layer memory, worker perso…
Grom
BYOLLM. AI coding assistant for VS Code that runs on your machine — agentic, private, zero friction.