Agentty MCP Server

agentty

An agent harness for your terminal. Ready to type in 47 ms, 21 MB of memory while idle.<br> One small native binary. Use the Claude, ChatGPT or Copilot plan you already pay for, or any model, even local.

<p> <a href="https://github.com/agentty-org/agentty/releases/latest"><img src="https://img.shields.io/github/v/release/agentty-org/agentty?style=flat-square&color=blue" alt="Release" /></a> <a href="https://github.com/agentty-org/agentty/stargazers"><img src="https://img.shields.io/github/stars/agentty-org/agentty?style=flat-square&color=f1c40f&labelColor=555555" alt="Stars" /></a> <a href="https://github.com/agentty-org/agentty/releases"><img src="https://img.shields.io/github/downloads/agentty-org/agentty/total?style=flat-square&color=brightgreen" alt="Downloads" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue?style=flat-square" alt="License" /></a> <a href="https://discord.gg/qhb9AZ8f3c"><img src="https://img.shields.io/badge/Discord-join%20chat-5865F2?style=flat-square&logo=discord&logoColor=white" alt="Discord" /></a> <a href="https://web.libera.chat/#agentty"><img src="https://img.shields.io/badge/IRC-%23agentty-0b2b8a?style=flat-square" alt="IRC" /></a> </p> <p> <a href="https://agentty.org">Website</a> · <a href="https://agentty.org/docs/">Docs</a> · <a href="https://agentty.org/benchmarks/">Benchmarks</a> · <a href="https://agentty.org/agent-harness/">What is an agent harness?</a> · <a href="https://agentty.org/changelog/">Changelog</a> </p> <p> <img src="https://agentty.org/agentty.gif" alt="agentty fixing a failing test: plan, map the repo, run the tests, search, read, send a subagent, edit, patch, write a test, re-run, review" width="780" /> <br>_{A real session with the current release, replayed from the terminal.} </p>

curl -fsSL https://agentty.org/install.sh | sh    # Linux · macOS
irm https://agentty.org/install.ps1 | iex         # Windows (PowerShell)

What it is

The model decides what to do; the harness is everything around it: the tools it can call, the sandbox they run in, what goes into its context, which model handles which turn, and the interface you steer it from. agentty is that harness, written in C++26 and shipped as a single static binary.

• One small binary. About 23 MB, starts in milliseconds, no Node, Python or Electron, no npm install. Download it and run it.
• Any model. Sign in with the Claude Pro/Max, ChatGPT, GitHub Copilot or Kimi plan you already have, use an API key for OpenAI, DeepSeek, Gemini, Grok, Mistral, Groq, OpenRouter and more, or run a local model through Ollama. Switch mid-thread with ^P and ^/.
• Sandboxed by default. Every shell command runs behind a wall the operating system enforces; your ~/.ssh, ~/.aws and .env files are masked.
• Frugal with context. A local retrieval engine finds the code that matters instead of pasting whole files, so turns stay small and cheap.
• Everywhere you work. In the terminal, inside Zed or JetBrains over ACP, as an MCP server, in scripts and CI, or on an air-gapped machine over SSH.
• Open source (MIT).

Coming from another tool? vs Claude Code · vs Codex CLI · vs Gemini CLI · vs opencode · vs jcode · vs Aider · vs Cursor · all alternatives

Benchmarks

What each harness costs you before the model does any work. Same machine, fresh install, no login, runs interleaved across tools; median of 10 launches (30 for --version).

	ready to type	idle memory	on disk, with runtime	--version
agentty 0.9.51	47 ms	21 MB	23 MB	2.6 ms
jcode 0.99.1	56 ms	106 MB	163 MB	17 ms
Codex CLI 0.167.0	402 ms	152 MB	536 MB	77 ms
Claude Code 2.1.319	635 ms	152 MB	325 MB	14 ms
Aider 0.86.2	1.0 s	74 MB	653 MB	1.1 s
Gemini CLI 0.67.0	3.0 s	441 MB	197 MB	2.6 s
opencode 1.19.5	5.2 s	651 MB	409 MB	0.8 s

_{Measured 2026-11-08 on an Intel i5-6200U (4 threads, 16 GB), Linux. "Ready to type" is the time until the first prompt is fully drawn, read from the rendered terminal. agentty and jcode launch within the same range; call that a tie. Method, ranges and the script to reproduce it: <a href="https://agentty.org/benchmarks/">agentty.org/benchmarks</a>.}

Getting started

cd your-project
agentty

The first launch asks how to connect: sign in with Claude Pro/Max, ChatGPT, GitHub Copilot or Kimi (no API key), paste an API key, or pick a local Ollama model. Then type a request and press Enter. Rerun the install line to update. Quick start ↗ · other installs

Features

<table> <tr> <td width="50%" valign="top">

Fast all the way through

A prompt on screen in under 50 ms. Independent tool calls run in parallel, and read-only tools start while the model is still writing, so tool-heavy turns finish sooner.

Any model, any plan

Subscriptions you already pay for, API keys for ten more providers, any OpenAI-compatible endpoint, or local Ollama. One model picker across every provider you're signed into. Providers ↓

Sandboxed by default

Shell and build commands run inside claybin: seccomp, Landlock and cgroups on Linux, seatbelt on macOS, AppContainer and job objects on Windows. Credential files are masked, file tools refuse paths outside your workspace, and network goes through a proxy that refuses your LAN, localhost and cloud metadata. Turn it off with --sandbox off. Sandboxing ↗

Air-gapped mode

agentty airgap user@host runs a session on a machine with no internet; your laptop relays the traffic over SSH with TLS pinned end to end.

</td> <td width="50%" valign="top">

A full tool suite

read · edit · write · apply_patch · shell · grep · glob · outline · find_definition · repo_map · git · test · diagnostics · web · search_code · search_docs · task · todo · remember — each with a purpose-built widget in the UI.

Learns your codebase

A fully local retrieval engine: search_code over your repo, search_docs over your docs, skills and memory. Keyword search works out of the box; ollama pull nomic-embed-text adds meaning-based search. Agent Skills in Claude Code's format, and remember / forget across sessions. Retrieval ↗

Smart Mode

A flagship model plans; cheaper models do the legwork. Effort scales to each turn, and the router learns your repo across sessions. Off is a strict no-op. Smart Mode ↗

Scripts and CI

agentty run "fix the failing test" runs one prompt with tools and prints the answer. --json, --timeout, --events jsonl, clear exit codes, and --read-only --no-network for untrusted code. Docs ↗

</td> </tr> </table>

Providers

Sign in with a subscription you already have:

agentty login        # → Claude Pro/Max · ChatGPT (Plus/Pro) · GitHub Copilot · Kimi

Or point it at any of these:

--provider	What	Key
anthropic	Claude (the default): API key or Pro/Max sign-in	agentty login
chatgpt	Codex models with your ChatGPT plan	agentty login
copilot	GitHub Copilot models	agentty login
kimi	Kimi K2 models	agentty login
openai	GPT and o-series	OPENAI_API_KEY
deepseek	DeepSeek V4 (chat and reasoner)	DEEPSEEK_API_KEY
gemini	Google Gemini	GEMINI_API_KEY
xai	xAI Grok	XAI_API_KEY
mistral	Mistral, Codestral, Magistral	MISTRAL_API_KEY
groq	Llama, Mixtral, Kimi on Groq LPUs	GROQ_API_KEY
cerebras	Wafer-scale inference	CEREBRAS_API_KEY
together	Open models on together.ai	TOGETHER_API_KEY
fireworks	Open models on fireworks.ai	FIREWORKS_API_KEY
openrouter	Any model via openrouter.ai	OPENROUTER_API_KEY
ollama	Local models on localhost:11434	none
host:port	Any OpenAI-compatible server (llama.cpp, vLLM, LM Studio…)	optional

agentty --provider ollama -m qwen2.5-coder        # local, no key, no cloud
agentty --provider deepseek -m deepseek-v4-pro
agentty --provider openrouter                     # pick any model in-app

--provider persists. Inside a thread, ^P switches provider and ^/ switches model, with no restart. Behind a gateway, --auth-header X-API-Key sends the key under a custom header. Full reference: Providers & Models.

Keys

Key	Action	Key	Action
Enter	Send / queue	^K	Command palette
Esc	Cancel / reject	^J	Thread list
S-Tab	Cycle permission profile	^P	Provider picker
Alt+Enter	Newline	^/	Model picker
^B	Loop: resend until off	^N	New thread
^G	Run a code block	^S	Smart Mode
^R	Review changes	^T	Plan / todo
^O	Tool outputs	^U	Read thinking (empty composer)
^L	Stats	^E	Expand composer
^C	Quit	Alt+←/→	Cycle threads

The composer is a readline-style editor (^W, Alt+D, ^Z, / @ # pickers, image paste). Full keymap ↗

Installation

curl -fsSL https://agentty.org/install.sh | sh        # Linux, macOS (builds from source if the binary won't run)
brew tap 1ay1/tap && brew install agentty             # macOS
winget install agentty                                # Windows (or: irm https://agentty.org/install.ps1 | iex)
yay -S agentty-bin                                    # Arch

Every release is a single static executable for Linux (x86_64, aarch64), macOS and Windows.

<details> <summary><b>.deb, .rpm, Scoop, Termux</b></summary>

# Debian / Ubuntu
curl -fsSLO https://github.com/agentty-org/agentty/releases/latest/download/agentty_${V}_amd64.deb
sudo dpkg -i agentty_${V}_amd64.deb

# Fedora / RHEL / CentOS
sudo dnf install https://github.com/agentty-org/agentty/releases/latest/download/agentty-${V}-1.x86_64.rpm

# openSUSE
sudo zypper install https://github.com/agentty-org/agentty/releases/latest/download/agentty-${V}-1.x86_64.rpm

# Windows (Scoop)
scoop bucket add 1ay1 https://github.com/1ay1/scoop-bucket; scoop install agentty

# Termux / Android (no root; commands run unsandboxed there)
pkg install git cmake clang openssl libnghttp2
curl -fsSL https://agentty.org/install.sh | sh -s -- --build

V is the version, e.g. 0.9.53. Installation ↗

</details>

Building from source

Needs a C++26 toolchain (GCC 14+, a recent Clang, or MSVC).

git clone --recursive https://github.com/agentty-org/agentty.git
cd agentty && cmake -B build && cmake --build build -j

Editing the code? cmake --preset debug rebuilds in about 1.7 s after a one-line change (no LTO). Building ↗

More

• Air-gapped hosts: agentty airgap --setup user@host once, then agentty airgap user@host. Docs ↗
• Zed, JetBrains (ACP): agentty acp. Zed setting below. Docs ↗
• MCP, both ways: agentty mcp-serve exposes the native tools; servers in .agentty/mcp.json join them; agentty mcp import copies yours from another tool. Docs ↗
• Loop a prompt (^B): resends after every turn until you press ^B again, with backoff on errors and a ⟳ LOOP ×N chip so it never looks idle.
• Run code blocks (^G): runs a block from the last reply on your real terminal, then lets you attach the output. Details
• Agent Skills: drop a SKILL.md in .agentty/skills/ (Claude Code's format works). Installing skills
• Architecture: (Model, Msg) -> (Model, Cmd), rendered by maya. docs/ARCHITECTURE.md

{ "agent_servers": { "agentty": { "command": "agentty", "args": ["acp"] } } }

Community

Discord (with a helper bot that answers using agentty itself), or #agentty on Libera.Chat / #agentty:libera.chat on Matrix.

License

MIT; see LICENSE.