A
autohandai/code-cli
Terminal coding agent with many providers and a plan mode
View on GitHub ↗Link checked 2026-11-12 · HTTP 200 · opens the vendor's own site
Install & config
Install command from the repository
brew install autohandai/code/autohand-code
Parsed from the README we fetched on 2026-11-07; we have not executed it.
This is the install method the repository states, not an MCP client config, so no JSON is generated.
Key names differ by client: Clients & CLI
- Source
- collected from the abordage/awesome-mcp list · type: MCP server
- Harvest history
- first seen 2026-11-05 · last seen 2026-11-14 · seen 10× · listed by 10 sources
- Score
- score 1,003 · 10 sources · mcp
- Install
brew install autohandai/code/autohand-code
FAQ (answers come from our records)
How do I install it?
The repository provides this install command:
brew install autohandai/code/autohand-code. It comes from the repository itself; we cannot guarantee it runs as-is in your client.Who is it for?
We filed it under these tags: MCP 服务. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
first catalogued 2026-11-05;last seen 2026-11-14。There is no official certification or quality rating here — we record sources and dates only.
# Autohand Code CLI
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
Follow us on X | Join Discord
Docs: English | 日本語 | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Polski | Русский | Português (Brasil) | Türkçe | Čeština | Magyar | हिन्दी | Bahasa Indonesia
A fast, self-improving terminal-native AI coding agent for planning, reflecting, remembering, editing, testing, and automating work across your codebase.
Autohand Code CLI is a fast, terminal-native AI coding agent that lives where you already work. It reads project context, plans changes, edits files, runs tools, and asks for approval before risky operations.
The interface is built for focused interactive sessions: minimal chrome, smooth Ink rendering, file mentions, slash commands, skills, permissions, provider switching, and session history all available from one prompt.
Install it, run autohand, and describe the outcome you want in natural language. Use Autohand Code CLI locally, with your editor, or in CI/CD to automate repetitive engineering work without giving up control.
## Features
Interactive sessions assess repository readiness in the background while you work. A bounded, read-only scan compares AGENTS.md and CLAUDE.md history with committed and uncommitted changes, then asks your configured model for a repository map and concrete improvement candidates. It runs no project scripts and makes no edits. After your first successful turn, new findings appear once per repository; materially new findings can be offered in a later session. Use /readiness to review the evidence, /readiness apply 1 to choose a finding, or /readiness dismiss to skip. Set ui.repositoryReadiness to false to disable this background model request. Bare, ephemeral, offline, command, RPC and ACP sessions skip it.
The shell installer includes Zit v0.1.2 by default on supported macOS and Linux platforms, preserving an existing installation and verifying release checksums. Use --no-zit or AUTOHAND_SKIP_ZIT_INSTALL=1 to opt out. The Windows installer supports -NoZit and the same environment variable; it preserves an existing Zit installation and reports that native Windows binaries are currently unavailable. autohand --zit requires Git 2.38 or newer. Installing Zit does not initialize repositories.
On Windows, running install.sh from Git Bash, MSYS, or Cygwin delegates to the native PowerShell installer and preserves installation options. Autohand launched from Git Bash uses Bash for command tools; see shell settings to choose an executable explicitly.
The npm package includes checksum-verified Zit binaries for macOS and Linux on ARM64 and x64. npm install -g autohand-cli and bun install -g autohand-cli download them with the package, including when lifecycle scripts are disabled. Autohand uses ZIT_BIN, an existing zit on PATH, or its packaged binary, in that order. Rust and a separate Zit installation are not required. Native Windows Zit binaries are currently unavailable.
Terminal-Native Agent: Understands your codebase and executes approved changes from the CLI
Planning + Tools: Combines reasoning, file edits, shell commands, and web context in one loop
Interactive REPL: Smooth terminal experience with file mentions, slash commands, and keyboard shortcuts
Docs: English | 日本語 | 简体中文 | 繁體中文 | 한국어 | Deutsch | Español | Français | Italiano | Polski | Русский | Português (Brasil) | Türkçe | Čeština | Magyar | हिन्दी | Bahasa Indonesia
A fast, self-improving terminal-native AI coding agent for planning, reflecting, remembering, editing, testing, and automating work across your codebase.
Autohand Code CLI is a fast, terminal-native AI coding agent that lives where you already work. It reads project context, plans changes, edits files, runs tools, and asks for approval before risky operations.
The interface is built for focused interactive sessions: minimal chrome, smooth Ink rendering, file mentions, slash commands, skills, permissions, provider switching, and session history all available from one prompt.
Install it, run autohand, and describe the outcome you want in natural language. Use Autohand Code CLI locally, with your editor, or in CI/CD to automate repetitive engineering work without giving up control.
## Features
Interactive sessions assess repository readiness in the background while you work. A bounded, read-only scan compares AGENTS.md and CLAUDE.md history with committed and uncommitted changes, then asks your configured model for a repository map and concrete improvement candidates. It runs no project scripts and makes no edits. After your first successful turn, new findings appear once per repository; materially new findings can be offered in a later session. Use /readiness to review the evidence, /readiness apply 1 to choose a finding, or /readiness dismiss to skip. Set ui.repositoryReadiness to false to disable this background model request. Bare, ephemeral, offline, command, RPC and ACP sessions skip it.
The shell installer includes Zit v0.1.2 by default on supported macOS and Linux platforms, preserving an existing installation and verifying release checksums. Use --no-zit or AUTOHAND_SKIP_ZIT_INSTALL=1 to opt out. The Windows installer supports -NoZit and the same environment variable; it preserves an existing Zit installation and reports that native Windows binaries are currently unavailable. autohand --zit requires Git 2.38 or newer. Installing Zit does not initialize repositories.
On Windows, running install.sh from Git Bash, MSYS, or Cygwin delegates to the native PowerShell installer and preserves installation options. Autohand launched from Git Bash uses Bash for command tools; see shell settings to choose an executable explicitly.
The npm package includes checksum-verified Zit binaries for macOS and Linux on ARM64 and x64. npm install -g autohand-cli and bun install -g autohand-cli download them with the package, including when lifecycle scripts are disabled. Autohand uses ZIT_BIN, an existing zit on PATH, or its packaged binary, in that order. Rust and a separate Zit installation are not required. Native Windows Zit binaries are currently unavailable.
Terminal-Native Agent: Understands your codebase and executes approved changes from the CLI
Planning + Tools: Combines reasoning, file edits, shell commands, and web context in one loop
Interactive REPL: Smooth terminal experience with file mentions, slash commands, and keyboard shortcuts
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/autohandai-code-cli/)
- Source
- awesome · https://github.com/autohandai/code-cli
- Browse by field
- MCP servers
- Listed by
- 10 independent sources
- added
- today
More like this
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.