genai-io/san

genai-io/san has 149 GitHub stars and 36 forks. Star changes are not measured yet. Last checked 2026-11-13 10:07 UTC. Last push 2026-11-13.

Comment ces chiffres sont mesurés

Open-source terminal agent runtime. Lean context, native speed, open all the way down — in a single Go binary.

149 étoiles 36 forks

Progression mesurée des étoiles

in 24h: Historique en cours
in 7 days: Historique en cours
in 15 days: Historique en cours
in 1 month: Historique en cours

Variations nettes sur des périodes qui se chevauchent, pas des totaux quotidiens. Les mesures absentes restent vides. Les étoiles indiquent l’intérêt, pas la qualité.

README.md

Original

< SAN ✦ />

Minimal overhead. Maximum agent.

Lean context, native speed, open all the way down.

English · 简体中文

_{Open the full-quality intro ↗}

Why San

Small and fast — A single native Go binary with minimal context overhead. No Node.js or Python required.
A less opinionated harness — A model-agnostic runtime with a consistent interface for shaping agent behavior through system prompts, personas, skills, and tools.
Multi-agent coordination — Subagent collaboration, cross-session messaging, and dynamic workflows.
Control and visibility — Configure execution permissions and inspect model context and tool calls.

Features · Architecture

_{*The name — San, written 三 ("three") and drawn ☰. From the Dao De Jing, 三生万物 — "three begets the ten-thousand things": one runtime that becomes any agent, running a three-step loop (reason → act → observe). The command stays san.*}

Installation

macOS / Linux — choose one:

# Homebrew
brew install genai-io/san/san

# Or use the install script
curl -fsSL https://raw.githubusercontent.com/genai-io/san/main/install.sh | bash

Windows (PowerShell)

irm https://raw.githubusercontent.com/genai-io/san/main/install.ps1 | iex

Other installation methods, updates and uninstall

Uninstall

# macOS / Linux
curl -fsSL https://raw.githubusercontent.com/genai-io/san/main/install.sh | bash -s uninstall

# Windows (PowerShell)
& ([scriptblock]::Create((irm https://raw.githubusercontent.com/genai-io/san/main/install.ps1))) uninstall

Go Install (requires Go 1.26.9+)

go install github.com/genai-io/san/cmd/san@latest

Build from Source

git clone https://github.com/genai-io/san.git
cd san
go build -o san ./cmd/san
mkdir -p ~/.local/bin && mv san ~/.local/bin/

Updates

Automatic: new releases install in the background; the status line prompts you to restart.
Manual: run san update, or brew update && brew upgrade genai-io/san/san for Homebrew installations. The Homebrew formula syncs daily, so newly published releases may take time to appear.
Disable automatic updates: use /settings › General or set SAN_DISABLE_AUTOUPDATE=1.

Usage

Run san, then choose a model and add its API key when prompted.

san                          # interactive
san "explain this function"  # one-shot
san -p "do something"        # print mode (no TUI), pipe-friendly
san --continue               # resume the latest session
san --resume                 # pick a past session to resume

Use san --help for CLI options and /help for interactive commands.

Benchmark: San vs Claude Code

Compared with Claude Code v2.1.112 on Apple Silicon, same model (claude-sonnet-4-6):

Metric	San	Claude Code	Advantage
Download size	12 MB	63 MB (+ Node.js 112 MB)	5x smaller
Disk footprint	38 MB	175 MB	4.6x smaller
Startup time	~0.01s	~0.20s	20x faster
Startup memory	~32 MB	~189 MB	5.8x less
Simple task	~2.4s / 39 MB	~10.4s / 286 MB	4.3x faster, 7.3x less memory
Tool-use task	~3.3s / 39 MB	~26.0s / 285 MB	7.9x faster, 7.2x less memory
Harness context*	~2.3k tokens	~20.9k tokens	~9x leaner

_{*Context overhead is system prompt + tool schemas on an empty first turn, measured separately on San v1.22.0 vs Claude Code v2.1.220 — see method. All other rows are from the v1.13.2 / v2.1.112 run.}

Comparable feature sets — the gap is client-side overhead, not capability. docs/operations/benchmark.md

Documentation

Get started — setup, configuration, commands, and permissions.
Features — capabilities and detailed documentation.
Customize and extend — prompts, personas, skills, and integrations.
Develop and contribute — architecture, development, and design.

Related Projects

Claude Code — Anthropic's AI coding assistant
Aider — AI pair programming in terminal
Continue — Open-source AI code assistant

Community

Two ways in — WeChat for the Chinese community, Slack for everyone else:

WeChat — 关注公众号「极客外传」· 回复 san 或 三 入群
Slack — Join our Slack

Contributing

Contributions welcome! See CONTRIBUTING.md for guidelines.

License

Apache License 2.0 - see LICENSE for details.