Hugging Face 出的极简智能体，手把手教你从零造一个属于自己的 coding agent。学习写 agent 的入门玩具。

https://t.co/7nBeX7B2DE https://t.co/lfSqRk2ZLN

huggingface/tau

Source: https://github.com/huggingface/tau

A small, readable terminal coding agent — and a working example of how coding agents are built.

Documentation · Quickstart · Architecture · PyPI · Roadmap

What is Tau?

Tau is a coding agent that lives in your terminal. You type requests like “explain this repo”, “add tests”, or “fix this stack trace”; Tau can read files, edit code, run commands, and keep a durable session history while streaming what it is doing.

Tau is also meant to be read. It is a teaching project for understanding the shape of a coding-agent system without starting from a giant production codebase.

tau_coding  →  tau_agent  →  tau_ai

• tau_ai translates model providers into Tau’s provider-neutral stream.
• tau_agent owns the portable brain: messages, tools, events, loop, harness, and session primitives.
• tau_coding wraps the brain as a real coding app: CLI, TUI, file/shell tools, provider config, project instructions, skills, and on-disk sessions.

The important boundary is:

AgentHarness = reusable brain
CodingSession = coding-agent environment
TUI = one possible frontend

The core does not know about Textual, Rich, local config paths, slash commands, or rendering. Frontends consume events.

Install

Tau is published on PyPI as tau-ai and installs a tau command. It requires Python 3.12 or newer.

uv tool install tau-ai
tau --version

Don’t have uv? Install with pipx or pip instead:

pipx install tau-ai
# or
python -m pip install tau-ai

If you prefer uv, install it with:

curl -LsSf https://astral.sh/uv/install.sh | sh

For local development:

git clone https://github.com/alejandro-ao/tau.git
cd tau
uv sync --dev
uv run tau --version

Quickstart

Run Tau from the project you want it to work on:

cd my-project
tau

Then type a request and press Enter:

explain what this project does

One-shot print mode is useful for scripts and quick prompts:

tau -p "summarize the architecture"
tau --cwd /path/to/project -p "find the CLI entry point"

Tau needs a model provider. Start Tau and connect one with /login:

tau

/login
/login openai
/login openai-codex
/model

Tau ships with support for OpenAI, Anthropic, OpenAI Codex subscription auth, OpenRouter, Hugging Face, and custom OpenAI-compatible endpoints, including local models. See the providers guide.

The built-in catalog lives in src/tau_coding/data/catalog.toml; add your own providers and models by dropping a ~/.tau/catalog.toml with the same schema — no code changes required.

What Tau can do

• Interactive Textual TUI and non-interactive print mode.
• Built-in coding tools: read, write, edit, and bash.
• Durable JSONL sessions under ~/.tau/sessions/ with resume and branching.
• Slash commands for login, model selection, sessions, compaction, export, theme, and more.
• Project instructions from AGENTS.md, .tau/, and .agents/ resources.
• User skills and prompt templates.
• Context accounting, manual compaction, and optional automatic compaction.
• Provider-neutral event rendering for Rich, plain text, JSON, transcripts, and custom frontends.

Philosophy

Tau follows a few rules:

• Small layers beat magic. Each package has one job and can be read alone.
• Events are the contract. Providers, renderers, the TUI, and custom frontends meet at a typed event stream.
• The core stays portable. The reusable harness does not depend on the CLI, Textual, Rich, or Tau’s file layout.
• Tools are ordinary typed functions. A tool is a schema plus an async executor returning a structured result.
• Sessions are durable and inspectable. History is append-only JSONL; active context can be compacted without rewriting the record.
• Documentation follows implementation. The public docs explain the result; dev-notes/ preserves the phase-by-phase build journal.

Use Tau as a library

from tau_agent import AgentHarness, AgentHarnessConfig

harness = AgentHarness(
    AgentHarnessConfig(
        provider=provider,
        model="my-model",
        system="You are a helpful coding agent.",
        tools=tools,
    )
)

async for event in harness.prompt("Explain this package"):
    print(event)

Because the harness emits events instead of rendering UI directly, the same core can drive the built-in TUI, print mode, or a frontend you build yourself.

Development

See CONTRIBUTING.md for project philosophy, layer boundaries, testing expectations, and pull request guidelines.

uv sync --dev
uv run pytest
uv run ruff check .
uv run ruff format --check .
uv run mypy

Run Tau from the checkout:

uv run tau
uv run tau -p "explain this repo"

Run the Hugo documentation site:

cd website
hugo server -D

Open http://localhost:1313/. Build with hugo --minify.

Documentation

User docs are published at https://twotimespi.dev/ and live in website/content/.

Useful entry points:

• What is Tau?
• Quickstart
• Core concepts
• Architecture overview
• The agent loop & events
• CLI reference

Tau is under active development. The implementation roadmap is tracked in GitHub issue #1.

License

Tau is released under the MIT License.