Skip to main content

A Python implementation of a minimalist Pi-style coding-agent harness.

Project description

Tau — a Python coding-agent harness inspired by Pi

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

GitHub · PyPI · Issues


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-biggz and installs a tau command. It requires Python 3.12 or newer.

Install with uv (recommended)

uv tool install tau-biggz
tau --version

Don't have uv? Install it first:

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

Install with pipx

pipx install tau-biggz

Install with pip

python -m pip install tau-biggz

One-command install script

Linux / macOS:

curl -fsSL https://raw.githubusercontent.com/biggs-100/tau-biggz/main/install.sh | sh

Windows (PowerShell):

irm https://raw.githubusercontent.com/biggs-100/tau-biggz/main/install.ps1 | iex

The script detects your Python, installs with pip, and adds tau to your PATH if needed.

Install from source (local development)

git clone https://github.com/biggs-100/tau-biggz.git
cd tau-biggz
uv sync --dev
uv run tau --version

Or install the local checkout as a regular package:

pip install .
# or
uv tool install --reinstall .

Update / Upgrade

From PyPI (latest published version):

# With uv tool
uv tool upgrade tau-biggz

# With pip
python -m pip install --upgrade tau-biggz

# With pipx
pipx upgrade tau-biggz

From source (after git pull):

pip install --upgrade .
# or
uv tool install --reinstall .

The install scripts always pull the latest version, so you can re-run them:

curl -fsSL https://raw.githubusercontent.com/biggs-100/tau-biggz/main/install.sh | sh

Uninstall

# If installed with uv tool
uv tool uninstall tau-biggz

# If installed with pip
python -m pip uninstall tau-biggz

# If installed with pipx
pipx uninstall tau-biggz

All methods remove the tau command and the tau-biggz package from your system. Session history and configuration under ~/.tau/ are preserved — delete that directory manually if you want a full cleanup.

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, trust, 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.
  • --offline flag to skip network calls on startup.
  • --rpc mode for non-Python integrations (JSONL over stdin/stdout).
  • --harness / --list-harnesses for loading and listing agent harnesses.
  • tau models sync to sync model metadata from the model registry.
  • tau package to install, list, and remove community packages.

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 live in website/content/. Build and view them locally:

cd website
hugo server -D

Useful entry points:

Tau is under active development. The implementation roadmap is tracked in GitHub issues.

License

Tau is released under the MIT License.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tau_biggz-0.1.9.tar.gz (774.3 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

tau_biggz-0.1.9-py3-none-any.whl (294.4 kB view details)

Uploaded Python 3

File details

Details for the file tau_biggz-0.1.9.tar.gz.

File metadata

  • Download URL: tau_biggz-0.1.9.tar.gz
  • Upload date:
  • Size: 774.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tau_biggz-0.1.9.tar.gz
Algorithm Hash digest
SHA256 140c59a83babb1bf07e177ffd41700a90f9cf1da7376e8215be45efbda48f7da
MD5 8a4d4b84b9ca36068cff2fa91ccbb7cb
BLAKE2b-256 d6c0145b813141e2fc3f8f7223327103ed1deeae8b88ab5d9064c096708c8ed5

See more details on using hashes here.

File details

Details for the file tau_biggz-0.1.9-py3-none-any.whl.

File metadata

  • Download URL: tau_biggz-0.1.9-py3-none-any.whl
  • Upload date:
  • Size: 294.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.12

File hashes

Hashes for tau_biggz-0.1.9-py3-none-any.whl
Algorithm Hash digest
SHA256 f091cf3a4b2c2374cbc265eabe5ddd44776e32b9575772d0a6befa03b6a13165
MD5 ab3755f33613bf42ff408d07765111d9
BLAKE2b-256 ed2da28395051ebc3acfce467614068c6d5276a66a5f989d80a58a68e567965b

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page