Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A Python port of Pi’s minimalist coding agent.
| Date | Stars |
|---|---|
| 2026-07-31 | 2129 |
| 2026-08-01 | 2144 |
| 2026-08-02 | 2157 |
| 2026-08-03 | 2166 |
| 2026-08-04 | 2177 |
| 2026-08-05 | 2208 |
| 2026-08-06 | 2223 |
Today
+15 stars today
This week
— stars this week
This month
— stars this month
Momentum
120.0
growth rate 0.00%/day
<p align="center"> <img src="docs/assets/tau-header.svg" alt="Tau — a Python coding-agent harness inspired by Pi" width="100%" /> </p> <p align="center"> <strong>A small, readable terminal coding agent — and a working example of how coding agents are built.</strong> </p> <p align="center"> <a href="https://twotimespi.dev/">Documentation</a> · <a href="https://twotimespi.dev/quickstart/">Quickstart</a> · <a href="https://twotimespi.dev/internals/architecture/">Architecture</a> · <a href="https://pypi.org/project/tau-ai/">PyPI</a> · <a href="https://github.com/huggingface/tau/issues/1">Roadmap</a> </p> --- ## 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. ```text 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: ```text 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. The recommended installers use [`uv`](https://docs.astral.sh/uv/) and install it first when necessary. macOS and Linux: ```bash curl -LsSf https://twotimespi.dev/install.sh | sh ``` Windows PowerShell: ```powershell irm https://twotimespi.dev/install.ps1 | iex ``` The installers do not use `sudo`. They announce before installing `uv`, install Tau in an isolated tool environment, verify `tau --version`, and report if a shell restart is needed. You can [inspect the shell installer](https://twotimespi.dev/install.sh) or [PowerShell installer](https://twotimespi.dev/install.ps1) before running it. Already have a package manager? Install Tau directly: ```bash uv tool install tau-ai # or pipx install tau-ai # or python -m pip install tau-ai ``` Then check it worked: ```bash tau --version ``` Tau is also available on [conda-forge](https://conda-forge.org), and can be installed using [pixi](https://pixi.prefix.dev/latest/#installation): ```bash pixi global install tau-ai ``` Upgrade a normal installation with: ```bash tau update ``` For local development: ```bash git clone https://github.com/huggingface/tau.git cd tau uv sync --dev uv run tau --version ``` To make the checkout-backed command available globally, install it as an editable tool: ```bash uv tool install --editable --force . ``` Run that command again after `git pull`. Editable installs expose source-code changes immediately, but the tool environment's package metadata, dependencies, and entry points are only refreshed when uv reinstalls the tool. Without the refresh, `tau --version` can still show the version from the previous install. ## Quickstart Run Tau from the project you want it to work on: ```bash cd my-project tau ``` Then type a request and press **Enter**: ```text explain what this project does ``` One-shot print mode is useful for scripts and quick prompts: ```bash 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`: ```bash tau ``` ```text /login /login openai /login openai-codex /model ``` Tau ships with support for OpenAI, Anthro
Excerpt of 7,432 characters
Read on GitHub
607
12
pablo
5
4
4
3
2
2
2
1
1
1
1
luo jiyin
1
1
Julien Chaumond · @huggingface · United States
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:77cced4690fd91d3, desc:coding agent