via - GitLite

KO | EN

gitlite — search

#react-native #redis #web #artificial-intelligence #cloud-native #computer-vision #tensorflow #openai #video #macos

via

(★ 9)

No description available.

파일 탐색기

ZIP 다운로드

- bowl_plate.md
- bowl_plate_min.md
- open_drawer.md
- open_drawer_min.md
- rainbow_min.md
- t_block_min.md
- turn_stove.md
- turn_stove_min.md
- LIBERO
- - franka.obj
  - franka_closed.obj
  - robotiq.obj
  - robotiq_closed.obj
  - template_index.html
- agent_common.py
- build_video_index.py
- claude_harness.py
- codex_harness.py
- episode_recorder.py
- harness.py
- mcp_server.py
- rainbow_env.py
- record_sim.py
- robot_utils.py
- run_eval.py
- serve.py
- sim_env.py
- t_block_env.py
- utils.py
.gitignore
.gitmodules
.mcp.json
.python-version
CLAUDE.md
pyproject.toml
README.md
set_env.sh
uv.lock

# CDN으로 사용하기

jsDelivr

jsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.

버전

파일

링크

예시

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

VIA lets a general-purpose coding agent control a simulated robot through a browser-based
3D interface and MCP tools.

## Setup

We use uv to manage packages. Install [uv](https://docs.astral.sh/uv/) if you haven't.

### Clone and install dependencies

```shell
git clone https://github.com/hengyuan-hu/via.git
cd via
git submodule update --init --recursive           # LIBERO

uv venv --python 3.10 --prompt via .venv
uv sync
.venv/bin/python -m playwright install chromium    # browser for the MCP server (one-time)
```

`uv sync` installs everything in `uv.lock`, including the subset of LIBERO's runtime deps
declared in `pyproject.toml` (`bddl`, `gym`, `future`, `easydict`, `cloudpickle`).

`torch`/`torchvision` come from PyTorch's own indexes (`[tool.uv.sources]`), so one lock works
on both platforms — CUDA 12.1 wheels on Linux, CPU/MPS on macOS. On a newer NVIDIA driver,
bump the `pytorch-cu121` index in `pyproject.toml` to `cu124`.

### LIBERO

LIBERO is vendored as a git submodule at `third_party/LIBERO` and put on `PYTHONPATH`;
`set_env.sh` handles this. On first import it writes `~/.libero/config.yaml` via an interactive prompt.
Seed it once:

```shell
source set_env.sh
echo N | python -c "import libero.libero"
```

## Usage

Note: `source set_env.sh` once per shell
(activates `.venv`, sets `PYTHONPATH` for the repo root and LIBERO).

Start an interactive run:

```shell
# in one terminal
python -m via.record_sim --task stack

# in another terminal
claude  # or codex
```

Run an eval with multiple seeds:

```shell
# -j3 means running 3 seeds in parallel
python -m via.run_eval stack-opus-dev -j3
```

Evaluation runs also require the CLI for the configured harness (`claude` or `codex`) to be
installed and authenticated. The MCP server (`via/mcp_server.py`) is launched automatically
from the same `.venv` via `.mcp.json`; you do not run it by hand.

## Repo layout notes

- `via/` — the active code: the flat `via.*` package (`record_sim`, `sim_env`, `run_eval`, `mcp_server`, and their helpers), plus `via/UI/` for the browser assets.
- `prompts/` — per-task instruction files referenced by the evaluations in `run_eval`.
- `pyproject.toml` / `uv.lock` — the single 3.10 environment (sim stack + MCP server).
- `set_env.sh` — activates `.venv` and sets `PYTHONPATH` (repo root + LIBERO submodule).
- `third_party/LIBERO` — LIBERO submodule (on `PYTHONPATH`, not pip-installed).