RunanywhereAI/wally

Profil RunanywhereAI

Dernière activité source enregistrée: 8 octobre 2026 à 09:11

Catalogue SkillsMP mis à jour: 17 octobre 2026 à 00:09

skills collectés: 6

Étoiles GitHub: 1 566
Forks GitHub: 93

README du dépôt

Fichier source du README : README.md

Lire le README source

Afficher le README complet

<p align="center"> <img src="docs/assets/wally.gif" alt="Wally, the RunAnywhere mascot" width="120"> </p> # Wally [![Release](https://img.shields.io/github/v/release/RunanywhereAI/wally?label=release)](https://github.com/RunanywhereAI/wally/releases/latest) ***Wally*** is a command-line tool that connects your coding agent to the model of your choice. With a single command, it opens a coding agent, such as OpenCode, Claude Code, Hermes, OpenClaw, DeepSeek Harness or Prime Agent, already configured for that model, and it installs the agent first if it is missing. You can use a hosted model, such as GLM 5.3 Flash, billed against your RunAnywhere credit, or download an open model and run it on your own machine without an account. Wally can also chat with a model in the terminal and serve it through an OpenAI-compatible API. It runs on macOS, Linux and Windows. **Get started with the [official documentation](https://docs.runanywhere.ai/).** <picture> <source media="(prefers-color-scheme: dark)" srcset="docs/assets/harness-dark.gif"> <img src="docs/assets/harness-light.gif" alt="OpenCode on the hosted GLM model fixing a bug through wally" width="100%"> </picture> ## Install On macOS with Apple Silicon (Intel Macs are not supported) and on Linux with x86-64 or ARM64 and glibc 2.39 or newer (Ubuntu 24.04+, Debian 13+): ```bash curl -fsSL https://raw.githubusercontent.com/RunanywhereAI/wally/main/install.sh | sh ``` On Windows (x64 and ARM64): ```powershell irm https://raw.githubusercontent.com/RunanywhereAI/wally/main/install.ps1 | iex ``` The installer adds wally to your PATH for new terminals. In the terminal you installed from, run the line it prints (`. ~/.zshrc` or similar), or open a new one, before your first `wally` command. On Windows, open a new terminal. ## Quick start Get up and running with a few commands. **Log in:** ```bash wally account login ``` **Open a coding agent on a hosted model:** ```bash wally opencode -m glm-5.3-flash ``` **Or open it on the default model:** ```bash wally opencode ``` The default model is `glm-5.3-flash`. To change it, run `wally models default <model>`. **Get help:** ```bash wally help ``` Learn more about open models in our **[official documentation](https://docs.runanywhere.ai/)**. ## Ask Eve Wally runs the models; Eve makes the calls. `eve` is RunAnywhere's hosted decision model: it scores explicit labels without generating text. Ask yes/no, choice, or ordered score questions: ```bash wally decisions --input "Checkout is blank after Pay" \ --ask "Is this a software bug?" \ --choice "Owner=frontend,payments,account" ``` Use `--json` for response fields plus `request_id` and `http_status` (or an `error` document on failure), or `--request FILE` for the complete typed request shape. `--image FILE` (PNG, JPEG or WebP, up to 8, cloud only; on macOS a HEIC photo is sent as a full-size JPEG, upright and without its EXIF or GPS) asks every question about the images too; each image is billed as prompt tokens once per question, and a model that does not take images refuses the request before anything is billed. Images are sent at full size: the service shrinks each to what the model sees, so a larger photo scores and costs the same. It takes a request of up to 24 MiB with its images (1 MiB outside them), and an image of up to 64 MP as JPEG or 24 MP as PNG or WebP; past those it refuses with HTTP 400 and says which limit. Decision models are refused by `wally run` and the coding tools, which point back here. Eve is also runnable on this machine. Pull a local checkpoint and point `-m` at it; `--local` (or just a local `-m`) scores in-process through the SDK's decision component, `--cloud` forces the hosted path: ```bash wally models pull clef-flash-9b wally decisions --local -m clef-flash-9b \ --input "Checkout is blank after Pay" --ask "Is this a software bug?" ``` Both transports share the request flags, the human rendering and the `--json` document, so the same invocation works locally and hosted. ## Build from source Wally is written in Rust and built with CMake against a prebuilt RunAnywhere C++ desktop kit (not the SDK source tree). [CONTRIBUTING.md](CONTRIBUTING.md) has the steps. ## More - [Releases](https://github.com/RunanywhereAI/wally/releases): every version, with checksums - [Engines and platforms](docs/ENGINES.md): what runs where and how wally picks - [Models](docs/MODELS.md): the full catalog - [Editors and hosted models](docs/EDITORS.md): how each coding agent is wired and where your session lives - [docs.runanywhere.ai](https://docs.runanywhere.ai) - [Discord](https://discord.gg/N359FBbDVd) - [Hugging Face](https://huggingface.co/runanywhere) Licensed under the MIT license. See [LICENSE](./LICENSE).

Chargement du README du dépôt…

Skills dans ce dépôt

classification en attente

skill

métier

description

mis à jour

runanywhere

non classé

Set up and use RunAnywhere Wally from the terminal — install wally, sign in, pick a coding harness, run a model, check spend. Use when the user wants to get started with RunAnywhere or Wally, run a harness like opencode against a hosted or on-device model, or…