Open-source Rust coding agent for terminal, supports many models and providers.
CodeWhale is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
gh repo view Hmbown/CodeWhale --webOpen the official repository or website.
Check the README for package manager, auth, and platform requirements.
Try it in a small test task inside your agent workflow.
Repository setup guidance
Strong trust signals; still review the README and permissions before production use.
Last commit was about 24 days ago.
40828 GitHub stars indicate community interest.
156 open issues signal maintenance load.
MIT license detected.
3 security/trust notes recorded.
Setup difficulty is 2/5.
Run large language models locally with a simple CLI. Supports Llama, Mistral, Gemma, and 100+ models with one command.
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
The leading open-source AI code assistant for VS Code and JetBrains. Connect any model, customize your workflow.
Anthropic's official CLI agent for coding. Claude-powered terminal agent that reads, writes, and refactors entire codebases.
CodeWhale is a tool that runs in your terminal and helps you code. You give it a task, and it reads your code, edits files, runs commands, and checks its own work. You can choose different AI models for different roles, and it works with many providers like DeepSeek, OpenAI, and Anthropic.
CodeWhale is an open-source, community-driven agent harness written in Rust. It started as a native experience for DeepSeek but has grown to support a wide range of models and providers, including open models, hosted or local. The key differentiator is that you can assign different models to different roles in a 'fleet', allowing a cheap fast model to direct an expensive reasoning model, or a GLM builder to work with a Kimi reviewer. It offers an interactive TUI, a headless 'exec' mode for scripts and CI, and a local web client. Features include switching models mid-task with '/model', building teams with '/fleet', undoing turns, and restoring workspace snapshots. It supports 30+ providers, including vLLM, SGLang, and Ollama, and is licensed under MIT.
40,828
Stars
3,530
Forks
156
Issues
MIT
License
Open-source Rust coding agent for terminal, supports many models and providers.
Developers who want an AI coding assistant in the terminal., Teams looking for a customizable, multi-model agent harness., Open-source contributors interested in community-driven tools.
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
The tool can execute shell commands and edit files, so it may introduce unintended changes if not supervised. When using cloud-based models, code snippets may be sent to third-party providers; ensure compliance with data policies.
Similar or complementary options to evaluate include Ollama, anthropic-skills, Continue.
Aug 20, 2026