Codewhale Open source
Rust terminal coding agent that edits files, runs commands, and checks its own work
Codewhale ecosystem
What Codewhale can load, and the skills, subagents and MCP servers in this directory that work with it.
- – Agent Skills
- – Subagents
- – MCP
- – AGENTS.md
- – Plugins
- – Hooks
- – Rules
🧩 Agent skills for Codewhale
Nothing listed yet.
🔌 MCP servers for Codewhale
Nothing listed yet.
What is Codewhale?
What it does
Codewhale is an open-source terminal coding agent, written in Rust, that reads your project, edits files, runs commands, and checks its work using either a hosted model provider or a local model you choose. It positions itself as a fully open alternative to closed CLI coding agents, with the model backend left up to you rather than tied to one vendor.
What is inside
- Approval modes and review mechanisms so you control what the agent is allowed to do before it acts
- Session persistence, so you can save sessions and set durable goals it keeps working toward
- Multi-agent coordination for running more than one agent against a project
- MCP server integration and configurable skills for extending what the agent can do
- A Computer Use plugin for observing and interacting with other applications
- Multiple clients: a terminal TUI, a local web interface, and a VS Code extension
Works with
Connects to hosted LLM providers as well as local inference via Ollama, vLLM, or SGLang, so it is not locked to a single model vendor.
How to install or connect
Documented install paths include a curl-pipe script for macOS/Linux, direct installers for Windows, and packages via npm, Cargo, Docker, and Nix, pointing to codewhale.net for the primary installer.
Maintenance and safety
MIT licensed, with third-party license notices documented. The project shows genuine, organic-looking activity: 41k+ stars, 3.6k forks, over 10,000 commits, 114 open issues and active pull requests, plus clear contribution guidelines. Because it runs commands and edits files locally, use its approval/review modes rather than full-auto mode until you trust it on a given codebase, as with any file-editing agent.
Who should use it
Developers who want a vendor-neutral terminal coding agent that can run against either paid hosted models or fully local/offline models, and who want an editor extension and web UI alongside the CLI.
Source code: Hmbown/Codewhale ★ 41k · +-4 this week · MIT · updated 2026-10-02
Pros
- Model-agnostic: works with hosted APIs or fully local models via Ollama/vLLM/SGLang
- Ships TUI, web UI and a VS Code extension from one core agent
- Genuinely active development history (10k+ commits) rather than inflated-looking stats
Cons
- Newer entrant competing in a crowded terminal-agent space with less brand recognition
- Full capability (multi-agent, computer use) requires careful approval-mode configuration
Codewhale pricing
Open source. Prices change often, so confirm on the official pricing page. See every vibe coding app's pricing side by side.
Codewhale alternatives
All alternatives →Claude Code Paid
Anthropic's agentic coding tool for the terminal, IDE, desktop and web
🔥 Claude Pro billed annually: $17/month instead of $20OpenAI Codex Freemium
OpenAI's coding agent for the terminal, IDE and cloud, included with ChatGPT plans
OpenCode Open source
Open-source terminal coding agent that works with any model provider
Amp Freemium
Frontier coding agent for the terminal and editor, from the makers of Sourcegraph
Orca Open source
An ADE for running fleets of coding agents in parallel worktrees, from desktop or mobile
Qwen Code Open source
Open-source AI coding agent from Alibaba's Qwen team, for terminal, IDE and desktop
Compare Codewhale
Verdict
Codewhale scores 7.5/10 in our terminal coding agents ranking. Model-agnostic: works with hosted APIs or fully local models via Ollama/vLLM/SGLang.