codewhale vs pi
Two of the top projects in Coding agents and AI editors, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
codewhale
Terminal coding agent in Rust that works with 40+ model providers
pi
Terminal coding agent with extensions, skills, and an SDK
Verdict
codewhale ranks higher, 94 to 92. Of the 4 score parts we measure for both, codewhale leads on 2, pi on 1 and 1 is even.
- Adoptionpi leads by 7 points, 98 to 91.
- FreshnessEven at 100.
- Maintenancecodewhale leads by 1 point, 98 to 97: close to even.
- Agent-readycodewhale leads by 40 points, 70 to 30: a wide gap.
Pick codewhale if you are
Developers who want a model-agnostic terminal coding agent with audit trails
- /receipts lists changed files, commands run, web and MCP calls, and approvals
- Plan, Work and Operate modes with Ask, Auto-Review and Full Access permissions
Pick pi if you are
Developers who want a scriptable, customizable terminal coding agent
- Multiple interfaces: interactive CLI, print/JSON mode, RPC and a TypeScript SDK
- Extensions, skills, prompt templates and themes ship as npm or git packages
| What we compare | codewhale | pi |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 91, widely used | 98, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 98, healthy | 97, healthy |
| Agent-ready | 70, partly | 30, minimal |
| Facts from GitHub and the README | ||
| Stars | 41.2k | 119.3k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Nov 2026 | Nov 2026 |
| Last release | Oct 2026 | Oct 2026 |
| Language | Rust | TypeScript |
| Docker | Yes | No |
| GPU | Optional | Not needed |
| arm64 or Apple Silicon | Mentioned | Mentioned |
codewhale
Codewhale is a terminal coding agent that reads a repository, edits files and runs shell commands until a task is done or it needs input. It supports more than 40 built-in providers, any OpenAI-compatible endpoint, and local models through Ollama, vLLM or SGLang, with DeepSeek as the default. It also has a headless exec mode, a local web UI, a PR review command and an ACP server for editors.
Who it is for: Developers who want a model-agnostic terminal coding agent with audit trails
Strengths
- /receipts lists changed files, commands run, web and MCP calls, and approvals
- Plan, Work and Operate modes with Ask, Auto-Review and Full Access permissions
- One engine behind the TUI, exec, local web UI, Runtime API and ACP over stdio
- Reads AGENTS.md; opt-in import of CLAUDE.md and Cursor rules; supports MCP, skills, hooks
Weaknesses
- Telemetry is on by default; aggregate counts are sent until you disable it
- No OS sandbox on Windows, and Full Access disables the sandbox everywhere
- Some features, such as the one-step /undo and terminal workbar, are only in unreleased 0.10.2
- exec --auto defaults to Full Access with no shell sandbox
- GPU optional
- Docker
- Needs Git repository, Provider API key or local runtime (Ollama, vLLM, SGLang), bubblewrap (optional, Linux sandbox)
- Models: DeepSeek, Anthropic, OpenAI, Google, Mistral
pi
Pi is a TypeScript coding agent CLI that runs in your project directory and connects to LLM providers through a login or API key. It is customized with extensions, skills, prompt templates and themes, shared as npm or git packages, and can be driven interactively, in print/JSON mode, over RPC, or through a TypeScript SDK. The monorepo also ships a multi-provider LLM API, an agent runtime and a terminal UI library.
Who it is for: Developers who want a scriptable, customizable terminal coding agent
Strengths
- Multiple interfaces: interactive CLI, print/JSON mode, RPC and a TypeScript SDK
- Extensions, skills, prompt templates and themes ship as npm or git packages
- Core libraries (pi-ai, pi-agent-core, pi-tui) are published as separate packages
- Installer pins dependencies; Nix flake builds on Linux and macOS, ARM64 and x86-64
Weaknesses
- No built-in permission system; runs with the launching user's full permissions
- Sub-agents and plan mode are intentionally omitted and must be added via packages
- Requires Node.js 22.19 or newer
- New contributors' issues and PRs are auto-closed by default
- no GPU
- Needs Node.js 22.19+, LLM provider API key or subscription
- Models: OpenAI, Anthropic, Google
More in Coding agents and AI editors
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.