At a glance
An MIT-licensed terminal coding harness with an adaptive tool loop, interactive and headless modes, persistent memory, branchable and resumable session trees, MCP and skills, local-model routes, optional OS or external sandboxes, and ledger-backed multi-worker fleets.
Good choice if
- Terminal or CI workflows that need the same tools across hosted, local, and OpenAI-compatible model routes
- Teams that want explicit planning, approval, repository-law, and optional OS-sandbox controls
- Longer tasks that benefit from persistent memory, turn restore, and ledger-backed multi-worker resume
Check before choosing
- Local execution is host-first: macOS Seatbelt depends on a successful probe, Linux bubblewrap is opt-in, Windows has no advertised local OS sandbox, and unavailable wrappers fall back unless external policy blocks the run
- The strongest approval and lifecycle-hook controls are configurable; Full Access weakens prompts, and TUI hooks do not fire for codewhale exec or other CLI subcommands
- The loopback web client is a local control surface rather than remote managed execution, and its one-time token does not turn it into a multi-user service
See 4 more considerations
- Fleet workers reuse headless CodeWhale and an append-only ledger; this establishes coordination and resume, not independent quality or task-success evidence
- CodeWhale 0.9.5 removes the default 100-step ceiling from headless runs and makes automatic goal continuation unlimited unless configured, so unattended workloads still require explicit turn, time, spend, credential, and network bounds
- Fresh 0.9.6 installs enable anonymous aggregate usage counting after a first-run modal; prior opt-outs remain off and the release documents an immediate persistent opt-out
- Repository eval and acceptance assets are project-owned development evidence, so no product benchmark score is imported