Codewhale
by Hmbown
Runs a terminal coding agent with plan and work modes, approval levels, durable goals, agent teams, and MCP, using hosted or local models through Ollama, vLLM, or SGLang.
Skills
Plan And Work Modes
Explores read-only in plan mode, edits in work mode, and lets you pick Ask, Auto-Review, or Full Access approval levels.
Headless Exec Runs
Runs a task non-interactively with codewhale exec for scripts and CI, or opens the same runtime in a local web client.
Agent Teams
Coordinates teams of agents with roles kept as readable files in the project, without dumping their instructions into your transcript.
GitHub PR Review
Reviews pull requests from a GitHub Action that runs codewhale review on a pinned release, authorized by a Codewhale account key.
Undo And Restore
Recovers workspace changes with /undo and /restore, and saves sessions with a durable /goal so long work can resume.
Related Agents
BitFun
Runs an open-source desktop and terminal coding agent that plans, edits, tests, and reviews changes inside real Git rep…
AgentOps for Apify Builders Bundle
Apify actor bundle for agent builders: normalize run traces for QA, control costs, and guard tool calls with a firewall…
OpenSandbox
Runs AI-agent workloads in isolated Docker or Kubernetes sandboxes, exposing sandbox lifecycle, command, filesystem, an…
Qwen Code
Runs an open-source coding agent in the terminal with subagents, agent teams, hooks, skills, plan mode and MCP, switcha…