Skip to main content

Grove

Grove

Grove is a software factory for the coding agents you already use. Give each task a workspace. Guide the work with files and diagrams. Follow delivery from ticket to trace.

CI Docs Python 3.12+ License: MIT

Supports

Claude Code  Codex  OpenCode  Linear  GitHub  Gitea

🌳 Overview

  • Writing the code stopped being the slow part. Deciding what to build did. More agents can build in parallel but shared checkouts cause conflicts and laptops limit capacity. Grove turns the agents you already use into a software factory. Guide each task from ticket to delivery.
  • Give each task its own workspace. Each agent gets its own worktree and branch in a separate window. Agents report progress phases for the workspace and each attached ticket independently. You can see what is being planned, built or verified across the fleet.
  • Choose how each agent runs. Run agents on your host with the environment they normally inherit. Or use a container defined by your repository's .devcontainer/. It provides separate services and ports with resource limits. Use that isolation for runs with agent permission checks disabled.
  • Choose where the work runs. Tests, builds and scripts compete for CPU and memory across concurrent workspaces. Move those workloads off your laptop when it slows down. Reuse the container configuration on a shared team machine or serverless cloud infrastructure.
  • Let the tracker start the work. Assign an issue and Grove starts a workspace for it. Progress returns to the same ticket. Follow the task where you defined it.
  • Show it instead of describing it. Mark up a screenshot or collaborate with the agent on a diagram. Approve the diagram or mockup and attach it to a ticket. Then coordinate your fleet around it.

✨ Features

Terminal UI and CLI

Use the terminal UI to see which agents need you. The CLI autocompletes commands and live workspace names. People and agents can launch, pause and resume work from the shell.

Docs → · CLI →

The Grove TUI: a project-scoped workspace list with a live agent peek rail showing the summary, recent commits, and transcript

The whole fleet in your browser

Follow headless agent sessions from any browser. Review the transcript beside the branch and diff. Upload files or annotate screenshots to show what needs changing. Edit a draw.io diagram together without leaving the workspace.

Docs →

Grove's web dashboard cycling through seven views: the launch composer, the host-wide session catalog, one workspace with its agent transcript beside the work panel, an image being annotated beside the transcript, an architecture diagram the agent drew filling the work pane, the usage audit, and the attention-sorted fleet grid

Containerized agents

Run each agent in a containerized sandbox for its task. Separate files and services keep parallel work from colliding. Set CPU and memory limits per task. Scale each agent container independently on serverless cloud platforms as tasks arrive.

Docs →

Grove creating a containerized workspace: the create modal selects the Container runtime after finding the project's .devcontainer/devcontainer.json, then Claude Code runs inside the container behind a DEV CONTAINER statusline reporting the container user, the branch, and the container's own CPU and memory limits

Drive Grove from any agent

An orchestrator uses Grove's MCP tools to launch agents, track progress and steer the fleet. Worker agents use the mailbox to discover peers and exchange messages as tasks run in parallel. They can coordinate without sharing a checkout.

Docs →

Claude Code listing Grove's MCP tools: create, list, peek, pause, and steer workspaces

Status lands on the ticket

Every ticket a Grove workspace works gets one comment, rewritten in place as the work moves. The phase, the checklist and the latest commit stay current where your team already looks. Nobody has to ask, and there is no second dashboard to check.

Docs →

Grove's status comment on a tracker issue, showing a table of phase, checklist, branch and commit above a six step progress diagram running from Scope to Handoff

Audit and tune the whole fleet

Trace each agent turn's work and cost. Rate the answer in Grove with a thumb. Add reasons or a note without leaving the transcript. That feedback stays on its Langfuse trace. Your team can review patterns and calibrate automated LLM judges against human scores.

Docs →

One Claude Code turn as a Langfuse trace: an agent-turn root with cost and duration, nested model generations, and a span for each Bash, Skill, WebFetch and WebSearch call, with GenAI and Grove attributes on the selected span

Also in the box:

  • Branch-aware lifecycle. Create, pause, resume, respawn, and kill. Pause keeps the branch and drops the worktree. Kill deletes only branches Grove created, never remotes.
  • Configuration cascade. A committed .grove/config.json sets the team baseline. Six layers let each developer override locally without touching it.
  • Per-agent model selection. Each agent exposes its own model catalog. Pick the model per workspace: a cheap one for scaffolding, a strong one for the hard refactor, side by side.
  • Session recovery. Grove pane-verifies each agent session and re-adopts it across daemon restarts and a different user attaching. A stale pointer remaps to the recovered session in a click.
  • Ticket providers. Attach a GitHub, Gitea or Linear issue or pull request to a workspace, or let Grove read the link straight off the branch name so it follows the branch.
  • Push notifications. Get pinged when an agent finishes a turn or needs you.
  • Attachments and annotation. Paste a screenshot or attach a file in either composer, draw on the image before it goes, and the agent is handed a path inside its own worktree.
  • Diagram collaboration. A person and an agent edit one draw.io file with revision checks. Quick UI mockups and architecture specs are approved as a picture before code exists.
  • Subscription windows. Track each plan's usage, reset and burn rate. See which limit comes first.
  • Usage trends. Track a year's daily tokens, model cost and latency. See where agents spend time across projects.
  • Local by default. The audit reads local transcripts. Export is optional. Prompt bodies stay off until you enable them.

🚀 Get started

Grove needs git and tmux. It publishes to PyPI as grove-factory, and one install carries everything: the TUI, the CLI, the daemon, the MCP server and the web dashboard. With uv:

uv tool install grove-factory

cd path/to/your/repo
grove config init               # scaffold .grove/config.json
grove                           # launch the TUI
uv tool upgrade grove-factory   # pull the latest release later

Try it without installing with uvx --from grove-factory grove. The web dashboard is grove daemon serve plus grove web, and brings its own Node, so nothing else to install. No uv? pipx install grove-factory works too. Releases are cut on GitHub and land on PyPI minutes later. See Get Started for prerequisites and every install path.

🤖 Let an AI agent configure Grove for you

Configuration has a few layers and many knobs, so you do not have to write it by hand. Hand the prompt below to Claude Code, Codex or any coding agent. It reads Grove's config skill and sets things up with you, then verifies every field against the version you actually installed.

Read https://raw.githubusercontent.com/bearlike/Grove/current/src/grove/skills/configuring-grove/SKILL.md

It is the skill for configuring Grove, a software factory for coding agents.
It covers the six-layer cascade, agents, init scripts, containers and ticket
providers.

Help me write my Grove user and project config, then verify every field
against my installed version with `grove config schema --stdout`.

🤖 Skills for Claude Code

claude plugin marketplace add https://github.com/bearlike/Grove.git
Teach your agent to drive Grove and to configure it for a project

Grove's skills ship from the repository that implements them, so they never drift from the code. They are the same files grove skills install copies into a tool's skills directory; grove skills list --details is the full roster.

Skill For
using-grove Driving a fleet from outside. CLI verbs, MCP tool ids, ticket and PR linking
leading-in-grove Leading a fleet of teammates toward one deliverable. Splitting the work, check-ins, verification, teardown
working-in-grove The agent inside a workspace, reporting phase and keeping attached tickets current
configuring-grove The config cascade, agents, init scripts, containers, ticket providers
reinstalling-grove When an update did not take
collaborating-on-diagrams Editing a .drawio file together with a person, through managed reads and writes
mocking-up-in-grove Getting a frontend mockup approved as a picture before any code exists

📚 Documentation

Full documentation lives at https://factory.mewbo.com/.

Section Covers
Get Started Install, prerequisites, first run, verify.
Configure Project setup, agents, init scripts, configuration reference.
Use TUI tour, CLI, web IDE, authentication, daily workflow.
Capabilities Lifecycle, branch provenance, live activity, status semantics, configuration cascade.
Develop Architecture, public API, engineering principles, contributing, design system.
Troubleshooting Symptom → cause → fix for common failures.

🤝 Contributing

Bugs and feature requests on the issue tracker. For development setup, lint/test commands, and PR conventions, see the contributing guide and CLAUDE.md.

📄 License

MIT © Krishna Alagiri.

Metadata

Release files for grove-factory 0.0.11

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for grove-factory 0.0.11
File Size Uploaded
grove_factory-0.0.11.tar.gz 1.9 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for grove-factory 0.0.11
File Interpreter ABI Platform
grove_factory-0.0.11-py3-none-any.whl Python 3 none any Details

Total release size: 16.0 MB

Release files / grove_factory-0.0.11.tar.gz

Download URL grove_factory-0.0.11.tar.gz
Size 1.9 MB
Tags Source
SHA-256 checksum
How to use checksums
27ddee30a622ad4b14d6def48fb9288dfd744b9da22921152699aba759bb579e
BLAKE2b-256 checksum
How to use checksums
d349bdc1d1d9eee1a7ace2691600ee6424e259983ad1b24ccda897b89e572439
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 30, 2026.

Transparency log

Release files / grove_factory-0.0.11-py3-none-any.whl

Download URL grove_factory-0.0.11-py3-none-any.whl
Size 14.1 MB
Tags Python 3
SHA-256 checksum
How to use checksums
66c9d8ccc90f5a63031b2f2c2468a84261a7cf84a433cc07acf41bd49d854593
BLAKE2b-256 checksum
How to use checksums
bd1f10d11d663fd845a78b6dd2b5365e73ceda26d6f78bbffbb850ae6c486ba5
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.14

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Sep 30, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.0.11 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page