Skip to main content

Grove: your team's agents, one software factory. Works with Claude Code, Codex, OpenCode, Linear, GitHub and Gitea.

Run your coding agents as a software factory, each task in its own workspace and tracked from ticket to trace.

CI Docs Python 3.12+ License: MIT

Supports Claude Code · Codex · OpenCode · Linear · GitHub · Gitea · Langfuse

🌳 Overview

  • Coding is no longer the slow part. Deciding what to build is. Parallel agents hit checkout conflicts and laptop limits. Grove turns your agents into a software factory. Turn tickets into outcomes.
  • Give each task its own workspace. Each agent gets a worktree and branch. Agents report phases for their workspace and each attached ticket. See what's planned, built or verified across the fleet.
  • Choose how each agent runs. Run agents in their usual host environment or a container defined by your repository's .devcontainer/. Containers provide separate services and ports with resource limits.
  • Choose where the work runs. Concurrent tests and builds compete for CPU and memory. Reuse your container configuration on a shared team machine or serverless cloud to free your laptop.
  • Let the tracker start the work. Assign an issue and Grove starts its workspace. Progress returns to the same ticket. Follow the task where you defined it.
  • Show it instead of describing it. Annotate a screenshot or draw a diagram with your agent. Approve the diagram or mockup and attach it to a ticket to coordinate your fleet.

✨ 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

Every agent turn becomes a Langfuse trace. A small local decision model labels each observation, such as why a shell command ran, with a confidence score. Add thumbs up or down from Grove, then calibrate the labels against human judgement.

Docs →

Langfuse Scores view of evaluator scores beside an agent-turn trace whose Bash spans each carry a bash_purpose label such as explore_code or edit_files, with the selected call's command open

Also in the box:

🚀 Get started

Needs git and tmux. Install with uv:

uv tool install grove-factory

cd path/to/your/repo
grove config init               # scaffold .grove/config.json
grove                           # launch the TUI
  • Try it first: uvx --from grove-factory grove
  • No uv? pipx install grove-factory, or see every install path.
🤖 Let an AI agent configure Grove for you

Hand this prompt to Claude Code, Codex or any coding agent. It configures Grove with you and checks every field against your installed version.

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

Share bugs and ideas on the issue tracker, or contribute using the contributing guide and CLAUDE.md.

📄 License

MIT © Krishna Alagiri.

Metadata

Release files for grove-factory 0.0.12

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 0.0.12
File Size Uploaded
grove_factory-0.0.12.tar.gz 1.9 MB Details

Built distribution (wheel)

Table of built distributions (wheels) for grove-factory 0.0.12
File Interpreter ABI Platform
grove_factory-0.0.12-py3-none-any.whl Python 3 none any Details

Total release size: 16.1 MB

Release files / grove_factory-0.0.12.tar.gz

Download URL grove_factory-0.0.12.tar.gz
Size 1.9 MB
Tags Source
SHA-256 checksum
How to use checksums
a7d07fbc6c513ef00c4a9ef0d7ca7fe89a3ab6faa3ffd3746b9bac3f606b938b
BLAKE2b-256 checksum
How to use checksums
fd51967d2831dfed5401d804e6bb88a2dc54b2935eb506164ce3b97918ae824b
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 Oct 2, 2026.

Transparency log

Release files / grove_factory-0.0.12-py3-none-any.whl

Download URL grove_factory-0.0.12-py3-none-any.whl
Size 14.2 MB
Tags Python 3
SHA-256 checksum
How to use checksums
a795cb840565350a9a3fe27708bf30fca647e2523ea12e4652e5f688e3ce692e
BLAKE2b-256 checksum
How to use checksums
07072f4902a5045444d765a9265308fb772436ce5437c088babdfd71638804cc
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 Oct 2, 2026.

Transparency log

Release history Release notifications | RSS feed

This release

0.0.12 This release

2 release files

0.0.11

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