Skip to main content

Local-first orchestrator for AI coding agents — one window over your fleet

Project description

Rubberduck

Shadow companion across multiple agents and sessions — a second brain looking over your shoulder.

Local-first orchestrator for AI coding agents. Launches agents (Claude Code, Codex, any CLI agent) into isolated git worktrees, supervises them, lets you fork a running session into a tree of parallel attempts, and keeps durable history with an intention → outcome summary per session.

Design: rubberduck-design.md. Built Act by Act (0–10 complete).

Run

pip install -e .
rubberduck serve                       # http://127.0.0.1:4200
# in another shell:
rubberduck launch "claude" --cwd ~/myrepo --prompt "add a healthcheck"
rubberduck snapshot                    # bundle active sessions

cd web && npm install && npm run dev   # dashboard (proxies to the server)

Launch on a repo to get an isolated git worktree per session; fork a session to branch it; sessions are tracked live and persisted with an intention → outcome summary. Runtimes: generic (any CLI), claude-code (richest — hook events + JSONL transcript), codex.

Develop

python3 -m venv .venv && . .venv/bin/activate
pip install -e ".[dev]"

ruff check src tests        # lint
black --check src tests scripts
mypy                        # types (strict)
pytest                      # unit + runtime tests
python scripts/slop_check.py

cd web && npm install
npm run lint && npm run typecheck && npm run build

State lives in ~/.rubberduck/ (override with RUBBERDUCK_HOME).

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rubberduckhq-0.1.0.tar.gz (93.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

rubberduckhq-0.1.0-py3-none-any.whl (100.5 kB view details)

Uploaded Python 3

File details

Details for the file rubberduckhq-0.1.0.tar.gz.

File metadata

  • Download URL: rubberduckhq-0.1.0.tar.gz
  • Upload date:
  • Size: 93.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.4

File hashes

Hashes for rubberduckhq-0.1.0.tar.gz
Algorithm Hash digest
SHA256 3a2976b67e264c2fe5d42754442c477de46846ade00629229d92fed4d28ff27a
MD5 e2bb00af547f2a1c1657107e43c83208
BLAKE2b-256 fa04489df5bbbd7a8e6b54819760a24cf918a47b2c4a17c710c8ef2d9d566fd5

See more details on using hashes here.

File details

Details for the file rubberduckhq-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: rubberduckhq-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 100.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.4

File hashes

Hashes for rubberduckhq-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 badd7609fcdf21f136dd3381977282a08d9795dfb387ad9af2ef138baf8f5c4e
MD5 dea75b9a77b1ba57e3aaad822eeeab69
BLAKE2b-256 bebbecea94a92e611bfd0d83a6a80f75f0e3cab13815951dec992c7120e497a0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page