agentleFS
OpenAdaptAIOpenAdaptAI/OpenAdapt/CLAUDE.md

OpenAdapt

CLAUDE.md1.8k starsChanged 14 days agoMITView on GitHub

This public repository is the launcher/meta-package and stable community entry point for OpenAdapt. It owns pip install openadapt, the unified openadapt CLI, release compatibility, and launcher packaging. The compiler and governed runtime (openadapt-flow) live in this monorepo under packages/flow, next to packages/agent, packages/types and packages/capture. The standalone openadapt-flow, openadapt-agent and openadapt-types repositories are frozen; changes go here. CAPABILITIES.md is the map of what exists and how proven it is; update it in the same pull request as any capability change.…

  • Installs packages

We split this CLAUDE.md into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Very specific:

    Read the workspace AGENTS.md and current STATUS.md when available.

    line 26
  2. Distinctive:

    Read README.md and CONTRIBUTING.md.

    line 28
  3. Very specific:

    Keep public installation centered on pip install openadapt and openadapt ....

    line 29
  4. Distinctive:

    Use a focused branch and pull request for every change.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 25,680 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Claude Code Guidelines for OpenAdapt

Repository role

This public repository is the launcher/meta-package and stable community entry point for OpenAdapt. It owns pip install openadapt, the unified openadapt CLI, release compatibility, and launcher packaging.

The compiler and governed runtime (openadapt-flow) live in this monorepo under packages/flow, next to packages/agent, packages/types and packages/capture. The standalone openadapt-flow, openadapt-agent and openadapt-types repositories are frozen; changes go here. CAPABILITIES.md is the map of what exists and how proven it is; update it in the same pull request as any capability change. For a new openadapt-flow command, add packages/flow/docs/commands/<group>/<verb>.md and run python scripts/build_command_map.py (a test enforces it). Refresh the review brief with python scripts/build_llms_full.py when you change README.md, CAPABILITIES.md, SURFACES.md, LIMITS.md or the flow CHANGELOG, and always before a release.

The current product compiles demonstrated GUI workflows into deterministic, locally executable programs. Healthy runs make no model calls. Training, retrieval, and general computer-use agents are separate research surfaces.

Before changing the repository

  1. Read the workspace AGENTS.md and current STATUS.md when available.
  2. Fetch origin and base findings and changes on fresh origin/main.
  3. Read README.md and CONTRIBUTING.md.
  4. Keep public installation centered on pip install openadapt and openadapt ...; openadapt-flow remains the contributor/engine package.
  5. Preserve local-first use, fail-closed execution, and the open-core boundary.

Repository layout

  • openadapt/: launcher package and unified CLI
  • packages/: the product packages, each folded in with its history (flow, agent, types, capture, privacy, desktop, tray; see docs/monorepo/), and program-graph, the program map Desktop, Cloud and the website share
  • tests/: launcher, integration-seam, and release-artifact tests
  • legacy/: frozen pre-1.0 monolith
  • docs/: noncanonical historical repository documentation; docs.openadapt.ai is maintained in OpenAdaptAI/openadapt-ops
  • .github/: CI, security, dependency, and release workflows

Development and delivery

python -m pip install -e '.[dev]'
pytest
ruff check openadapt tests

Use a focused branch and pull request for every change. Do not push directly to main. Releases are performed only through the reviewed GitHub Actions release workflow after explicit authorization; never publish from a development task.

Download now (ZIP)

Trending

Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data

Week of Aug 30: 0 new projectsWeek of Sep 6: 0 new projectsWeek of Sep 13: 0 new projectsWeek of Sep 20: 0 new projectsWeek of Sep 27: 0 new projectsWeek of Oct 4: 0 new projectsWeek of Oct 11: 0 new projectsWeek of Oct 18: 0 new projects
Aug 2026Sep 2026Oct 2026
New projects taking a version of this file each week, over the 8 weeks our latest run read: only 0 in all, so this is a hint, not a trend.

Who's talking about OpenAdaptAI/OpenAdapt

The biggest 5 of 27 mentions linking to the repository that our crawl found. Each line is their own headline.

See all 27

Talked about on GitHub and Hacker News (27 times).

On GitHub · 21

16 more on GitHub

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.