The Steward
A guardian that watches your repos overnight, spends intelligence only on what's new, investigates it to a decision, and hands you a short morning brief — not a firehose.
The Steward sits beside your projects. Most of the time it does nothing but watch (cheap, local, no inference). When something genuinely changes — a new error in your logs, a risky commit, a regression — it spins up an isolated worktree, investigates with an LLM, verifies the finding against reality, and either fixes it on a branch or writes it up. In the morning you read one digest.
Status: early access for friends. Linux, WSL2, and macOS (launchd) today. One-liner:
curl -fsSL https://inferroute.ai/steward/install.sh | bashPrefer to see each step?
pipx install the-steward && pipx ensurepath && steward init. See INSTALL.
What it does
- Watches your tracked git repos + their logs locally, on a timer. No inference until something is new.
- Investigates novelty in a throwaway git worktree — never your working tree, never your branches.
- Verifies findings against the real repo (it won't surface a fix for a file that doesn't exist).
- Scrubs secrets out of anything before it leaves your machine for the model.
- Briefs you each morning — read it in the dashboard (
localhost:5057) orsteward review.
Requirements
-
Linux with
systemd --user(or WSL2 with systemd enabled), or macOS withlaunchd— the local watch runs on both. On a Mac the watch/deep-floor/digest install as launchd agents; on a laptop that sleeps,--mode gha(run in the repo's GitHub Actions) is the better choice andsteward initsays so. -
Python ≥ 3.10,
git,tmux, andbash. -
Claude Code — the
claudeCLI is the agent harness the Steward drives to investigate;steward inithard-checks for it. Install: https://claude.com/code -
An inferroute account for the economy lane (the recommended way to run — cheap, always-on compute that keeps the overnight watch affordable):
pipx install 'inferroute>=0.3.28'(0.3.28+ required — it honors the Steward's write-scoping)- Sign up at https://inferroute.ai — early-access friends start with a small $5 credit headstart on their own account; top up with your own credits once you've kicked the tires.
ir login(paste your key) — orir setupfor the guided first-run.
Escape hatch: you can instead bring your own Anthropic/Claude key (
ir anthropic/ BYO), but the economy lane is what makes always-on watching cheap, so it's the default.
Install
One line (macOS + Linux) — installs everything isolated with pipx, offers anything system-level, guides your key, and opens the onboarding dashboard:
curl -fsSL https://inferroute.ai/steward/install.sh | bash
Step by step, if you'd rather. The package is on PyPI (proprietary, licensed for evaluation — see License):
pipx install the-steward # or: pip install the-steward into a venv
pipx ensurepath # first pipx package? this puts `steward` on your PATH (then open a new shell)
steward init # preflight + economy on-ramp + opens your local dashboard
If steward says "command not found", that's the PATH step above — run pipx ensurepath and open a
new terminal; the tool is installed, your shell just can't see ~/.local/bin yet.
Update any time with pipx upgrade the-steward.
steward init runs a preflight (checks your tools + that your inferroute economy login is funded, with
the exact fix for anything missing), then installs your local dashboard and points you to it.
Pick your projects in the dashboard — http://localhost:5057 — where you discover repos, see each
one's fit (evaluated for you), and start watching the ones you want. That's the main way to drive it.
steward review # the morning digest (auto-runs each morning; run any time)
steward status <repo> # a repo's health from the terminal
# headless / no browser? pick from the terminal instead:
steward discover # list watchable repos
steward track <repo> # watch one · steward untrack <repo> to stop · steward onboard for a TUI
No always-on machine? Run it in your repo's own GitHub Actions
Local mode assumes a box that stays on. If your project deploys elsewhere and your machine sleeps,
a repo can instead run the whole loop in its own GitHub Actions — the watch is a scheduled
workflow, investigation runs in your repo's real CI, results live on a steward-state branch, and
verified fixes arrive as pull requests gated by your checks.
steward track <repo> --mode gha # guided install: preflight → config → workflow
steward track <repo> --mode gha --dry # print the full plan first, change nothing
The install tells you the steps only you can do (set the inference credential as a repo secret, commit and push the workflow it writes, dispatch the first run). Notes: your repo should be private — the install writes Steward runner files into it, and shipping logs to a public repo is refused; per-repo Actions minutes are consumed on your account; and the schedule is best-effort (GitHub cron), so think hours, not seconds.
Privacy
- The watch loop is fully local — zero inference, zero egress.
- When an investigation runs, context is scrubbed of secrets before it reaches the model.
- Fleet telemetry (run/turn metadata to improve the tuning loops) is configurable:
stewardshows the setting at setup; turn it off to ship nothing. (See INSTALL for the current default and exactly what's sent.)
What it is NOT (yet)
- Not open source — it's on PyPI, but under a proprietary evaluation license: run it on your own machines, but don't redistribute, fork, or use it commercially.
- Not an OS-level sandbox — point it at your own repos, not untrusted code. Agents run in throwaway worktrees, but a misbehaving agent with shell access could still read files in your home dir.
License
Proprietary — © 2026 Henry Declety. Licensed to early-access users for evaluation only: you may run it on your own machines, but not redistribute, fork, or use it commercially. See LICENSE.
Metadata
Release files for the-steward 0.2.7
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| the_steward-0.2.7.tar.gz | 1.1 MB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| the_steward-0.2.7-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 2.4 MB
Release files / the_steward-0.2.7.tar.gz
| Download URL | the_steward-0.2.7.tar.gz |
|---|---|
| Size | 1.1 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
eed1ca96e63edcc00f3923d45adcfef1cd1c6445aecdee6727bfc8e9000e8c1a
|
|
BLAKE2b-256 checksum How to use checksums |
2225e40dfbc3d4c9be464339d7d4f0c62c06800d35cc471bd6758866ca0a02e2
|
| 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 Aug 21, 2026.
Transparency logRelease files / the_steward-0.2.7-py3-none-any.whl
| Download URL | the_steward-0.2.7-py3-none-any.whl |
|---|---|
| Size | 1.2 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
8c741a9ce136355a1713521a6f88820ff12b37d1a29fb8c57a3aac25107c0314
|
|
BLAKE2b-256 checksum How to use checksums |
a9a1123ada2e32713049b9c4da1bd60dead9a0633cc58f6daecd67e3affad8f2
|
| 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 Aug 21, 2026.
Transparency log