ENGINEERING
Auto-pin or revert HF models that drift off the license allowlist
Continuously checks tracked HuggingFace models against an approved-license allowlist.
How it runs
The automated pipeline, trigger to output.
- TriggerScheduled allowlist check fires
- ActionLoad tracked models and last-good revisionsPostgres
- ActionFetch current license per model cardHugging Face
- LogicFlag licenses not on the approved allowlist
- ActionOpen PR pinning repo to last-good revisionGitHub
- OutputOpen issue documenting the disallowed licenseGitHub
What it does
This workflow enforces a hard license allowlist on the HuggingFace models in your repos. On a schedule it compares each model card's current license to your approved SPDX list. Models still on the allowlist are left alone. Models that have drifted to a disallowed license are automatically pinned back to the last revision known to carry an approved license, and a GitHub issue is opened documenting the revert and the offending license so the team can decide next steps.
When to use it
Use it when you have a firm policy on acceptable licenses and want enforcement, not just alerts — keeping production on safe revisions automatically while a human reviews whether to migrate off the model entirely.
How it works
- 1A schedule triggers the allowlist check.
- 2It loads tracked models and their last-good approved revisions from Postgres.
- 3It fetches each model card's current license from HuggingFace.
- 4A branch flags any license not on the approved allowlist.
- 5For flagged models it opens a GitHub PR pinning the repo to the last-good revision.
- 6It opens a GitHub issue documenting the disallowed license and the auto-pin action.
Set it up
What you configure once, before turning it on.
- 1Connect Hugging FaceModels, datasets, spaces — the open-source hub.
- 2Connect GitHubRepos, issues, pull requests, actions.
- 3Connect PostgresAny Postgres URL — query, write, migrate.
- 4Set each agent's modelWe leave models unset so you pick the tier — fast + cheap, or top-quality.
- 5Tune it to your dataEdit the prompts, filters, and field mappings so it matches how your team works.
- 6Test, then turn it onRun once against a sample, confirm the output, then enable the trigger.
More Engineering workflows
Gate breaking API PRs behind downstream consumer acknowledgement
When a PR introduces a breaking contract change, comments the impact summary back on the PR, applies a blocking label.
Publish a versioned API changelog to Confluence on each release tag
On a new semver release tag, gathers the contract changes since the last release and writes a clean.
Agent reviews model-license fit and suggests compliant swaps on the PR
When a PR adds a Hugging Face model, an agent reads the model card and license, judges fit against your commercial-use policy.
Upgrade Impact Router to Module Code Owners
Maps a dependency-bump PR's affected modules to their CODEOWNERS, then DMs each owner on Slack with only the changelog slice that touches code they own.
Re-Voice IVR Prompts on Phone-Tree Config Merge
When a phone-tree config change merges in GitHub, regenerates the ElevenLabs audio for any prompt whose script changed in the diff and opens a follow-up PR adding the new audio…
Upstream Release to Notion Upgrade Brief
When a watched package publishes a new release, fetches the release notes, maps them to the internal modules that depend on it.
Run it inside a business
This workflow drops into a full company template. Import the org, and this is one of the playbooks its agents run.
Run this workflow in your colony.
14-day trial. No DevOps. No Sales call. Provisioned in under a minute.