experientiallabs

Set up the full CLaaS stack (vLLM + API + OpenClaw/Telegram) locally. Uses Docker if available, falls back to native setup otherwise.

Deploy the CLaaS Modal serverless distillation API. Use when deploying the SDPO distillation service to production.

Deploy the CLaaS Tinker stack (API + OpenClaw/Telegram) via Docker Compose. No GPU required.

Delete all checkpoints from your Thinking Machine Tinker prod account to reduce storage charges. Requires TINKER_API_KEY.

Address reviewer feedback on GitHub pull requests by making targeted fixes or explaining disagreements. Use when responding to PR comments.

Iteratively improve the RubricJudge (or any LLM scorer) against a hand-labeled dataset - run the judge, identify false positives/negatives, diagnose why each failed, propose one experiment (prompt, model, or context) per failure class, and prove the fix without regressing controls. Use when the user distrusts judge scores, asks to improve/calibrate/tune the judge, or a new corpus type needs judge coverage.

Mandatory pre-merge gate for every PR. Runs /code-review --fix at an effort level scaled to the PR's breadth, resolves every review comment (Cursor, Greptile, humans), and verifies the diff complies with AGENTS.md. Use whenever the user says a PR is ready to merge, asks to merge, or invokes /ready-for-merge.