Showing 1-12 of 14
Add a CTRLRun step to your GitHub Actions CI to enforce runtime policies, produce per-run audit logs, and restrict agent tool access. Includes a simple config and rollout checklist.
Run Foremerge locally or in CI to record agents' intent JSON, use a .foremerge decision table to surface incompatible plans, and gate PRs so conflicts are resolved before code is written.
A hands-on guide to fetch an SDI act, canonicalize its JSON, compute the SHA-256 digest, and verify Chromite's recorded seal with only curl and Python—includes CI tips and failure modes.
Fetch and archive FelonyBench's felonies.json, pick high‑impact labels (e.g., production database compromise 4×), then run sanitized CI tests to produce auditable model-risk reports.
Use Tracelint to statically analyze saved agent execution traces and surface reproducible evidence for ignored tool errors, schema violations, and loops—plus CI rollout tips.
Open-source linter for files that steer AI coding agents (skills, CLAUDE.md). It flags vague instructions, contradictions, embedded secrets, and can auto-fix many issues.
CI-medic auto-summarizes failed CI runs into 1–3 diagnostic bullets, redacts secrets, and suggests next steps. Single-repo proof-of-concept in ~60–120 minutes; explore trade-offs.
Practical Musts guide: configure a fast CI validation loop (lint, tests, commands) so AI-opened pull requests are blocked from merging until checks pass. Includes setup and rollout tips.
Use DoneSpec to convert ambiguous agent outputs into deterministic PASS/FAIL validators, enabling CI gating, automated retries, and measurable pass-rate observability.
Flightplanner makes short, human-readable product specs the canonical source for end-to-end checks, reducing brittle test upkeep as AI agents raise integration churn.
Litmus records complete LLM agent executions (prompts, tool calls, outputs) so teams can deterministically replay failures, inject faults, and gate regressions in CI.
A commit-gated pipeline (Prompt→LLM→Validation→Normalizer→Retry→Commit) keeps AI-generated structured files off disk until they pass schema checks, revealing schema gaps.