Skip to content

Loki Mode

v7.18.3 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai-agents aider anthropic autonomous ci-cd claude
+13 more
cline code-review devops gemini github-action github-issues loki-mode multi-agent openai-codex openapi pull-request-review sdlc spec-driven-development

Summary

AI summary

Fixed mismatched loki demo description to correctly state it builds a sample todo app end‑to‑end.

Full changelog

Changed

  • First-run experience: loki with no arguments now leads with a "New here?"
    getting-started block (loki doctor, loki quick, loki demo, loki start) so a
    new user has an obvious next step instead of a wall of 30+ commands. Reduces
    time-to-first-value. Help text only, no behavior change.

Fixed

  • Honest loki demo description. The command help and the no-arg command list
    previously called demo a "~60s simulated session," but loki demo runs a
    real end-to-end build of a sample todo app. All three descriptions now say
    "Build a sample todo app end to end (real run)" so the copy matches behavior.
  • The crash-report channel (loki crash submit prefilled GitHub issue URL, and
    the references in docs/PRIVACY.md) now resolves: GitHub issues were
    re-enabled on the repository, so the v7.18.2 crash-report promise works.

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track Loki Mode

Get notified when new releases ship.

Sign up free

About Loki Mode

Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 11 quality gates.

All releases →

Related context

Beta — feedback welcome: [email protected]