loki-mode

Installation
Summary

Autonomous multi-agent system that takes product requirements to fully deployed, revenue-generating product with zero human intervention.

  • Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success using a distributed task queue with dead letter handling and circuit breakers
  • Implements parallel code review with 3 specialized reviewers, severity-based issue triage, and self-healing via automatic retry with exponential backoff and distributed state checkpoints
  • Follows RARV cycle (Reason-Act-Reflect-Verify) for every iteration, with model selection strategy: Opus for planning only, Sonnet for development, Haiku for operations and testing
  • Includes constitutional self-critique, debate-based verification for critical changes, and deterministic validation gates to prevent false positives and ensure quality before deployment
  • Requires --dangerously-skip-permissions flag to run; maintains working memory in .loki/CONTINUITY.md and learns from mistakes via episodic and semantic memory consolidation
SKILL.md

Loki Mode - Multi-Agent Autonomous Startup System

Version 2.35.0 | PRD to Production | Zero Human Intervention Research-enhanced: OpenAI SDK, DeepMind, Anthropic, AWS Bedrock, Agent SDK, HN Production (2025)


Quick Reference

Critical First Steps (Every Turn)

  1. READ .loki/CONTINUITY.md - Your working memory + "Mistakes & Learnings"
  2. RETRIEVE Relevant memories from .loki/memory/ (episodic patterns, anti-patterns)
  3. CHECK .loki/state/orchestrator.json - Current phase/metrics
  4. REVIEW .loki/queue/pending.json - Next tasks
  5. FOLLOW RARV cycle: REASON, ACT, REFLECT, VERIFY (test your work!)
  6. OPTIMIZE Opus=planning, Sonnet=development, Haiku=unit tests/monitoring - 10+ Haiku agents in parallel
  7. TRACK Efficiency metrics: tokens, time, agent count per task
  8. CONSOLIDATE After task: Update episodic memory, extract patterns to semantic memory
Related skills
Installs
485
GitHub Stars
37.3K
First Seen
Jan 19, 2026