loki-mode  by asklokesh

Autonomous system for end-to-end product development

Created 9 months ago
1,090 stars

Top 35.0% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

Loki Mode is a Claude Code skill designed to autonomously transform a Product Requirements Document (PRD) into a fully deployed, revenue-generating product. It targets developers and power users seeking to automate the entire startup lifecycle, offering a complete solution from ideation to market operation with minimal human intervention.

How It Works

This system orchestrates 37 specialized AI agents across 6 distinct swarms (Engineering, Operations, Business, Data, Product, Growth). It employs a novel approach featuring parallel code review by three simultaneous reviewers (code, business, security) and integrates 14 automated quality gates covering security, load testing, and accessibility. The architecture supports multi-cloud deployment with advanced strategies and manages complex business operations autonomously.

Quick Start & Requirements

  • Primary Install/Run: Use the autonomous runner script: ./autonomy/run.sh <path_to_prd>. This script handles prerequisite checks, installation verification, state initialization, live output display, and auto-resume capabilities.
  • Prerequisites: Claude Code CLI, internet access for research and deployment, cloud provider credentials (AWS, GCP, Azure, Vercel, Railway), Python 3 (for test suite).
  • Links: Example PRDs are available in the examples/ directory. Detailed documentation for the autonomous runner is in autonomy/README.md.

Highlighted Details

  • Features 37 specialized AI agents organized into 6 swarms for comprehensive lifecycle coverage.
  • Implements parallel code review with simultaneous code, business logic, and security checks.
  • Integrates 14 automated quality gates, including security scans and load testing.
  • Supports multi-cloud deployment (AWS, GCP, Azure, Vercel, Railway) with blue-green and canary strategies.
  • Includes full-stack business operations agents for marketing, sales, HR, legal, and finance.
  • Offers robust state recovery and auto-resume functionality for uninterrupted operation.

Maintenance & Community

No specific details regarding notable contributors, sponsorships, or community channels (e.g., Discord, Slack) were found in the provided README. Contributions are welcomed via GitHub issues.

Licensing & Compatibility

  • License: MIT License.
  • Compatibility: The MIT license permits commercial use and integration within closed-source projects.

Limitations & Caveats

Manual operation requires running Claude Code with the --dangerously-skip-permissions flag, suggesting potential security implications or advanced user requirements. The system's effectiveness is dependent on the Claude Code ecosystem and requires valid cloud provider credentials for deployment phases.

Health Check
Last Commit

1 day ago

Responsiveness

Inactive

Pull Requests (30d)
6
Issues (30d)
20
Star History
4 stars in the last 30 days

Explore Similar Projects

Starred by Peter Norvig Peter Norvig(Author of "Artificial Intelligence: A Modern Approach"; Research Director at Google), Zhen Lu Zhen Lu(Cofounder of Runpod), and
1 more.

agents-towards-production by NirDiamant

0.0%
22k
Production-ready GenAI agent tutorials
Created 1 year ago
Updated 2 weeks ago
Starred by Eric Zhu Eric Zhu(Coauthor of AutoGen; Research Scientist at Microsoft Research), Elie Bursztein Elie Bursztein(Cybersecurity Lead at Google DeepMind), and
27 more.

goose by aaif-goose

0.0%
55k
Open-source AI agent for automating complex engineering tasks
Created 2 years ago
Updated 20 hours ago
Feedback? Help us improve.