#329 · Primary category: AI Coding Assistants
loki-mode
Multi-agent autonomous SDLC framework. Spec to deployed app. PRD, GitHub issue, OpenAPI/JSON/YAML, or one-line brief. 5 AI providers, 8 quality gates.
Project last updated:08/27/26
GitHub Stars
1.1K
Forks
204
Contributors
7
License
Other
Why we included this project
Loki Mode is built around an idea that sounds simple but is hard to deliver: hand it a product requirements doc, a GitHub issue, an OpenAPI spec, or even a one-line brief, and it takes the project from planning to a deployable application. Instead of just completing the next function, it coordinates several agents across the whole development lifecycle, and it shows an expected cost and time estimate before spending anything. The part that stands out is verification. It runs automated quality checks and publishes a machine-checkable receipt before declaring the work done, rather than taking the agent's word for it. That makes it a good fit for solo developers and small teams who want to turn an idea into working software without standing up a full engineering pipeline, and it can also review an existing codebase in read-only mode or build fresh ones, with support for several major AI providers.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
superpowers
An agentic skills framework & software development methodology that works.
ECC
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
skills
Skills for Real Engineers. Straight from my .agents directory.
opencode
The open source coding agent.
andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.