# asklokesh/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.

Repository: https://github.com/asklokesh/loki-mode
Canonical: https://ross.abutalabs.com/products/loki-mode
Homepage: https://www.autonomi.dev
Language: Shell
License: NOASSERTION
License Family: other
Topics: ai-agents, autonomous, ci-cd, claude, code-review, devops, gemini, github-action, multi-agent, openai-codex, pull-request-review, loki-mode, aider, anthropic, cline, github-issues, openapi, sdlc, spec-driven-development
Last push: 2026-08-31T19:51:14+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 100, release rhythm 87, longevity 17
- inputs: {"age_days": 250, "days_push": 2, "days_rel": 9, "gap_med": 0.0, "n_releases_24m": 801}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1054, forks 205 (observed 2026-09-01T02:13:58.910413+00:00)

## What it is
Loki Mode is a spec-driven autonomous SDLC framework that turns a PRD, GitHub issue, OpenAPI spec, or one-line brief into a deployed application using multiple AI coding agents. It enforces verified completion through quality gates and supports five AI providers including Claude, Gemini, and OpenAI Codex.

## Use cases
- build an app from a one-line idea
- turn a PRD into a deployed application
- autonomous coding agent for CI pipelines
- spec-driven development with quality gates
- automate the software development lifecycle with AI agents
- generate code from GitHub issues or OpenAPI specs
- multi-agent autonomous code review and PR review

## When to choose
- you want to go from spec to deployed app with minimal manual coding
- you need verified completion - builds that fail tests or produce empty diffs are rejected
- you want to run autonomous builds in CI, scripts, or containers non-interactively
- you want flexibility across multiple AI providers (Claude, Gemini, OpenAI Codex, etc.)

## When to avoid
- you need a permissive open-source license - it is BUSL-1.1 source-available, not OSI open source
- you prefer full human control over every code change rather than autonomous agent execution
- your project is small enough that an autonomous multi-agent pipeline adds overhead without benefit
- you rely on AI providers outside the five supported ones

## Facets
- artifact type: framework
- maturity: active
- function: agent-framework, ci-cd, code-review, workflow-automation, developer-tools, cli
- domain: developer-tools
- platform: cli, windows
- tags: spec-driven-development, sdlc, multi-agent, autonomous-coding, github-action, openapi, github-issues, quality-gates, busl-license, source-available, ai-agents, devops, automation, docker, nodejs, macos, linux

## Member repositories
- asklokesh/loki-mode (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-09-01T02:13:58.910413+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:00:16.772587+00:00, confidence not recorded.
  - readme: https://github.com/asklokesh/loki-mode (fetched 2026-09-01T02:13:58.910413+00:00, sha 010423939468)
  - homepage: https://www.autonomi.dev (fetched 2026-08-29T13:01:29.289465+00:00, sha 8e3e41454efc)
- Data as of 2026-08-30T08:39:29.467469+00:00.