Loki Mode

Autonomous multi-agent development with self-verification. PRD in, tested code out.

Current Version: v6.31.0

Traction

737 stars | 150 forks | 10,600+ Docker pulls | 19,000+ npm downloads | 590 commits | 252 releases published | 18 releases in a single day (March 18, 2026)

What Is Loki Mode?

Loki Mode is a multi-agent system that transforms a Product Requirements Document into a built and tested product. It orchestrates 41 specialized agent types across 8 swarms -- engineering, operations, business, data, product, growth, review, and orchestration -- working in parallel with continuous self-verification.

Every iteration follows the RARV cycle: Reason (read state, identify next task) -> Act (execute, commit) -> Reflect (update continuity, learn) -> Verify (run tests, check spec). If verification fails, the system captures the error as a learning and retries from Reason. This is the core differentiator: code is not "done" until it passes automated verification. See Core Workflow.

What "autonomous" actually means: The system runs RARV cycles without prompting. It does NOT have access to your cloud accounts, payment systems, or external services unless you provide credentials. Human oversight is expected for deployment credentials, domain setup, API keys, and critical decisions. The system can make mistakes, especially on novel or complex problems.

What To Expect

Limitations

Quick Start

Requirements: Node.js 18+, Python 3.8+, macOS/Linux/WSL2, and at least one AI CLI (Claude Code, Codex, Gemini, Cline, or Aider).

CLI Mode

npm install -g loki-mode
loki doctor                        # verify environment
loki start ./prd.md                # uses Claude Code by default

Interactive Mode (inside Claude Code)

claude --dangerously-skip-permissions
# Then type: "Loki Mode" or "Loki Mode with PRD at ./my-prd.md"

This is the easiest way to try it if you already have Claude Code installed. No separate loki CLI installation needed.

What Happens

The system classifies your PRD complexity, assembles an agent team, and runs RARV cycles with 9 quality gates. Output is committed to a Git repo with source code, tests, deployment configs, and audit logs. The dashboard auto-starts at http://localhost:57374 for real-time monitoring, or use loki status from the terminal.

Other install methods: Homebrew (brew tap asklokesh/tap && brew install loki-mode), Docker, Git clone, VS Code Extension. See Installation Guide.

Cost: Loki Mode uses your AI provider's API. Simple projects typically consume modest token usage; complex projects with parallel agents use more. Monitor token economics with loki memory economics. See Token Economics for details.

BMAD Method Integration

Loki Mode integrates with the BMAD Method, a structured AI-driven agile methodology. If your project uses BMAD for requirements elicitation (product briefs, PRDs, architecture documents, epic/story breakdowns), Loki Mode can consume those artifacts directly:

# Start from BMAD project artifacts
loki start --bmad-project ./my-project

# BMAD artifacts are discovered automatically from _bmad-output/
# PRD is analyzed with BMAD-aware scoring dimensions
# Architecture decisions are injected as execution context
# Epics/stories are loaded into the task queue

The adapter handles BMAD's frontmatter conventions, FR-format functional requirements, Given/When/Then acceptance criteria, and artifact chain validation. Non-BMAD projects are completely unaffected -- the integration is additive and opt-in via the --bmad-project flag.

See BMAD Integration Validation for the compatibility analysis.

Presentation

9 slides: Problem, Solution, 41 Agents, RARV Cycle, Benchmarks, Multi-Provider, Full Lifecycle | Download PPTX

Architecture

Fallback: PRD -> Classifier -> Agent Team (41 types, 8 swarms) -> RARV Cycle <-> Memory System -> Quality Gates (pass/fail loop) -> Output

See full architecture documentation for the detailed view.

Key components:

• RARV Cycle -- Reason-Act-Reflect-Verify with self-correction on failure. Core Workflow
• 41 Agent Types -- 8 swarms auto-composed by PRD complexity. Agent Types
• 9 Quality Gates -- Blind review, anti-sycophancy, severity blocking, mock/mutation detection. Quality Gates
• Memory System -- Episodic, semantic, procedural tiers with progressive disclosure. Memory Architecture
• Dashboard -- Real-time monitoring, API v2, WebSocket at port 57374. Dashboard Guide
• Enterprise Layer -- OTEL, policy engine, audit trails, RBAC, SSO (requires env var activation). Enterprise Guide

Features

Multi-Provider Support

Claude gets full features (subagents, parallelization, MCP, Task tool). All other providers run in sequential mode -- one agent at a time, no Task tool. See Provider Guide for the full comparison.

CLI

Run loki --help for all commands. Full reference: CLI Reference | Configuration: config.example.yaml

Enterprise

Enterprise features are included but require env var activation. Self-audit results: 35/45 capabilities working, 0 broken, 1,314 tests passing (683 npm + 631 pytest). 2 items partial, 3 scaffolding (OTEL/policy active only when configured). See Audit Results.

export LOKI_TLS_ENABLED=true
export LOKI_OIDC_PROVIDER=google
export LOKI_AUDIT_ENABLED=true
export LOKI_METRICS_ENABLED=true
loki enterprise status               # check what's enabled
loki start ./prd.md                   # enterprise features activate via env vars

Enterprise Architecture | Security | Authentication | Authorization | Metrics | Audit Logging | SIEM

Benchmarks

Results from the included test harness. Self-reported and not independently verified. Verification scripts included so you can reproduce. See benchmarks/ for methodology.

Research Foundation

Practitioner insights: Boris Cherny -- self-verification loop patterns | Simon Willison -- sub-agents for context isolation | HN Community -- production patterns from real deployments

Full Acknowledgements -- 50+ research papers, articles, and resources

Contributing

git clone https://github.com/asklokesh/loki-mode.git && cd loki-mode
npm install && npm test              # 683 tests, ~10 sec
python3 -m pytest                    # 631 tests, ~3 sec
bash tests/run-all-tests.sh          # shell tests, ~2 min

See CONTRIBUTING.md for guidelines.

License

MIT -- see LICENSE.

Autonomi | Documentation | Changelog | Installation | Comparisons