Loki Mode

Autonomous multi-agent development with self-verification

PRD in, tested code out.

Website | Documentation | Installation | Changelog | Purple Lab Web UI

How it works: You provide a PRD. Loki Mode classifies complexity, assembles an agent team from 41 specialized types across 8 swarms, and runs autonomous RARV cycles (Reason - Act - Reflect - Verify) with 9 quality gates. Code is not "done" until it passes automated verification. Output is a Git repo with source, tests, configs, and audit logs.

Get Started in 30 Seconds

npm install -g loki-mode
loki doctor                        # verify environment
loki start ./prd.md                # autonomous build starts

| Method | Command | |--------|---------| | Homebrew | brew tap asklokesh/tap && brew install loki-mode | | Docker | docker pull asklokesh/loki-mode | | Inside Claude Code | claude --dangerously-skip-permissions then type "Loki Mode" | | Git clone | git clone https://github.com/asklokesh/loki-mode.git |

See the full Installation Guide.

What To Expect

| | Simple | Standard | Complex | |---|---|---|---| | Examples | Landing page, todo app, single API | CRUD + auth, REST API + React | Microservices, real-time, ML pipelines | | Duration | 5-30 min | 30-90 min | 2+ hours | | Autonomy | Completes independently | May need guidance on complex parts | Use as accelerator with human review |

Architecture

RARV Cycle

Every iteration: Reason (read state) - Act (execute, commit) - Reflect (update context) - Verify (run tests, check spec). Failures trigger self-correction.

Core Workflow

41 Agent Types

8 swarms: engineering, operations, business, data, product, growth, review, orchestration. Auto-composed by PRD complexity.

Agent Types

9 Quality Gates

Blind review, anti-sycophancy, severity blocking, mock/mutation detection. Code does not ship until all gates pass.

Quality Gates

Memory System

3-tier architecture: episodic (interaction traces), semantic (generalized patterns), procedural (learned skills). Vector search optional.

Memory Architecture

Dashboard

Real-time monitoring, agent status, task queue, WebSocket streaming. Auto-starts at localhost:57374.

Dashboard Guide

Enterprise Layer

TLS, OIDC/SSO, RBAC, OTEL tracing, policy engine, audit trails. Activated via env vars.

Enterprise Guide

Purple Lab

The hosted development platform. A Replit-like web UI for visual PRD-to-code workflow with AI chat for iterative development.

loki web                           # launches at http://localhost:57375

Platform Pages

• Home -- PRD input with plan-before-build flow
• Projects -- browse, search, filter past builds
• Templates -- 20+ starter PRDs by category
• Settings -- provider selection, configuration

IDE Workspace

• Monaco editor with tabs, Cmd+P quick open
• AI chat panel for iterative development
• Activity panel: build log, agents, quality gates
• Live preview with URL bar navigation
• Right-click context menu: Review, Test, Explain

Multi-Provider Support

| Provider | Autonomous Flag | Parallel Agents | Install | |----------|:-:|:-:|---------| | Claude Code | --dangerously-skip-permissions | Yes (10+) | npm i -g @anthropic-ai/claude-code | | Codex CLI | --full-auto | Sequential | npm i -g @openai/codex | | Gemini CLI | --approval-mode=yolo | Sequential | npm i -g @google/gemini-cli | | Cline CLI | --auto-approve | Sequential | npm i -g @anthropic-ai/cline | | Aider | --yes-always | Sequential | pip install aider-chat |

Claude gets full features (subagents, parallelization, MCP, Task tool). Other providers run sequentially. Auto-failover switches providers when rate-limited. See Provider Guide.

CLI Reference

| Command | Description | |---------|-------------| | loki start [PRD] | Start with optional PRD file | | loki stop | Stop execution | | loki pause / resume | Pause/resume after current session | | loki status | Show current status | | loki dashboard | Open web dashboard | | loki web | Launch Purple Lab web UI | | loki doctor | Check environment and dependencies | | loki plan [PRD] | Pre-execution analysis: complexity, cost, iterations | | loki review [--staged\|--diff] | AI-powered code review with severity filtering | | loki test [--file\|--dir\|--changed] | AI test generation (8 languages, 9 frameworks) | | loki onboard [path] | Project analysis and CLAUDE.md generation | | loki import | Import GitHub issues as tasks | | loki ci | CI/CD quality gate integration | | loki failover | Cross-provider auto-failover management | | loki memory <cmd> | Memory system: index, timeline, search, consolidate | | loki enterprise | Enterprise feature management | | loki version | Show version |

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

Loki Mode integrates with the BMAD Method, a structured AI-driven agile methodology. If your project uses BMAD for requirements elicitation, Loki Mode can consume those artifacts directly:

loki start --bmad-project ./my-project

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

See BMAD Integration Validation.

Enterprise features are included but require env var activation. Self-audit: 35/45 capabilities working, 0 broken, 1,314 tests passing.

export LOKI_TLS_ENABLED=true
export LOKI_OIDC_PROVIDER=google
export LOKI_AUDIT_ENABLED=true
loki enterprise status

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

Self-reported results from the included test harness. Verification scripts included for reproduction.

| Benchmark | Result | Notes | |-----------|--------|-------| | HumanEval | 162/164 (98.78%) | Max 3 retries, RARV self-verification | | SWE-bench | 299/300 patches | Patch generation -- evaluator not yet run |

See benchmarks/ for methodology.

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

Download PPTX

Limitations

| Area | What Works | What Doesn't (Yet) | |------|-----------|---------------------| | Code Gen | Full-stack apps from PRDs | Complex domain logic may need human review | | Deploy | Generates configs, Dockerfiles, CI/CD | Does not deploy -- human runs deploy commands | | Testing | 9 automated quality gates | Test quality depends on AI assertions | | Providers | 5 providers with auto-failover | Non-Claude providers lack parallel agents | | Dashboard | Real-time single-machine monitoring | No multi-node clustering |

What "autonomous" means: The system runs RARV cycles without prompting. It does NOT access your cloud accounts, payment systems, or external services unless you provide credentials. Human oversight is expected for deployment, API keys, and critical decisions.

Research Foundation

| Source | What We Use | |--------|-------------| | Anthropic: Building Effective Agents | Evaluator-optimizer, parallelization | | Anthropic: Constitutional AI | Self-critique against quality principles | | DeepMind: Scalable Oversight via Debate | Debate-based verification in council review | | DeepMind: SIMA 2 | Self-improvement loop design | | OpenAI: Agents SDK | Guardrails, tripwires, tracing | | NVIDIA ToolOrchestra | Efficiency metrics, reward signals | | CONSENSAGENT (ACL 2025) | Anti-sycophancy in blind review | | GoalAct | Hierarchical planning for complex PRDs |

Practitioner insights: Boris Cherny, Simon Willison, HN Community

Full Acknowledgements -- 50+ papers and resources

Contributing

git clone https://github.com/asklokesh/loki-mode.git && cd loki-mode
npm install && npm test              # 683 tests
python3 -m pytest                    # 631 tests

See CONTRIBUTING.md for guidelines.

License

Business Source License 1.1 -- Free for personal, internal, academic, and non-commercial use. Converts to Apache 2.0 on March 19, 2030. Contact [email protected] for commercial licensing.

Autonomi | Documentation | Changelog | Comparisons