slogansand

i have a claude subscription and i use https://github.com/asklokesh/loki-mode for most things, it's just working for me

because it's all AI generated content. Unfortunately, no truth or human interest in reading it except what AI feels like with a gem of keyword manipulation of a million characters

I have stopped autocompletions. Found easier to just prompt and get it done

Install:

bash # npm npm install -g loki-mode

# Homebrew brew install asklokesh/tap/loki-mode

# Docker docker pull asklokesh/loki-mode Usage:

bash # CLI wrapper loki start ./prd.md loki start --provider codex ./prd.md loki start --provider gemini ./prd.md

# Or directly in Claude Code claude --dangerously-skip-permissions # Then say: "Loki Mode" or "Loki Mode with PRD at path/to/prd.md" Human intervention controls:

touch .loki/PAUSE — Pause after the current task

echo "instructions" > .loki/HUMAN_INPUT.md — Inject guidance

Ctrl+C once to pause, twice to exit

Research foundation:

Built on 2025 patterns from OpenAI Agents SDK, Anthropic Constitutional AI, DeepMind SIMA, Chain-of-Verification (arXiv:2309.11495), and MemEvolve (arXiv:2512.18746).

What it does:

Reads your PRD and breaks work into phases: Discovery, Architecture, Infrastructure, Development, QA, Deployment, and Growth

Runs the RARV cycle (Reason, Act, Reflect, Verify) continuously

Uses parallel agents for independent tasks (up to 10 Haiku agents simultaneously on Claude)

Maintains working memory across sessions via .loki/CONTINUITY.md

Includes a 7-gate quality system with 3-reviewer blind review

Multi-provider support (v5.0+):

Claude Code: Full features (parallel agents, Task tool, MCP)

OpenAI Codex CLI: Degraded mode (sequential)

Google Gemini CLI: Degraded mode (sequential)

[2.35.0] - 2026-01-08 Added - Anthropic Agent Harness Patterns & Claude Agent SDK Sources:

Effective Harnesses for Long-Running Agents - Anthropic Engineering Claude Agent SDK Overview - Anthropic Platform New Patterns:

One Feature at a Time (Rule #7 in Core Autonomy)

Work on exactly one feature per iteration Complete, commit, verify before moving to next Prevents over-commitment and ensures clean progress tracking E2E Browser Testing with Playwright MCP

Features NOT complete until verified via browser automation New Essential Pattern: Playwright MCP -> Automate browser -> Verify UI features visually Detailed verification flow added to SKILL.md Note: Playwright cannot detect browser-native alert modals Advanced Task Tool Parameters

run_in_background: Returns output_file path, output truncated to 30K chars resume: Continue interrupted agents with full context Use cases: Context limits, rate limits, multi-session work Fixed Release workflow: Use gh CLI instead of softprops action for atomic release creation

Last time someone raised concerns about web crawling for competitive research. Valid point.

New version has configurable research modes. You can disable external crawling entirely and run fully offline if needed. Feedback heard.

vs single-agent coding assistants: They tap out around 50% on SWE-Bench. No specialization. No parallel review. No self-healing.

vs other multi-agent frameworks: Most focus on chat or simple task delegation. Loki Mode runs full SDLC - from PRD to deployed product with monitoring and business ops.

vs hiring a team: Obviously humans are better for ambiguous problems. But for well-defined PRDs, this removes the "I'll get to it this weekend" bottleneck.

For the skeptics (fair): FireLater repo has full git history. You can see the commits. No human intervention in the implementation phase.

I reviewed outputs and approved deployments. But architecture decisions, code, tests, docs - all Loki Mode.

It's not perfect. Some rough edges. But it works and enterprises can self-host it today.

On the swarm architecture for those curious:

Engineering (8 types): frontend, backend, database, mobile, API, QA, perf, infra Operations (8 types): devops, SRE, security, monitoring, incident, release, cost, compliance Business (8 types): marketing, sales, finance, legal, support, HR, investor, partnerships Data (3 types): ML, data eng, analytics Product (3 types): PM, design, tech writer Growth (4 types): growth hacker, community, success, lifecycle Review (3 types): code, business, security

Agents don't step on each other. Frontend agent never thinks about database schemas. QA agent never writes deployment scripts. Domain isolation is key.

Author here. Quick context on the benchmarks:

We used RARV (Retrieve, Analyze, Reason, Validate) pattern with multi-agent collaboration. Each problem gets worked by specialized agents, reviewed by 3 parallel reviewers (code, business logic, security), and only merged after consensus.

The 99.67% isn't cherry-picked. Full run against standard SWE-Bench dataset. Happy to share methodology if anyone wants to reproduce.

https://skillsmp.com/skills/asklokesh-claudeskill-loki-mode-... loki-mode in > Agent Skills Marketplace

makes sense

@boundring Appreciate the edit. And yeah, the crawling/consent question is thorny - the whole AI ecosystem is built on it. Thanks for checking it out. I'll revisit this and release a new version considering crawling.

Fair question. What specifically worries you about it?

I built this to solve my own problem - too many side projects dying because solo founders can't be 10 people at once.

It's a Claude Code skill that orchestrates 37 specialized AI agents (engineering, ops, marketing, legal, etc.) to take a PRD and autonomously build, deploy, and operate a product.

Key features: - Parallel 3-reviewer code review (code, business logic, security) - Multi-cloud deployment (AWS, GCP, Azure, Vercel) - State persistence for rate limit recovery - Full business ops (Stripe billing, legal docs, landing pages)

Open source, MIT licensed. Feedback welcome - still iterating.