ClawFlows mascot

ClawFlows

If you build, ship, or manage SaaS products with OpenClaw, ClawFlows helps OpenClaw become a growth engine: run automations, manage analytics, and learn what to improve with Agent Analytics.

🚀 109+ automations and growing!

Powered by 🦞 Lobster — deterministic workflow pipelines, zero LLM tokens.

install clawflows Tell your OpenClaw bot
Growth-aware OpenClaw
New

Let OpenClaw manage analytics and growth, not just workflows.

ClawFlows gives OpenClaw the automations to build, ship, and manage SaaS products. Agent Analytics adds the measurement layer, so your agent can see what users did, which changes moved outcomes, and what to improve next. If you are not sure where to start, scan your site first to see what your site should measure first.

Add Agent Analytics
Flow → evidence loop
1Choose a growth workflow in ClawFlows
2Let OpenClaw ship or manage the change
3Track traffic, clicks, and conversion outcomes
4Use the evidence to pick the next growth move
Built for Claude Code, Codex, Cursor, OpenClaw, and Paperclip workflows.

🚀 All Automations 109

Loading automations...

🦞 Powered by Lobster

The open-source workflow engine that makes ClawFlows automations actually run.

Without Lobster

LLM orchestrates every step

10+ tool calls, ~100K tokens per run

With Lobster

lobster run workflow.yaml

Deterministic pipeline, 0 LLM tokens

Zero Token Cost

Data collection runs as shell commands — curl, jq, scripts. No LLM needed to fetch calendars, check APIs, or parse RSS.

🔄

Stateful Pipelines

Workflows remember what they've processed. Yesterday's changelog check won't re-alert on old releases.

Approval Gates

Workflows halt at checkpoints and ask before acting. No "oops, it sent 50 emails" moments.

Lobster is the execution engine. ClawFlows is the registry.
Together: npm + node for AI agent automations.

⭐ Lobster on GitHub Integration Guide
The future of automation

⚡ Two Formats, One Registry

Every automation comes in two flavors: abstract (portable) and Lobster-ready (runs now).

📋 Abstract (Capability-Based)

needs: prediction-markets

Portable — works with any skill

+

🦞 Lobster-Ready (Concrete)

command: curl ... | jq ...

Runs NOW — zero LLM tokens

Abstract format = universal spec for any agent runtime. Lobster format = deterministic shell pipelines that execute today. Use abstract for portability, Lobster for performance.

📊 Fetch
⚙️ Process
🗄️ Store
📈 Visualize
🔔 Notify

Standard Capabilities

These are the building blocks. Browse all or propose new ones.

📊

prediction-markets

Polymarket, Kalshi

🗄️

database

SQLite, storage

📈

chart-generation

Graphs & visuals

🔍

social-search

X/Twitter search

📅

calendar

Events & scheduling

🔊

tts

Text to speech

🤝 Add Your Automation

Just tell your agent what you want automated. It handles everything — writing the YAML, creating the PR, the whole thing.

Tell your agent:

"Create a ClawFlows automation that tracks [X] and alerts me when [Y]. Publish it to the registry."

Your agent will:

  1. 1 Write the automation YAML with the right capabilities
  2. 2 Create README with examples and documentation
  3. 3 Open a PR to clawflows-registry

Manual instructions in the Publishing Guide if needed.

Join the community