Theo is right. Bash is just the beginning. We built the "Execution Layer" he talks about in the video. We are calling it Worklayer. Here is a sneak-peek of the landing page. Details & product link in comments.

WAAAAIIIIITTT 😂

Worklayer Day 5 Update (April 12) → The founders went on a hike and touched grass → Oh and we added🛍️ Shopify integration. We are now waiting for approval from the official Shopify App Store.

Introducing Fire-PDF, our new Rust-based parsing engine 🔥 - Convert PDFs into markdown 5x faster - Extract full tables and preserve formulas - Zero config required

99% of Ramp uses ai daily. but we noticed most people were stuck — not because the models weren't good enough, but because the setup was too painful and unintuitive for most. terminal configs, mcp servers, everyone figuring it out alone. so we built Glass. every employee gets a fully configured ai workspace on day one — integrations connected via sso, a marketplace of 350 reusable skills built by colleagues, persistent memory, scheduled automations. when one person on a team figures out a better workflow, everyone on that team gets it and gets more productive. the companies that make every employee effective with ai will compound advantages their competitors can't match. most are waiting for vendors to solve this. we decided to own it.

id love to see a shopify integration!

Theo is right. Bash is just the beginning. We built the "Execution Layer" he talks about in the video. We are calling it Worklayer. Here is a sneak-peek of the landing page. Details & product link in comments.

Worklayer Day 3 Update April 10 Change log New Integrations - 📟 PagerDuty: Let your agents handle incidents and escalate them when needed. - 🗃️ Sanity-io: Agents can manage your CMS - 📆 Calendly: Agents handle scheduling - ∴ Asana: Let agents handle tasks in asana New Features - Added 12 new tools to 📩 Gmail. - Added auto-refresh system for all integrations - Logical session traces: Inspect session as events grouped by tasks and not agent chats. Agents decide what events belong to the task/workflow being worked on. Improvements - Fixed Make integration connection issue - Disabled autofill for API key fields. Was annoying for users - Auto-generate trace session descriptions - Minor UI fixes - Fixed drafting of HTML emails.

Worklayer Day 2 Update: April 9 change log New Integrations - 🐘 Postgres: Worklayer can now do SQL code scripts on your Postgres DB and help you capture insights. - 💬 Discord: Manage communities using Claude Code. We are using this to manage our Worklayer's Discord community - 🌃 Replicate: You can do image generation from all SOTA image models using Replicate API key - 💰 Dodo Payments: Generate Invoices, Issue Refunds, Tally payouts, and much more. Improvements - Update web UI for tool trace timeline. Not it shows partial tool failures & text-based tool responses - Updated JSON result truncation in the UI

Insane response on day 1. We are going all in on Worklayer to make it your agent's daily driver. New integrations shipping daily. Here is the change log from April-8. New Integrations - 🥕 Instacart: Your agents can now write code to do grocery shopping - 🔥 Incident-io: Prompt your agents to monitor the situation and fix issues in production - 🎨 Figma: Your agents can understand your design and implement it in React (tested internally: waiting for approval from Figma) - 📊 Gamma: Create slides using your agents! Improvements - Improved worklayer tool descriptions using evals. Agents will now be better at writing and executing code on your apps out of box. - Better default permissions (Ask, Allow, Deny) for all app actions. Actions that read data will be allowed by default. Actions that write, update or delete data will be in ask mode. - Centralized tool name sanitization in app-registry - Improved display names for connected credentials - Added subtle page animations for better UX Bug fixes - Prevented overlay click from closing dialogs - Removed certain clashing apps that we used as upstream MCPs but advertised as native - Fixed Google Docs to return tab contents with proper hierarchy - Fixed settings for app connectors. It only opens the intended dialog - Fixed MCP tool permissions inference for empty configs (linear showing 12 instead of 31 tools)

If you want your OpenClaw or Hermes Agent to be able to have perfect total recall of all 10,000 markdown files, GBrain is here to help. It's exactly my OpenClaw/Hermes Agent setup. MIT-licensed open source. Hope it helps you build your mini-AGI. github.com/garrytan/gbrain

Theo is right. Bash is just the beginning. We built the "Execution Layer" he talks about in the video. We are calling it Worklayer. Here is a sneak-peek of the landing page. Details & product link in comments.

Theo is right. Bash is just the beginning. We built the "Execution Layer" he talks about in the video. We are calling it Worklayer. Here is a sneak-peek of the landing page. Details & product link in comments.

Theo is right. Bash is just the beginning. We built the "Execution Layer" he talks about in the video. We are calling it Worklayer. Here is a sneak-peek of the landing page. Details & product link in comments.

Theo is right. Bash is just the beginning. We built the "Execution Layer" he talks about in the video. We are calling it Worklayer. Here is a sneak-peek of the landing page. Details & product link in comments.

Agents are good at bash. Bash is not good for agents. We should cut our losses and restart now before it is too late.