It's TypeScript with zero runtime dependencies. Repo: https://github.com/taskade/temporal-parser
Would love feedback, especially weird date/time strings you've run into that we should add to the tests.
251 karma · joined January 10, 2017
https://www.taskade.com
Email: john [at] taskade.com
1cd34a906772d9ed2947cffe61ab7fd8b5be67c0aa3cbfd4862cf5f953f44805
️
It's TypeScript with zero runtime dependencies. Repo: https://github.com/taskade/temporal-parser
Would love feedback, especially weird date/time strings you've run into that we should add to the tests.
Once agents have tools and a shared surface, coordination appears immediately.
https://www.moltbook.com/post/791703f2-d253-4c08-873f-470063...
We spent some time turning our GitHub org profile into a full architecture overview in ASCII art, box-drawing characters, and markdown tables.
Workspace DNA, how our AI agents work, the Genesis app builder pipeline, all documented in a single README.
Was fun seeing how much you can communicate visually now using plain text.
LLMs made it easy to generate apps. The harder problem is running them as real businesses. Where they live, remember state, coordinate agents, trigger workflows, and keep operating day to day. We treat the workspace itself as that layer.
One prompt becomes a living system. CRM, ops hub, internal tool, business in a box. Memory, agents, and automations working together. Feels closer to early web hosting than modern SaaS. Not demos. Real systems.
Still early, but builders are shipping real internal apps and workflows, not demos. Excited for the future of AI from productivity to agents and workflows to Infra!
We tried building with 3 founders across 3 timezones. On a good day it felt magical. On a bad day it felt like the kind of lag you remember from SC BW, CS 1.6, or classic WoW raids where one spike wipes the whole run just so everyone has to start over.
Async is great for shipping, but not when you are moving fast on hard problems where alignment is the whole game. The drag shows up slowly and you learn zero to one needs tight loops, high trust, and shared tempo. You cannot patch that with calls or docs.
Some teams crush remote. We did sometimes but not often enough and learned that the hard way. The work decides the model. For us it was about momentum and getting the fastest feedback loop possible. Ideas die in latency. Execution dies in drift.
At the end of the day it is not ideology. It is just whatever keeps the product moving as a startup, aiming high to become better, faster, cheaper than the status quo.
Just my 2c.~
Feels like we’re back again with vibe-coding, app builders, v0, bolt, lovable, all of it. The AI infra even feels familiar. End users getting back the kind of control we had in the public_html days via cPanel shared-hosting, VPS era. And for backend, it’s Supabase or Neon / Postgres now instead of phpMyAdmin and MySQL.
Full circle~
The part that buckles first is always the billing logic. Not the API calls, but the lifecycle math behind experiments… and the experiments never stop now.
So anything that lets teams iterate without rewiring state machines every week is going to find an audience. Most people just want to ship, test, adjust, repeat, without their billing layer collapsing under the pace of AI.
Nice launch!
Sure, it’s not AGI. But dismissing the progress as just marketing ignores the fact that we’re already seeing them handle complex workflows, multi-step reasoning, and real-time interaction better than any previous system.
This is more than just Lisp nostalgia. Something real is happening.
First 100 users came from showing up where early adopters hang out essentially.
Taskade started as a real-time workspace for teams to organize projects and ideas. It's evolved into something bigger — a platform where humans and AI work side by side.
We’re moving past simple chatbots into real agentic workflows, where teams can generate structured task lists, mind maps, and tables, train custom AI agents with dynamic knowledge, and automate work from start to finish.
Today, Taskade is built around three core pillars: Projects, Agents, and Automation. It’s like giving your team a second brain that can think, plan, and get work done across projects, automations, and real-time collaboration. If you’re interested in the future of human-AI collaboration, take a look!
Those trips were always fun. This year, he’s in a rehab hospital on another continent after a stroke, but we’re all staying hopeful to celebrate together next year.
These AI agents think, learn, and act—handling tasks, research, and more—right in your workspace where you can chat, manage tasks, create mind maps, tables, and more.
Check it out and let me know what you think!
Consider the recent Google demo. It was recreated and, while still fun and impressive, it's definitely not ready for commercial use. You can see it at https://sagittarius.greg.technology. This demo is a preview of what's to come, and I think it's important for us to stay open-minded.
I believe that in 2024, we're going to witness a significant expansion in what's possible with AI, while costs decrease. Increased contributions in the open-source community will likely fuel another wave of startups and new applications.
I ran a few popular fun map servers, constantly experimenting with new mods, game/gravity settings, and rotating new maps based on community votes. There was a strong sense of excitement around testing out the latest custom maps, and even the quirky bugs added to the fun.
Project Description: Real-time organization and collaboration tool for structured note-taking, mind mapping, and outlining.
What do you want to be tested: We recently integrated OpenAI / GPT-3 into our collaborative editor to generate automated outlines and mind maps, but it is still a work in progress and with some bugs. Would love to get some feedback and help with testing and improving it. Here is a preview: https://www.taskade.com/blog/ai-outliner
Contact Info: john@taskade.com
Thanks!
A random collection of my favorite GIFs and SoundCloud embeds over the years