You need to be able to own your agent’s memory! We are the Dots alternative that works with any model, including your ChatGPT subscription.
If execution is cheap, how you do things is your competitive advantage. Don’t let an agent hold that hostage!
Concerning: OpenAI Dots have a black box memory system. You can’t view, modify, or delete individual memories.
Implications:
- you can’t inspect/mine exactly what a Dot has learned about you or your company
- if it learns the wrong thing, you can’t directly correct its memory
- the only way to delete that context is to delete the Dot
Tough dot to swallow for companies.
Start for free, with paid plans where your agents get their own cloud computers for only $20/month.
latchloop.com
At OpenAI DevDay keynote, “You can sign in with ChatGPT in other products to use your existing subscription”
This is available now in LatchLoop!
LatchLoop retweeted
If you are excited to try OpenAI Dots right now, including the multiplayer team collaboration in a platform that works with any model and provider, LatchLoop is available to everyone now.
My team has been working this way since Feb 2025.
Free to start.
latchloop.com
Curious to see what OpenAI's "o" is tomorrow, and also to see Grok Bot's multiplayer announcement today.
Wondering how this compares to our Operator and multiplayer agents our team has been using internally since Feb 2025.
How its going:
LatchLoop made over 4800 commits and 443,000+ lines of code changed to itself in the last 30 days.
We call these agent apps and released them back in May inside LatchLoop!
xitter.cf/LatchLoopAI/status/206…
OpenClaw Dashboards
@hrudolph, @patrickerichsen and @jjjhenriksen demo personal and team dashboards, then show how to build a mini app inside OpenClaw with prompts.
Episode 10 of The ClawCast:
openclaw.ai/podcast/episode-…
Astra is available in LatchLoop. Use it with your existing ChatGPT subscription.
Its impressive at putting 3D games together quickly and building complex visuals in code from references.
By the way, this was what the game looked like while it was still being built. Here's a video of the result:
xitter.cf/LatchLoopAI/status/209…
Astra is amazing. It built this game in 2 prompts.
One for the base game and one that mostly said "make the graphics better".
This is built with three.js running in the browser at 120fps.
GLM-5.3 Flash (ox-alpha) has redrawn the Pareto frontier.
We're continuing to offer the model for free for a limited time.
Unlike some small models that look good in benchmarks but feel bad in real world tasks, this model is a joy to use.
The Ox Alpha (stealth model) is free for the next week in LatchLoop inference Gateway.
1M token context, zero data retention, and impressive performance.
Give it a try for free in LatchLoop!
Wish you could share projects and collaborate with a teammate but don’t have a business or enterprise ChatGPT account?
LatchLoop gives you the ability to share on our $20/mo plan and the person you are sharing with can be on the free plan!
And you can build much more than sites
If you relate to some of the problems DoorDash had with other off the shelf coding agents, LatchLoop is the solution!
Multiplayer, cloud agents, secure sandboxes, and team reporting come standard here.
Today we’re proud to announce Flux, our own cloud platform for running agents across DoorDash.
Flux automated 130k engineering tasks in one month and now powers 25k+ code reviews each week. Creating the platform ourselves moved us beyond local, laptop-based agent workloads, while preserving enterprise security guardrails over execution and access to DoorDash systems.
Here’s how Flux works and what we learned putting cloud-based agents to work:
Slack but with agents = everyone stressed out trying to keep up with and understand what the agents are doing
If we are trying to be productive and understand what is happening there is a better way.
Task based collaboration is the best multiplayer humans+agent solution so far
Related:
xitter.cf/jasonfried/status/2083…
To celebrate the price cuts and price to performance ratio we are giving additional free GPT 5.6 usage to everyone who signs up before the weekend.
We are committed to pushing the model frontier across cost efficiency, capability, and speed.
Starting today, we are reducing prices for GPT-5.6 Luna by 80% and GPT-5.6 Terra by 20% , and offering a faster option for GPT-5.6 Sol in the API.
Luna and Terra’s lower prices are reflected in how usage is counted in Codex and ChatGPT Work, so your usage goes further.
Every team should have multiplayer agents and must own their agent’s memory.
If we can all press the same magic button to have work done for us by AI, then your processes and how you do things is everything.
Don’t let vendors hold that hostage.
Replying to @alliekmiller
What do you use for Multiplayer AI? I just opened an account at @LatchLoopAI. In addition to their multiplayer capabilities, I'm interested in the repo-owned memory with the skills I create becoming portable assets to be used with any model.
















