We found a few tiny regressions the agent missed, mostly different shapes on buttons or slight ux regressions, overall I'm amazed how well this worked. Technical dept is can be counted in token now.
@steipete
-
Agentic Workflow Migrates OpenClaw’s Frontend From Lit to Solid
By
–
Two weeks ago I kicked off a loop to move OpenClaw's Lit-based Web frontend to Solid 2.0. Took ~6 days until we could remove Lit, and another week to move patterns to idiomatic Solid. I checked in with the session every other day, overall the process was mostly automatic. Took
-
Agent Rewritten TypeScript Tooling Delivers Large Performance Gains
By
–
Moved to tsrs over the weekend. Drop-in replacement. Around 5x faster for OC. Kind of amazing that it took Microsoft a team and two years to rewrite the TS compiler in go, and now you can just let an agent rip and get sth significantly better within weeks.
-
OpenClaw Displays Commentary for Code Mode Execution Calls
By
–
Openclaw generates commentary for each exec call in the Web UI when it uses code mode. Is that not enough?
-
Claude Therapy Satire Highlights Sycophantic Validation Risks
By
–
I recently used Claude as a therapist, and I was delighted to find that it validated my view of the world and confirmed my suspicion the other person was completely at fault. Strongly recommend, 10/10. Human therapists are cooked.
-
A Bot Is Asked to Find a Repository and Start Reviewing
By
–
@roboclawbot gonna be hard but maybe you find the matching github and can kick off a review
-
OpenClaw Can Reach Other Agents Through Computer Use
By
–
That is not accessible via API, but your claw can talk to any agent inclusive a dot via computer use. Other way around is easy with the openclaw cli
-
OpenClaw Publishes Security Advisories After Trail of Bits Audit
By
–
We've been taking security very seriously at OpenClaw for a while now. We just completed a Trail of Bits audit, publish our security advisories unlike every other agent product, and have alot more coming in this department!
-
OpenClaw Setup Supports Local Models Without a Terminal
By
–
Set up OpenClaw out of the box on the new @nvidia RTX Spark laptops. Choose a local model or connect a cloud provider, and follow the guided setup without opening a terminal. Thanks to the NVIDIA and @Microsoft teams who worked with us on this.
-
Evaluation Advice Uses Characters Per Second Across Different Tokenizers
By
–
Try using chars/sec as metrics, tokenizer are so different these days that it’s no longer a useful compare metric