New in portless:
Opt in to whole-branch worktree hostnames with { "worktree": { "prefix": "branch" } }
feat/checkout and fix/checkout get their own URLs instead of both being `checkout`
๐ We launched OpenBot in August - beyond excited to have reached the 1.0 today
OpenBot was re-designed and renamed in the days following the release of agent workspaces by the big labs.
We saw a strong need for an agent workspace that is open, self-hostable, customizable, and not tied to big token.
@CopilotKit has been leading the agent-user interaction layer for years, and our building blocks are trusted by the majority of the Fortune 500.
So we knew we could ship an amazing product, that can plug in to any agent harness (via AG-UI), and can be enterprise-grade from the start.
The launch got over 850k views on X, and much more elsewhere and OpenBot quickly became the leading open agent workspace.
Our releases of OpenDots, OpenMuse and OpenDuet received millions of views 16k more GitHub stars.
Today - these are all rolled into OpenBot as UX 'skins' with important milestones in the 1.0 release. Including:
๐ฅ๏ธ Desktop app, runs fully local
๐ง Any model, or your existing Claude/ChatGPT/Gemini/xAI plan
๐ Bring any agent: Claude SDK, LangChain, ADK, Strands (AG-UI)
๐ Teach a Bot: record a task once, it learns it
๐ค Subagents that ping you when needed
๐ฎ Generative UI: charts, tables, cards
๐งฐ Hundreds of apps via Composio and Arcade
๐ข Enterprise: SSO, SCIM, audit trail, self-host
The goal is simple:
A great experience for end users.
Real governance for enterprises.
Any custom agent for developers.
Open, and built for all three.
Try it at https://t.co/edm5ThvpJs
Vercel MCP is now open to any MCP client.
Clients no longer need to be allowlisted to request access to Vercel. Just host a JSON metadata file on your domain, and Vercel will display your name, logo, and hostname on the consent screen.
https://t.co/wOowjGK30M
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges.
Theyโre capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
Claude Fable 5.2 is available today! It generates output up to 30% faster than Fable 5.1.
Fable is best for the most ambitious, open-ended technical work. I'd still start most work on Opus 5.5. It's our strongest daily driver and what we recommend for most coding and knowledge tasks.
Fable 5.2 is available on all paid plans on the Claude Platform and on all major cloud platforms. If you try it, I'd love to hear how it went. The cases where it didn't help are useful for us to hear about too.
https://t.co/SIsDHNbNO7
Generative UI for conversational agents.
Combining @aisdk with Chat SDK and ๐๐๐๐-๐๐๐๐๐๐, you can go straight from LLM to UI on platforms like Slack and Teams.
I believe this will become the dominant Human-Agent Interaction (HAI) paradigm:
https://t.co/MHxtLyoy7t
๐๏ธ ๐ ๐๐ ๐ฐ๐ฒ๐น ๐ฎ๐ ๐๐ ๐ ๐๐ฑ๐๐ฎ๐ป๐ฐ๐ถ๐ป๐ด ๐๐ ๐๐ผ๐ฟ๐ฒ๐ฎ
On Nov 4, our CEO @inureyes presented LLM/VLM inference with MLxcel on AMD Strix Halo.
MLxcel 0.8 adds an AMD ROCm backend.
โก๏ธ https://t.co/q2xmR6qheN
Thanks to @AMD for the opportunity!
#Lablup#AMD