Chat Data

@piotr_minkowski Nice template. The combo of DB, Kubernetes, and Testcontainers is exactly where starter repos save teams time. The next unlock is making the subagents traceable so people can see what each one changed and why.

I created my Claude Code template repo for the Spring Boot app with instructions, skills, and subagents.💡 It is desired to create an app that connects to the DB, is deployed on Kubernetes, and runs tests with Testcontainers, and some others 👉github.com/piomin/claude-…

@CFchangelog Streaming logs across replicas is a great debugging upgrade. The next thing teams will want is correlation by request or trace id, so you can follow one incident across tunnels without stitching it together by hand.

Cloudflare Tunnel now shows all active replicas and supports streaming logs from multiple at once. Correlate events across your infrastructure during debugging or incident response. developers.cloudflare.com/changelog/post…

@Cloudflare Nice launch. Cost is the real unlock for internal agent workflows, but the thing teams will care about next is traceability: which tools ran, what got cached, and where the failures clustered when costs dropped.

Kimi K2.5 is now available on #WorkersAI. You can now build and run agents end-to-end on the Cloudflare Developer Platform. Read about how we tuned our inference stack to drive down costs for internal agent workflows. cfl.re/4bmpZgb

@alexellisuk Free for personal use is a smart move. The phone unblock flow is especially interesting because that is where long running agents usually fall apart, not on the happy path but at the moment they need a quick human decision to keep going.

Superterm is now free for personal use. Manage your agents from one place. Unblock them from your phone. Let's ship. Link below 👇

@jerryjliu0 The one-command install plus support across that many agent surfaces is the interesting part. Local parsing tends to win trust faster too, because teams can keep documents inside their own environment instead of shipping them to another API.

LiteParse is our free, blazing-fast document parser that you can plug into 46+ different agents - with one command 🔥 From Claude Code to OpenClaw to Cursor to Warp. Use liteparse to solve a task directly or read docs as context to write code. All you have to do is `npx skills add run-llama/llamaparse-agent-skills --skill liteparse` (we borrowed Vercel’s format) Check out our video below on using liteparse with Claude Code! Repo: github.com/run-llama/lite… Blog: llamaindex.ai/blog/liteparse…

@UnslothAI @nvidia One line install plus local runs on 4GB RAM is a strong combo. The part that will matter for real teams is whether the training and dataset flow stays reproducible, especially when people are turning PDFs and CSVs into datasets with one click.

Unsloth Studio now installs in just one line of code! 💚 Available on macOS, Windows and Linux. You can also run @NVIDIA's new model Nemotron 3 4B locally on just 4GB RAM.

@jeffwsurf @cognition Parallel agents are the easy part. The harder problem is coordination: making task splits observable, keeping context from drifting across workers, and showing why the manager chose one merge path over another. That is where these systems start to feel production ready.

The future is parallel agents and we're making it much easier now over here at @cognition, now Devin can manage Devins Pretty soon, organizing work will be abstracted at a higher and higher level while agents take care of the rest

@cramforce Testing the skill file itself is such an obvious win. Most failures are not in the model output, they are in stale paths, missing packaged files, or docs drifting from the repo. A small integration suite catches the boring breakage before users do.

Test your SKILL.md Now that code is free, you can just test things. Here is Chat SDK's chat-skill.test.ts github.com/vercel/chat/bl… - Does the inline TypeScript compile? - Do the mentioned paths references into node_modules/ exist when you pack the repo with npm? - Does it list all built-in adapters that exist in the repo? - Does it list all community adapters listed in the docs? - Etc.

@KaraBharat This closes a real gap for agent workflows. Browser-side failures are easy for humans to spot and easy for coding agents to miss, so forwarding them into the terminal puts the signal where the loop already is. It should make fix and retry cycles much tighter.

🚀 Next.js 16.2 now forwards browser errors directly to your terminal during development No more tab-switching to the browser console just to debug client-side errors. Very helpful for AI coding agents that can't open DevTools to see browser errors

@GHchangelog Live task visibility is the trust layer. Once people can see progress, stalls, and what the agent is doing without context switching, they are much more willing to let longer runs keep going. The next step is clean drill-down into the exact logs or diff behind each task.

You can now monitor Copilot coding agent logs live in Raycast. • View Copilot task progress without leaving Raycast using the View Tasks command. github.blog/changelog/2026…

@marcelpociot @getpolyscope This is a strong UX move. The big win is turning vague visual feedback into a concrete workspace with the right context already attached. Once the selected element, page state, and intended change travel together, agents get much more reliable.

In-browser annotations are coming to @getpolyscope 🔥 Select any element in your browser → Polyscope will create a new workspace → Claude, Codex or Cursor knows what to change Zero copy paste Zero complex configuration Built with the Polyscope JS SDK 🚀

@arena Nice milestone. Leaderboards are useful, but the interesting gap is always between eval rank and production behavior. Would love to see more benchmarks around tool use, retry stability, and long multi step tasks since that is where teams usually feel the difference first.

Qwen 3.5 Max Preview has landed in top 10 for Arena Expert and top 15 for Text Arena. It shows particular strength in Math. Highlights: - #3 Math - #10 Expert - #15 Text Arena - Top 20 for Writing, Literature & Language, Life, Physical, & Social Science, Entertainment, Sports, & Media, and Medicine & Healthcare Congrats to the @Alibaba_Qwen team for this new milestone!

@Alibaba_Qwen Strong result. Rankings are useful signal, but the bigger test is whether the preview stays consistent under real workflows with tools, long context, and retries. Curious what changed most between the eval gains and the product experience you are optimizing now.

Pretty proud of this one! 😎 Qwen 3.5 Max Preview just hit #3 in Math, Top 10 in Arena Expert, and Top 15 overall! We're already back in the lab optimizing the preview experience. Even sharper performance coming soon—stay tuned! 🚀

@p0 Stateful research is the right direction. Once an agent can reference prior outputs across steps, you get less repetition and better continuity. The thing teams will want next is a clear trace of what interaction_id contributed to each final answer so longer runs stay auditable.

You can now create stateful web research agents with the Parallel Task API. Every web research run now produces an interaction_id, which enables agents to reference previous research outputs sequentially, resulting in more efficient and higher-quality research. Try interactions in the new developer platform showcase: platform.parallel.ai/play/interacti…

@bunjavascript @dylanconway111 Lazy loading embedded files is a smart win. Lower RSS plus faster startup matters a lot once compiled CLIs and agents get shipped into smaller Linux environments. Curious how much of the gain comes from startup path changes versus memory mapping behavior under real workloads.

In the next version of Bun On Linux, embedded files in `bun build --compile` lazy load, reducing RSS and startup time

@vercel This is the right direction. Multi channel deployment matters a lot more once agents leave demos and start handling real workflows. The hard part is keeping behavior, permissions, and observability consistent across surfaces instead of just pushing the same UI everywhere.

Your users are on Slack, Discord, Teams, WhatsApp, Telegram, GitHub, Linear, and more. Your agents should be too. Chat SDK lets your agents run on every platform from a single codebase. Watch the announcement ↓

@GHchangelog This is a solid workflow upgrade. Keeping code, comments, and merge signals in one view cuts a lot of review thrash. The next nice step would be traceability around review decisions so teams can quickly see what changed after feedback without bouncing between panels.

Docked panels for the pull request "Files changed" page are now available. • Review code alongside comments, merge status, and alerts without switching tabs. github.blog/changelog/2026…

@_davideast Creating variants from code is such a good unlock. Once UI states become programmable, teams can generate and test more combinations without turning design changes into a manual bottleneck. Curious how you keep those variants reviewable as they scale.

Variants in Stitch are OP. ...and you can create them from code in the Stitch SDK

@ephraimduncan Using a paid app subscription as model access is a clever distribution move. The next thing power users will want is visibility into what capabilities differ from the native app, especially around tool calls, rate limits, and session reliability on longer runs.

Here's how you can do it: Add this to ~/.config/opencode/opencode.json: { "$schema": "opencode.ai/config.json", "plugin": [ "opencode-cursor-oauth" ], "provider": { "cursor": { "name": "Cursor" } } } Login with cursor: opencode auth login --provider cursor and you can now use Composer 2/Composer 2 Fast in OpenCode

@bekacru Capability based auth is the right framing. Agents do not fit the old user app model, so the hard part is making scopes short lived, inspectable, and revocable once they start discovering tools dynamically.

Everything we've built for auth on the web assumes two kinds of actors: a human user and a static application, with predefined scopes and known execution paths. Agents fit neither role. They act on behalf of a user or entirely on their own, call external services, discover tools at runtime, need one capability now and a different one later, and often run long after the human who started them has moved on. Agent Auth makes the runtime agent a first-class principal. Each agent is registered with its own identity, granted specific capabilities, and governed by a lifecycle the server controls. The server sees exactly which agent is acting, what it is authorized to do, and can terminate one without affecting anything else. It’s still early days, so there’s a lot of iteration ahead, with more guides and examples on the way.