Chat Data

@rachpradhan 150k req/s in a day is a wild iteration loop. The interesting part is not just the Zig rewrite, it is how quickly feedback from the comments turned into measurable wins. That kind of tight benchmark plus iteration cycle is exactly how infra projects compound.

We made TurboAPI hit 150k req/s. In under a day. It is now 22x faster than FastAPI Thanks to the amazing contributions from the people in the comment section, which allowed me to view what made the hyper optimized frameworks work the way that they do! Here's what changed..

@antigravity Importing Firebase Studio projects into a broader agent workflow is a smart bridge. The thing teams will care about next is how portable the traces, permissions, and environment assumptions are once that project moves between local, SSH, and hosted runs.

To all the Firebase developers exploring new AI workflows: welcome! 🤝 Import your Firebase Studio projects into Antigravity to pick up where you left off. You'll have access to Gemini models, Agent Skills, and a built-in Browser Agent. Antigravity supports core Firebase services including Auth, Firestore, and Hosting via the Firebase MCP server. It also adds new integrations like Google Search and Nano Banana, with the flexibility to run locally or over SSH to a VM.

@Cloudflare Big models on Workers AI is a strong step, but the real test is long running agent behavior under load. Curious how you are handling queueing, retries, and traceability once teams have many concurrent runs instead of single prompts.

Kimi K2.5 is now on Workers AI, helping you power agents entirely on Cloudflare’s Developer Platform. Learn how we optimized our inference stack and reduced inference costs for internal agent use cases. cfl.re/4bmpZgb

@ephraimduncan Nice bridge. Letting teams use Composer 2 through OpenCode lowers the switching cost a lot. The interesting part is whether traces and approvals stay intact across that handoff, because that is what makes agent workflows usable beyond solo tinkering.

You can now use Composer 2 in OpenCode with your Cursor Subscription

@melvynx Model quality debates get a lot clearer once people separate first draft wow from sustained runs. Clean code, UI fidelity, and respecting constraints over multiple edits is what actually makes a model useful in production workflows.

Just try Composer 2: → for new apps, it makes WAY cleaner and smarter code than Opus and Codex → makes reducers, respects clean code → respects the UI and features I ask for perfectly It's a good model. Really.

@stitchbygoogle Starter ideas are smart because blank canvas anxiety is real. The interesting part will be whether the AI Native Canvas can keep iterations inspectable, so teams can see what changed between prompts instead of just chasing screenshots.

We’ve been overwhelmed by the feedback on the new Stitch. 🫶 Now, let’s get to building. 😀 Over the coming weeks, we're dropping Starter Ideas to spark your creativity—and want to showcase what you build! 🌟 Starter Idea #1: Watch the new agent and AI-Native Canvas turn a messy doc into a fully styled portfolio. 📝 The Input: Highlight and copy your raw resume text 🎨 The Prompt: "Make me a single-page resume site in 3 fun styles" + paste your resume text ✨ Stitch turns your resume into a text canvas node where it can be referenced or edited ✨ It generates 3 unique Design Systems and layouts 🔷 The Polish: Upload a headshot, and the agent auto-crops and styles it to match the exact aesthetic of each site. We have loved seeing your creations so far. Drop your shared projects in the replies—we're putting together a plan to showcase our favorites!

@noahzweben The big unlock here is not just remote access, it is reducing friction. Once a team can reach an active Claude Code session from Telegram or Discord, long running work becomes much easier to supervise without being stuck at a laptop.

I forgot to text my mom back, but at least I can now text Claude on Telegram! Claude Code channels launching in Research Preview. Reference: code.claude.com/docs/en/channe…

@LangChain Build agents with natural language sounds great, but the trust layer is the real product here. Shared permissions, agent identity, approvals, and tracing are the pieces that make multi-team deployment realistic instead of just a demo.

Introducing LangSmith Fleet. Agents for every team. → Build agents with natural language → Share and control who can edit, run, or clone each agent → Manage authentication with agent identity → Approve actions with human-in-the-loop → Track and audit actions with tracing in LangSmith Observability Try Fleet: smith.langchain.com/agents?skipOnb…

@UnslothAI Local tool use on a 4B model is a bigger deal than the benchmark headline. Once small models can search, cite, and call tools reliably, the bar for useful on-device agents drops a lot. Curious how stable it stays over longer multi-step runs.

Qwen3.5-4B searched 20+ websites, cited its sources, and found the best answer! 🔥 Try this locally with just 4GB RAM via Unsloth Studio. The 4B model did this by executing tool calls + web search directly during its thinking trace.

@ClaudeCodeLog Checking memories against current files before use is a subtle but important fix. Agent quality falls apart when stale context feels authoritative. Restoring parallel tool results on resume matters too, because losing that execution history makes debugging long runs much harder.

Claude Code 2.1.80 has been released. 1 flag change, 17 CLI changes, 1 system prompt change Highlights: • Memories are checked against current files before use to avoid relying on stale data • Sessions restored with --resume include all parallel tool results, replacing '[Tool result missing]' errors • Many previously blocked SQL analysis functions reinstated, restoring prior SQL workflows and outputs Complete details in thread ↓

@ClaudeCodeLog The memory change is the real trust upgrade here. Treating stored memory as historical context instead of ground truth should cut a lot of subtle drift. The parallel tool results fix matters too, because missing intermediate output is exactly how long runs turn opaque.

@Palanikannan_M There is a real product lesson in that. A lot of people want better visibility and faster switching, not another layer on top of the terminal. The best agent UX usually looks boring from a distance because it stays close to the tools people already trust.

pov: you tried cmux and realized tmux was right there the whole time all i needed was "is my agent done?" and fast switching. not a new app. runs inside ghostty. same tmux shortcuts. freakishly fast

@livekit Adaptive interruption handling is a bigger deal than it looks. Real conversations are full of backchannels and noise, and agents that cut off too early feel robotic fast. Curious how well it generalizes across accents, crosstalk, and different mic setups.

How can a voice agent tell when you’re actually interrupting it? VAD is too sensitive—laughs, “mm-hmm,” or a sneeze shouldn’t stop the agent. We trained an audio model for adaptive interruption handling so agents can distinguish real interruptions from noise.

@neilhtennek Channels are such a natural fit here. Once an agent lives in the same surfaces people already use, response time and follow up get way better. The big unlock is keeping enough context across messages without turning the thread into a black box.

Today we're launching channels for Claude Code as an experimental feature! A few days ago, I was fed up that I couldn't text Claude on the go like I would any of my friends. But those days are gone! Claude is saved in my contacts and I can keep shipping on the go.

@upstash Giving agents filesystem, shell, and git inside isolated containers is exactly the right abstraction. The next thing teams want is a clean run trace so they can see what the agent changed, what commands ran, and how to replay failures.

New blog: Upstash Box for AI-SDK agents 🎉 ◆ Give AI-SDK agents filesystem, bash, and git access ◆ Isolated cloud containers for secure execution ◆ Works with AI-SDK v6 out of the box Step-by-step guide 👇

@_dylanga @tryramp @modal This is the part most teams skip. Once an agent can inspect its own traces and logs, you finally get a closed feedback loop instead of just more automation. The session level visibility is especially strong.

The first thing I did at @tryramp was set up distributed tracing, structured logging, and metrics for Inspect, our background coding agent. We now have full visibility in to everything the system is doing: the browser, CF workers/DOs, @modal sandboxes, database calls, etc. Most importantly, Inspect now has visibility in to itself. It can self-triage runtime errors it encounters and create PRs to fix them. Every morning, it reviews the past 24 hours of its own @datadoghq dashboard, identifies systemic issues, new errors, and long tail latencies, and has a summary + PR waiting for me at 9am.

@grinich Session scoped access plus server side tokens is the right shape for real agent tool use. The thing teams will care about next is traceability: which tool was used, what scope it had, and what got blocked when a run went sideways.

WorkOS Launch Week - Day 4 🔌 Pipes MCP 🔌 Give your agents secure, time-bound access to third-party tools. 🔐Scope access by session to prevent persistent access 🛡️ Audit every call and keep tokens server-side 📡 Connect to Google, Slack, GitHub, Snowflake, and more Read the blog: workos.com/blog/pipes-mcp

@supabase @vercel @GoogleDeepMind Zero to Agent is a smart angle. A lot of teams can ship the demo day, but the hard part is what happens after: auth, memory boundaries, and making each agent observable once it goes live. Curious how much of the workshop goes into production guardrails, not just prototyping.

San Francisco, NYC, London builders, this one’s for you ⚡️ We’re partnering with @vercel, @GoogleDeepMind, and Cerebral Valley to help you go from Zero to Agent 👇🧵

@kiwicopple @supabase Continuous Stripe sync into Postgres is one of those features that looks simple but removes a lot of glue code. Support for branches is especially nice since it makes it much easier to test billing workflows safely before they touch production data.

we've updated the Stripe Sync Engine on @supabase continuously sync your Stripe data to Postgres. updates: ◆ added support for Coupons ◆ you can use it on Branches ◆ admin controls: restricted to Admins/Owners ◆ ux refresh: A smoother, faster interface

@joshtriedcoding Isolated containers plus per agent filesystem and shell access is exactly the right direction. The thing teams will care about next is traceability: what files changed, what commands ran, and how easy it is to replay or audit a run when an agent goes sideways.

writing an article about AI SDK v6 running AI agents in isolated containers with their own filesystem and shell access 👀