Making developer experience better. App coming soon.

Joined September 2026
Your MCP plugin doesn't have to finish in one breath anymore ⏳🔌 @ClaudeDevs added MCP Tasks and Elicitations to Claude. Tasks let Claude hand a plugin a long job, like deep research, and get the result when it's done. xitter.cf/ClaudeDevs/status/2113…
We’re adding support for MCP Tasks and Elicitations in Claude. Tasks let Claude give plugins long-running jobs such as deep research and report back when they’re done.
1
6
🛠️ Try it if you build MCP servers: pick your slowest tool (a big export, a crawl, a full test run) and make it a Task, so it returns right away and reports back later. Then add one Elicitation before anything risky, like a delete or a payment.
1
4
Our take: an agent that asks one good question beats one that guesses fast 🤝 Which tool would you make async first? 👀 #MCP #ClaudeCode Follow along. Our app is coming soon 🚀
5
Run Node.js, Bun or Envoy? Go patch today 🩹 @OpenAI found a remote code execution bug in Brotli while red-teaming their training setup with agents. A bad compressed payload could take over a server, or a client like curl --compressed 😬 xitter.cf/OpenAI/status/21137663…
During this red-teaming exercise, we also found a vulnerability that allows for unauthenticated remote code execution in Brotli, a widely-deployed compression library included in many pieces of software such as Node.js, Bun, and Envoy. The flaw could let an attacker run their own code on affected systems by sending or replying with malicious compressed data, without any need to create a user account. That is, an unpatched server that accepts compressed input could be taken over by a malicious client, and an unpatched client that accepts compressed input (such as “curl --compressed”) could be taken over by a malicious server. This root cause issue was actually fixed in the Brotli source code in February, but it wasn’t known at the time that it gave rise to a security vulnerability and there was no more recent release of Brotli. Since Brotli is built into other software, any software which includes this library needs to take the update too, followed by the users of that software. We disclosed the vulnerability to Brotli and other downstream projects such as Node.js, which released or are currently releasing security updates, and Brotli cut new release versions and published a CVE. More details on the patch and mitigations below: patchtheplanet.org/brotli
1
12
Fixed versions 👇 🟢 Node.js 22.23.4, 24.22.1, 26.12.1 🟢 Bun 1.4.4 🟢 Envoy 1.40.0, or the latest patch on your branch Then rebuild your Docker images and restart every worker and cron job. An old container keeps the old runtime 😅
1
2
🛠️ Can't patch yet? Reject requests with Content-Encoding: br before any body parser runs. gzip can stay on. Our take: the scary bugs live in the boring libs nobody reads. Nice to see agents digging there 🕵️ #NodeJS Follow along. Our app is coming soon 🚀
3
A tiny model just beat a big LLM at catching leaked keys 🔑🤏 @github swapped its LLM secret scanner for a small fine-tuned ModernBERT classifier. 11.5% more accepted alerts, 86% faster scans, 98% cheaper to run. xitter.cf/github/status/21144796…
1
3
How it works 👇 🔎 Regex casts a wide net for anything key-shaped 🧠 The model reads the file path, var names and nearby code 🚫 "example", "dummy" and test fixtures get filtered out Fast enough that generic secrets now get caught at push time, not after.
1
1
🛠️ Try it: turn on push protection in your repo's security settings. Agents love dropping a real key into a test file 😅 Our take: not every job needs a giant model. Small, narrow and well trained wins a lot 🧠 #GitHub Follow along. Our app is coming soon 🚀
1
Your agent built the iOS feature. Now it can tap through it too 📱🤖 @cursor_ai: Cursor can now control your computer. Agents can drive desktop apps like the iOS Simulator to test the features they build. xitter.cf/cursor_ai/status/21136…
Cursor can now control your computer. Agents can drive desktop apps like the iOS Simulator to test the features they build.
2
19
🛠️ Try it: after your agent ships a UI change, ask it to open the Simulator, tap through the new screen and list what looks off.
1
2
🔒 Close apps with private stuff first. It's driving your real desktop 👀 Our take: "works on my machine" just got a second tester 😄 #Cursor Follow along. Our app is coming soon 🚀
5
Your agent doesn't need to write an essay to pick "billing" or "technical" 🎯⚡ @OpenAIDevs made the Decisions API generally available: it returns a typed answer (a probability, a choice or a score) instead of a full model response. xitter.cf/OpenAIDevs/status/2113…
Add near real-time decisions to your workflow with the Decisions API, now generally available. Build faster, more cost-efficient apps and agents that can classify text and images, evaluate inputs, and determine what happens next without generating a full model response.
1
8
🛠️ Try it: find the step where your agent asks a big model "which tool next?" or "is this safe?" Send it to POST /v1/decisions with gpt-6-luna and a choice question listing your options. Low confidence? Route it to a human.
1
6
Launch numbers: Datadog scores the risk of agent-written shell commands before running them, 40x faster at p95. Sierra picks next actions in under 280 ms p95. Our take: fast, cheap checks are how agents get guardrails 🛡️ #OpenAI Follow along. Our app is coming soon 🚀
12
Your coding agent can read your API keys. What happens when a prompt injection asks for them? 🔑😬 @vercel says it's time to retire long-lived static keys: they surveyed 1,000+ SaaS vendors and only 8.4% support secure auth. xitter.cf/vercel/status/21133972…
It's time to retire long-lived static credentials. We surveyed 1,000+ SaaS vendors and found only 8.4% support secure auth. This is our call to action and how we're doing our part. vercel.com/blog/death-to-lon…
2
18
The fix is short-lived tokens (OIDC) 👇 ✅ Your app gets a signed token that expires on its own ✅ A leaked copy dies fast, no painful key rotation ✅ On Vercel it already covers Blob, AI Gateway and Sandbox, plus AWS, GCP and Azure via federation
1
18
🛠️ Try it: list the keys in your .env that never expire. Pick one cloud key (AWS, GCP or Azure) and swap it for OIDC federation this week. Our take: agents + forever keys = a breach waiting for the right prompt 🛡️ #DevSecOps Follow along. Our app is coming soon 🚀
18