Popular News
Latest News
Top Stories
View all
Anthropic opened a private beta for self-hosted Claude Managed Agents
On November 12, Anthropic opened a private beta so you can host Claude Managed Agents yourself — the harness, sandboxes, credentials, and session history. Docs say each model call still sends the conversation to a provider. Here’s what I’d check.
AWS shipped a local stand-in for its APIs — and says agents wrote the code
On November 11, AWS released AWS Emulator, a local stand-in for its APIs that the CLI, SDKs, and coding agents can talk to on your machine. The company also says autonomous agents wrote the code. Here’s what I’d actually check.
Neo4j wants coding agents to remember how things connect, not just how they look
On November 11, Neo4j launched Relate, an open-source embedded graph database it says coding agents can install and query without standing up a server. Here’s what the company claims, and what I wouldn’t assume from the post.
Texas Instruments wants coding agents to know the chip, not just the code
On November 10, TI said it strengthened agentic AI in CCStudio: device context for the agents you already use, plus a migration skill it says can shrink MCU porting from months to days. Here’s what the release actually claims.
Automattic’s Spacefast wants your coding agent to keep its AI — and still have somewhere to ship
Automattic launched Spacefast on November 9: keep ChatGPT, Claude, Cursor or another agent, get a ready stack and a private live link for team comments. Here’s what the release actually ships today, and what it says is still coming.
PDD Kit asks a different review question: did the agent keep the plan?
Microsoft Research and GitHub Next’s PDD Kit turns plain-language intent into a Verus spec, proves agent-written Rust against it, and labels what’s only tested. Here’s how the Pet Store login demo works and where the proof stops.
OpenRouter’s Auto Code wants to pick the model for every turn of your coding agent
OpenRouter rebuilt its Auto Router and launched Auto Code, a router tuned for coding harnesses that picks a model per turn, tries not to break your cache, and switches when tests keep failing. Here’s what it claims and what I’d check.
Kiro bots want to own a slice of your dev work, not just one task
From Mexico: Kiro just made bots GA in Kiro Crew — named, long-running agents with their own memory, scoped permissions and schedules that run parallel sessions for you. Here’s what it changes, and what I’d test before trusting it.
Google’s coding agent just ported a 40-year-old ocean model to safe Rust in under an hour
From Mexico: Google says Antigravity with Gemini 4 Argon rewrote a 174k-line Fortran coastal ocean model core into safe Rust in 59 minutes, caught old bugs, and open-sourced the skill. Here’s what the run claimed — and what I’d verify.
GitHub Copilot is now one more agent in JetBrains Air, plugged in over ACP
From Mexico: GitHub Copilot now runs inside JetBrains Air over the Agent Client Protocol, locally or in sandboxed cloud tasks on your Copilot plan. Here’s what works, what Air can’t see or limit, and why the protocol matters more.
