Anthropic documented experimental Claude Code agent teams: set CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 so a lead session can spawn independent teammate sessions that share a task list and message each other directly. Off by default, interactive-only (no -p/SDK), and uses significantly more tokens than a single session or subagents.
Meta open sourced Apache 2.0 ESP32 and Linux SDKs so builders can connect Muse to displays, buttons, sensors, and actuators on off the shelf boards or a Raspberry Pi. It’s also waitlisting Muse Home Link (5,000 units, US Muse subscribers) for Wi Fi home device control via community skills…
Yokka is a kanban board for coding agents over MCP—Claude Code, Codex, Cursor, VS Code, ChatGPT—so cards move when an agent claims work, asks for input, or finishes, instead of you tabbing terminals. Code stays on your machine; an optional outbound only runner can start agents from your phone…
Anthropic launched Claude Frontier Academy with a $100M commitment to train 10,000 Frontier Deployed Engineers by end of 2027—first cohorts include Accenture, Bain, Capgemini, Deloitte, McKinsey, and others. Engineers run a multi day in person sim, then a 12 week residency leading a real Claude deployment at their own org…
Cloudflare launched a Web Search API through AI Gateway with Ceramic.ai, Exa, and Linkup—so agents can ground answers on live results instead of guessing URLs. Call it via REST or Workers bindings ( env.AI.websearch ); usage draws AI Gateway credits, supports BYOK, and partners commit to verified bot crawling rules…
Claude Code 2.1.287 turns on Mods by default: small JS/TS plugins that hook tool calls, prompts, and UI so you can rewrite behavior or draw custom panes—Anthropic already uses them for /diff and AGENTS.md. Install via /plugin ; they run with full machine access, so only load mods you trust…
Spotted something we missed? Start a thread.
