Announced Oct 7, Max 5x gets $100 and Max 20x gets $200 a month, while Team gets $20 per Standard seat and $100 per Premium seat, pooled and capped at $500, once you link a Claude Console organization in billing. The credits cover the Claude API, Managed Agents, the Agent SDK, and the playground (not Claude Code or Bedrock/Vertex), and they expire each billing cycle with no rollover.
Announced Oct 7, MXC takes one JSON policy (writable and read only paths, network, desktop access) and enforces it outside the agent with AppContainer on Windows, Seatbelt on macOS, or Bubblewrap on Linux, plus Windows only session and WSL containers and an experimental microVM. Copilot, Codex, Replit, OpenClaw, and LM Studio already support it with Claude Code listed as coming, and a Learning mode logs what an agent tried to reach so you can write a least privilege policy…
Released Oct 7, the update fixes Claude treating its last pre compaction actions as unfinished and retracting or redoing them, fixes HTTP MCP connections holding every sent request until they closed, and now loads path scoped rules and nested CLAUDE.md files when Claude reads a file via cat , head , or grep in Bash. It also makes Haiku 5.5 the default Haiku on the Anthropic API and adds agentType to the subagent status line payload…
Codex lead Tibo's Day 3 post (Oct 7) headlines GPT 6 in ChatGPT Chat, with GPT 6 Sol for paid tiers now and GPT 6 Luna for Free and Go users from Oct 8, while the models in Work and Codex stay unchanged. He also said Codex and ChatGPT Work hit a new high of 40M active users and that a banked reset is loading into every paid account, so you can save it for when you actually hit your limit…
Shown on HN Oct 7, the MIT licensed project runs one Rust binary, codync host , on your Mac, Windows, or Linux machine that drives any agent in the ACP registry with the plans you're already signed into, and you chat with each bot (its own folder, memory, and approval rules) from an iPhone app, desktop app, or terminal. Remote access goes through a free end to end encrypted Cloudflare relay, and bots can ask each other for help, like a Claude bot requesting a Codex review…
Starting in Copilot CLI 1.0.94 0 (announced Oct 7), /model lists tool calling, streaming capable models from a running Ollama instance next to the cloud ones, and you can add one for the current session without restarting. Picking a local model doesn't turn on offline mode or disable telemetry, so set COPILOT OFFLINE=true if you want that…
Spotted something we missed? Start a thread.
