AI Coding Live News

Ivan Leo, who works on developer experience at Google DeepMind, shared the official docs for Antigravity's new Remote Agents feature on X on November 4. Per the docs, Remote Agents run agent sessions and tools in an isolated, Google-managed remote environment, so tasks keep going when you close your laptop or browser or switch between desktop and mobile. Sessions start from the Antigravity App, the Antigravity CLI (1.4.12+, agy --remote-agent) or the web at antigravity.google.com, and remote projects can attach GitHub repositories, Google Drive files and uploads. It is rolling out gradually to Google AI Pro and Ultra subscribers on personal accounts; it is not available on the free plan, AI Plus or business accounts. The official changelog shows this ships in Antigravity v2.29.0 (November 3), which also starts rolling out a voice mode powered by Gemini Live for handing requests to the agent by voice, redesigns the Automations page into Scheduled, Always on and Paused lists, and adds a native Jupyter notebook viewer.

@DanKornas introduced agmsg, a local messaging tool for Claude Code, Codex, Gemini CLI, and GitHub Copilot CLI. Independent agent sessions coordinate through one shared SQLite store without a daemon, network service, or human copy-paste relay; durable history can be replayed into a fresh session, with monitor, turn, both, and manual delivery modes. The Bash + sqlite3 project is MIT-licensed and offers npx, plugin, and direct-script installation paths.

@DanKornas introduced tenequm/pond, an open-source storage and search layer for AI-agent sessions. It ingests history from clients such as Claude Code, Codex CLI, and Hermes Agent, stores it locally or in user-owned S3, and exposes BM25 search, read-only SQL, and MCP access for retrieving and restoring prior decisions, fixes, and dead ends. The repository had about 69 GitHub stars at verification and uses Apache-2.0.

Guillaume Laforge (@glaforge) shipped Antigravity Brain Visualizer v0.6.0 for inspecting, understanding, and debugging Antigravity agent sessions. Highlights: single-pass Gemini 3.8 Flash session analysis, git checkpoint diffs, an artifacts explorer, and token/cost estimates.

Dan Kornas (@DanKornas) launched Apache-2.0 open-source Sortie: define tracker, coding agent, and concurrency in WORKFLOW.md beside the repo, then schedule GitHub/GitLab/Gitea/Linear/Jira issues into isolated workspaces. Adapters cover Claude Code, Copilot, OpenCode, Codex, and Kiro, with SQLite run history, retry queues, and stall detection.

OpenAI Codex/ChatGPT lead Tibo (@thsottiaux) says Astra usage for long-tail power users logged in with a ChatGPT account has been improved: same quality, and on the long tail up to ~3–4× less subscription usage drawn. Direct win for long-horizon coding-agent sessions.

Open-source (MIT) macOS terminal kooky is built for AI coding: sidebar workspaces and split panes, one-click built-in or custom agent sessions, live running/waiting/failed states, plus git worktrees, SSH workspaces, session history, and kooky-cli for scripted tab control.

VS Code 1.136 release notes confirm experimental multi-root workspace support in the editor window. Developer @Marwan_3atef notes enabling chat.agentHost.copilotAgent.multiRootEnabled (and the Claude twin) lets Copilot/Claude Chat operate across every folder in a multi-root workspace. Hooks still pin to one primary folder, so monorepos with multiple .github/hooks trees must pick a home base.

GitHub said developers no longer need to hop between a separate AI chat and their development surface. Inside the GitHub Copilot app they can start projects, run multiple agent sessions, use Quick Chat, and preview the app in a browser canvas. The pitch is a single control plane from conversation to running UI, rather than copying context across tools.

Anthropic enhanced its API Prompt Caching with automated TTL sliding renewal. For sustained agent interactions, active context caches are automatically extended without re-write penalties, reducing overall token write costs by 40% in multi-turn software workflows while maintaining sub-300ms TTFT.

Chroma unveiled Foundation, a self-improving memory architecture that compiles agent sessions into structured, hyperlinked, and versioned wiki pages on top of ChromaDB + Context-1, setting a new SOTA on the BEAM 10M memory benchmark.

OpenAI announced its first custom inference chip Jalapeño, designed to deliver higher throughput and responsive Codex coding agent sessions.