GitHub (google-antigravity/antigravity-cli) · Oct 27, 2026 · 2:23 PM

Antigravity CLI 1.4.8 speeds up /diff in big repos and stops forked conversations inheriting a /goal

Released Oct 27, /diff now opens as soon as tracked changes are ready, loads untracked files and older turns in the background, and skips reading binaries or untracked files over 1 MB, while Auto mode's sandbox-escape review gets more time so it asks you to approve safe commands less often. Failed or canceled tool calls now reach the agent as errors it can recover from, and forks or /btw side questions no longer inherit an active /goal they can't stop.

Read at github.com

Google Antigravity

Agentic development platform with IDE, CLI, SDK, and local agents

More news

View all

Google Cloud's IAM Helper gives coding agents skills to debug 403s and request just-in-time access

Announced Oct 26, four open Agent Skills ( iam helper for troubleshooting , policy management , policy simulator , privileged access management ) sit on read only Google managed MCP servers so Gemini CLI, Claude Code, Cursor and ADK agents can trace a 403, simulate a policy change against 90 days of access logs, or request a time bound PAM grant. Diagnostics run on their own, but any policy change pauses for human approval, and risky bindings like allUsers or roles/owner get flagged; install with npx skills add google/skills…

Google Cloud Blog 9 minutes ago

OpenCode 2.2.0 adds shareable desktop plugins and drops its GitHub Action

Released Oct 27, OpenCode lets you create, install and share experimental desktop plugins, and plugins can now add keyed session instructions that survive compaction without busting the prompt cache. Heads up: the OpenCode GitHub Action is no longer published, @opencode/ai now exports the Promise API at its root (Effect moved to @opencode/ai/effect ), and TUI plugins need OpenTUI 0.7…

GitHub (anomalyco/opencode) 2 hours ago

Bito's Governor routes Claude Code, Cursor and Codex requests by task risk and feeds them code context

Launched Oct 27, you point your agent's base URL at Governor, which picks a model and reasoning level per request from the models your team allows, holds that choice for the whole task, and answers code searches itself with file and line results. Bito reports one customer's Claude Code cost per task fell 48% ($4.12 to $2.14) with success held at 100%; access is by request…

Bito Blog 3 hours ago

DeepSeek V4.1 Flash lands in Cursor's model picker at $0.60 to $0.98 per CursorBench task

Added Oct 26 with no BYOK proxy needed, the open weight 1M context model turns on under Cursor Settings Models, and Cursor says all four effort tiers (44.9% to 47.7% on CursorBench 4.0) sit on its cost frontier. It still trails Opus 5.5 Max's 57.8%, and as a third party model it bills outside your plan's included usage…

Cursor Docs 4 hours ago

Devin merges its Progress and Shell tabs into one searchable Activity stream, and shows artifacts inline

In release 2026.10.26 (Oct 26), everything Devin did now lands in one Activity timeline with search, type filters and a pinnable details drawer, with rows folded under the message they answer and shell cards listing the files they edited. Devin can also embed HTML reports, dashboards and charts right in its messages instead of only attaching them…

Devin Docs (Cognition) 5 hours ago

Spotted something we missed? Start a thread.