AI

Ruflo can coordinate hundreds of agent, memory, policy, federation, and

v3.32.29 is the corrective stable publication of the Capability Brain work

Name new sessions with /new or /clear, pin important threads, and switch between side conversations without closing them. (34605, 34840, 35011)

fix(core,a2a): group cancelled tool responses and coalesce consecutive roles to prevent 400 Bad Request by @luisfelipe-alt in https://github.com/google-gemini/gemini-cli/pull/28407

Restored compatibility with legacy MCP SDK clients.

dc2f851: Warn when xAI Responses models ignore unsupported sampling settings.

Updated dependencies [2e2224b]

A stability-focused patch: the unified omo.jsonc config surface is now the single source of truth, migration is far more resilient across platforms, model routing got a tune-up, an…

bash

Spend less, earn more - even smoother buying and selling across the app. More to come!

cicd: git app token for next release (cdfb14c)

We're introducing Cursor Start , a new ₹649 monthly plan for developers in India, making daily agentic development accessible and payment easy with local pricing and UPI.

Portability, hook-safety, and resolution-accuracy fixes.

core: Sign S3 object paths with strict RFC 3986 encoding (34871) (95ad6f6)

Improved compatibility with newer MCP servers and OAuth flows.

The updated detector, in your browser. The extension ships the current rule engine: the new kicker-above-heading ban, the radial-spotlight-glow rule, stylesheet stripe scanning, an…

Kickers are banned. New kicker-above-heading rule flags the first eyebrow label above any heading, replacing the old advisory that waited for three repeats. Breadcrumbs, datelines,…

Bug fixes and performance improvements.

ECC 2.1 turns plan review into a visual loop and opens the harness to self-hosted models. Plan Canvas lets you review agent plans in the browser. Point at the part you mean instead…

Ships the latest version of the CLI, which includes bug fixes and better browser management.

Fixes for incremental extraction correctness, graph loading, uninstall scoping, macOS paths, and Swift extraction.

core: Avoid loading execution data during credentials security audit (34912) (0b61a96)

Thank you for using the Walmart app! We've made a few enhancements to provide a seamless experience, so you can save time and money.

Fixed an MLX Metal bug that could reduce output quality for NVFP4 models, particularly Laguna.

A release focused on making your spiders smarter about the websites they crawl

This release tightens the machinery around long-running agent work. Completion and team messages now arrive through authoritative notifications instead of blocking polls, CodeGraph…

add git checkout support (be1844c)

Agent Skills 0.6.5 graduates the eval framework from opt-in to CI-enforced, hardens the validators, and kicks off an ecosystem-neutral pass so the skills stop assuming a JavaScript…

Claude Opus 5 — Available on Anthropic and Amazon Bedrock with adaptive thinking (including xhigh), inference profiles, and prompt caching. See Providers.

Support Laguna on Apple GPUs via the MLX engine

bash

Constrained tool sampling — Tools can prefer or require strict JSON Schema sampling or use OpenAI Lark/regex grammars, with model capability metadata preventing unsupported request…

Two structural changes to how SDD tracks progress and closes out review findings, both developed against live eval campaigns.

We've launched Claude Opus 5 ( claude-opus-5 ), a step-change improvement over Claude Opus 4.8. Claude Opus 5 supports a 1M token context window (both the default and the maximum), 128k max output tok…

Four root-cause fixes from the post-v13.12.2 issue batch.

The bug. On a version mismatch, hooks asked the running (stale) worker to restart itself — and the dying worker spawned its successor using its own install's code and resolver. A ≤…

0.16.1 is a focused patch release for the design preview.

Released: 2026-07-22

Refactor: exclude transient CI configuration files from workspace context by @DavidAPierce in https://github.com/google-gemini/gemini-cli/pull/28216

13628 - App sidebar layout with redesigned profile menu, org switcher & agent activity (by @Abhi1992002)

UI improvements and bug fixes

🎨 92 PRs · 20 contributors · 5 days — A more reliable path from creation to delivery. Open Design 0.16.0 strengthens automatic updates, long-running tasks, model setup, image gene…

Squashed some bugs and improved the overall experience. Yours, Claude

You can now set an effort level on a Claude Managed Agents agent's model configuration. Pass effort inside the model object when you create the agent . See Effort levels for what each level does. Webh…

Auto mode is now powered by Cursor Router.

这一版你可以做两件全新的事：把 xAI 的 Grok CLI（Grok Build）交给 CC Switch 管理——它成为第八个受管应用，供应商一键切换、MCP / Skills 同步、代理接管与用量统计一应俱全；以及把 Grok 接进 Claude Code、Claude Desktop 和 Codex——既可以直接用 xAI Grok 账号登录（设备码…

Release Date: July 20, 2026

Released: 2026-07-20

Bug fixes and performance improvements.

13543 - Refresh README for public platform (by @ntindle)

Release 0.13.6 with Browser Harness 0.1.6 by @gregpr07 in https://github.com/browser-use/browser-use/pull/5245

This patch solves a few issues which appeared when integrating Inkling model, most notably an issue affecting models using EncoderDecoderCache during assisted generation. It also f…

Generated from commits between v5.2.4 and HEAD

Add Inkling model 47347 by @molbap @Cyrilvallez @eustlb and @zucchini-nlp

<!-- Release notes generated using configuration in .github/release.yml at master --

<h1 align="center"