What changed in my AI tools?
Pick the tools you use. You will only see their recent changes, each linked to the vendor's official changelog or release notes. Your picks are saved in this browser.
NewBreakingPricingFix
Your tools
Wednesday
-
ChatGPTNew
Texting your dot
Texting your dot is starting to roll out in beta to Pro users in the U.S. Your dot is now just a text away. Reach your dot safely and securely, through iMessage or RCS.
help.openai.com (official source, opens in a new tab) -
ChatGPTPricing
API credits for eligible ChatGPT Pro and Business plans
Eligible ChatGPT Pro and Business subscribers can activate promotional API credits to build apps and agents with the OpenAI API. The credits apply to a linked API organization and are separate from ChatGPT usage credits.
help.openai.com (official source, opens in a new tab) -
CopilotNew
Route and orchestrate models with GitHub Copilot Fusion
GitHub Copilot Fusion is generally available. Instead of picking a model for each task, choose Copilot Fusion and let Copilot intelligently route and orchestrate which models it uses for you.
github.blog (official source, opens in a new tab) -
CopilotNew
GitHub Copilot app, Universe releases
Work doesn’t always fit in a single repository or session. A feature can span several repositories. A launch plan can pull in specs, designs, and assets without touching a repository at all.
github.blog (official source, opens in a new tab) -
CopilotNew
GitHub Enterprise now includes access to GitHub Copilot
Enterprises working with a GitHub or Microsoft account team can now get Copilot included with GitHub Enterprise for every licensed user.
github.blog (official source, opens in a new tab) -
CopilotNew
Security extension for the GitHub Copilot app
You can now work through your repository’s GitHub code scanning alerts without leaving the GitHub Copilot app.
github.blog (official source, opens in a new tab) -
CopilotNew
GitHub intelligence puts your code, context, and history to work
Agents should understand more than your codebase—they should understand how your team works. Your preferences, repository conventions, skills, and custom instructions guide how changes should be made, while code in related repositories can…
github.blog (official source, opens in a new tab) -
CopilotNew
Build shared workflows for your team with Copilot Automations
Shared Copilot Automations are rolling out, enabling teams to build and maintain AI-powered workflows together. With Copilot Automations, you can combine prompts, triggers, and tools to design workflows around the way your team works.
github.blog (official source, opens in a new tab) -
CopilotNew
GitHub Copilot in VS Code, Universe releases
This year, we focused on giving you more choice in how you work with GitHub Copilot in Visual Studio Code: which models you use, where your agents run, and how you stay involved.
github.blog (official source, opens in a new tab) -
CopilotNew
Generate and edit images directly in Copilot
You can now generate and edit images using natural language in GitHub Copilot. When you ask for an image, your selected reasoning model calls a dedicated image-generation tool powered by GPT Image 2.5 Flare, previews the result inline, and…
github.blog (official source, opens in a new tab) -
CopilotNew
GitHub Copilot Fusion now supports selection of local models
Today we are shipping intelligent routing for local models into experimental preview. GitHub Copilot Fusion can now choose between supported on-device models and cloud models, enabling intelligent local model routing in GitHub Copilot CLI,…
github.blog (official source, opens in a new tab) -
CopilotNew
GitHub Agentic Workflows generally available
GitHub Agentic Workflows , an open source project from GitHub Next, is now generally available. With agentic workflows, you can automate reasoning-based tasks like issue triage, CI failure analysis, documentation updates, and test writing…
github.blog (official source, opens in a new tab) -
OpenAI APINew
Eligible ChatGPT Pro and Business subscribers can now claim up to $500 per month in free API credits as a…
Eligible ChatGPT Pro and Business subscribers can now claim up to $500 per month in free API credits as a subscription benefit. Activate the benefit from ChatGPT or API Platform by linking an API organization you own.
platform.openai.com (official source, opens in a new tab)
Tuesday
-
ChatGPTNew
iCloud Mail and Calendar plugins in ChatGPT
iCloud users can now connect Mail and Calendar to ChatGPT to find emails, catch up on your inbox, check your schedule, and update calendar events. You can learn more about how ChatGPT uses connected apps here .
help.openai.com (official source, opens in a new tab) -
Claude CodeNew
Claude Code v2.1.312
39 changes (4 added, 13 improved/changed, 22 fixed). Added oidc.user_id_claim to the Claude apps gateway, to identify people by an id_token claim other than sub , such as Microsoft Entra ID's… · Added click to send: in fullscreen, clicking the "to send now" hint under a queued message sends it right away, as its key does
github.com (official source, opens in a new tab) -
Gemini APINew
Gemini API CLI (gemini-api) beta
Released the [Gemini API CLI](https://ai.google.dev/gemini-api/docs/cli) (gemini-api), a stateless, zero-dependency command-line client for AI coding agents, scripts, and CI pipelines.
ai.google.dev (official source, opens in a new tab) -
LovableNew
Events & hooks for your workspace
Workspace admins and owners on Business and Enterprise plans can now extend their workspace with their own services using Events & Hooks .
docs.lovable.dev (official source, opens in a new tab) -
LovableNew
Connect your app to Scrive
You can now connect your Lovable app to Scrive for e-signatures and electronic identification (eID). Scrive eSign sends documents for signature and tracks their signing status.
docs.lovable.dev (official source, opens in a new tab) -
LovableNew
Redesigned sidebar
The sidebar now organizes your projects and chats into three sections: Pinned , Projects , and Recent chats . Pinned replaces Starred and shows the projects and chats you pinned, with the most recently pinned first.
docs.lovable.dev (official source, opens in a new tab) -
LovableNew
Knowledge is now Instructions
In workspace and project settings, Knowledge is now Instructions . Workspace knowledge and project knowledge are now called workspace instructions and project instructions. They work the same way, so nothing changes for your projects.
docs.lovable.dev (official source, opens in a new tab)
Monday
-
ChatGPTNew
GPT-6.1 Terra
GPT-6.1 Terra is rolling out in ChatGPT Work and Codex. It supports a range of tasks, including visual reasoning, computer use, and writing. The rollout includes Plus, Pro, Business, Enterprise, and Edu plans.
help.openai.com (official source, opens in a new tab) -
Claude CodeBreaking
Claude Code v2.1.311
92 changes (5 added, 31 improved/changed, 54 fixed). Added --hold-idle-file and --max-hold-min to self-hosted-runner , to keep an idle session while your host reports processes it left running · Added a tip for the Explanatory output style, shown when you ask Claude for explanations
github.com (official source, opens in a new tab) -
ElevenLabsNew
Fast LLM service tier
ElevenAgents can now run supported LLMs on a fast service tier, which trades a per-token price premium for higher token throughput and lower latency.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
Knowledge base crawl exclusions
ElevenAgents knowledge base website crawls can now skip parts of a site. Pass up to 50 exclude_patterns to Create crawl job, or fill in the Exclude patterns field in the whole-website crawl dialog, and URLs that match any pattern are…
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsBreaking
Clone strength for v4 voices
Text to Speech and Text to Dialogue requests now accept clone_strength, a value from 0 to 1 that controls how closely a Professional Voice Clone fine-tuned for a v4 model follows its training samples.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
Expiring service account API keys
Workspaces service account API keys can now expire. Pass expires_at_unix when you create or update a key, or pick an Expire after value in the dashboard, and the key stops working after that time.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
All changes
Fast LLM service tier: Agents and workflow overrides accept service_tier (standard or fast) on supported models. List LLMs returns available_service_tiers for each model, and the LLM usage calculator accepts service_tier.
elevenlabs.io (official source, opens in a new tab) -
Gemini APINew
Generate Content API storage on by default
New projects using the Generate Content API (generateContent, streamGenerateContent, and batchGenerateContent) on the paid tier now store requests by default (store=true), matching the Interactions API.
ai.google.dev (official source, opens in a new tab) -
LovableNew
Manage IdP group mappings in one place
Workspace admins and owners on Business and Enterprise plans now map IdP groups to workspace roles in the Provisioning groups section of the workspace's Identity settings. On Enterprise plans, SCIM provisioning uses the same mappings.
docs.lovable.dev (official source, opens in a new tab) -
LovableNew
Redesigned connector pages
Each connector's page now has a Connect button that creates the first connection type the connector supports. More options lists the other types.
docs.lovable.dev (official source, opens in a new tab) -
LovableNew
Scroll through all files in the Files tab
Your project's Files tab now loads more files as you scroll , so you can browse a large project's files in one list.
docs.lovable.dev (official source, opens in a new tab) -
OpenAI APINew
Released GPT-6.1 Terra, a fast, efficient model for visual reasoning, precise computer use, and clear,…
Released GPT-6.1 Terra, a fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. See the GPT-6 guide for prompting and migration guidance.
platform.openai.com (official source, opens in a new tab) -
WindsurfFix
Windsurf v3.11.228
In Remote-SSH and Remote-WSL windows, the Agent Window folder picker correctly sets the session’s working directory. It lists the window’s remote folders and no longer offers local ones.
windsurf.com (official source, opens in a new tab)
Sunday
-
BoltNew
Update skills imported from GitHub
Skills you import from GitHub now stay linked to their folder in the source GitHub repository, so you can pull in updates if the skill changes in GitHub.
support.bolt.new (official source, opens in a new tab)
Saturday
-
WindsurfFix
Windsurf v3.11.216
Members whose org role has no Devin Cloud session permissions can see, open and start Devin Local sessions again.
windsurf.com (official source, opens in a new tab)
Friday
-
Claude APINew
The Claude Tag API is available in beta for Claude Enterprise organizations with the experimental-claude-tag-2026-10-21…
The Claude Tag API is available in beta for Claude Enterprise organizations with the experimental-claude-tag-2026-10-21 beta header.
platform.claude.com (official source, opens in a new tab) -
Claude CodeNew
Claude Code v2.1.310
26 changes (3 added, 8 improved/changed, 13 fixed). Added the Monitor tool and plugin monitors on Bedrock, Vertex, and Foundry, and when telemetry or nonessential traffic is disabled; long… · Changed the error for an MCP tool call that times out in a non-interactive session while the server's elicitation is unanswered: it now…
github.com (official source, opens in a new tab) -
ReplitNew
Monitoring Agent
Meet your autonomous on-call engineer. Agent can investigate production issues using your app's logs and metrics, then attempt and validate fixes. Turn on Monitoring alerts and Auto-fix to have Agent triage alerts in the background.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
Create and update skills with Agent
Turn useful workflows from your conversations and projects into reusable workspace skills. Agent can suggest new skills or improvements to existing ones, which you review and approve before saving to your workspace's skills library.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
Chat and asset sharing
Share a whole chat or a single asset with selected teammates or your whole workspace. Chat access is read-only and includes the chat's assets and development URLs. Development URLs open live servers, not isolated read-only previews.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
Stripe Atlas on Replit
Ask Agent to help incorporate your business through Stripe Atlas, with 20% off when you incorporate through Replit. See the Stripe Atlas announcement.
docs.replit.com (official source, opens in a new tab) -
ReplitPricing
Keep your apps running when credits run out
Eligible top-up customers can keep published apps running at zero credits, up to an overage limit. Paid Agent pauses, Free mode stays available, and warning emails arrive before suspension. New credits repay the overage first.
docs.replit.com (official source, opens in a new tab) -
WindsurfNew
Windsurf v3.11.212
New Agent Window The Agent Window now runs the same interface as the Devin web app: the sessions sidebar, session view, Automations, Review, Wiki, settings, and Command Palette (⌘K) match app.devin.ai, and follow your Devin Desktop theme.
windsurf.com (official source, opens in a new tab)
Thursday
-
Claude APINew
We’ve launched Claude Models on Google Cloud (Anthropic managed), the Claude API operated by Anthropic and reached…
We’ve launched Claude Models on Google Cloud (Anthropic managed), the Claude API operated by Anthropic and reached through your Google Cloud project. Google Cloud IAM controls access. Google Cloud Marketplace handles billing.
platform.claude.com (official source, opens in a new tab) -
Claude APINew
Fast mode is available for Claude Opus 5.5 on Claude Models on Google Cloud (Anthropic managed).
Fast mode is available for Claude Opus 5.5 on Claude Models on Google Cloud (Anthropic managed).
platform.claude.com (official source, opens in a new tab) -
Claude CodeBreaking
Claude Code v2.1.309
79 changes (1 added, 15 improved/changed, 58 fixed). Changed sed -i to get the standard Bash prompt and run as written, not a simulated file-edit preview; like other Bash edits, it is no… · Changed claude ultrareview to require workspace trust: it asks on a terminal, else refuses; scripts pass --trust-workspace , which takes no…
github.com (official source, opens in a new tab) -
Claude CodeFix
Claude Code v2.1.308
1 changes (0 added, 0 improved/changed, 0 fixed). Bug fixes and reliability improvements
github.com (official source, opens in a new tab) -
LovableNew
Clearer Privacy & security settings
The Privacy & security settings have reworded labels and descriptions that say what each setting controls. Changes with a wide effect, such as enabling automatic deletion of abandoned projects or restricting code downloads, now open a…
docs.lovable.dev (official source, opens in a new tab) -
LovableNew
Folder access applies to personal folders only
When a personal folder becomes a workspace folder, the access levels you granted stop applying to the projects inside it. The people and groups you invited keep their workspace role and any access you gave them on a project directly.
docs.lovable.dev (official source, opens in a new tab) -
LovableBreaking
Gemini 2.5 chat models are retired for your app's AI features
The Gemini 2.5 Pro , Gemini 2.5 Flash , and Gemini 2.5 Flash Lite chat models ( google/gemini-2.5-pro , google/gemini-2.5-flash , and google/gemini-2.5-flash-lite ) are no longer available for your app's AI features.
docs.lovable.dev (official source, opens in a new tab) -
OpenAI APINew
The Decisions API is now generally available with gpt-6-luna.
Cache shared input across requests for prompt-cache discounts, include images in individual question instructions, and pass structured data directly with input_json.
platform.openai.com (official source, opens in a new tab)
Wednesday
-
Claude APINew
We’ve released API version 2026-10-21. Migrating to API version 2026-10-21 shows how to upgrade.
We’ve released API version 2026-10-21. Migrating to API version 2026-10-21 shows how to upgrade.
platform.claude.com (official source, opens in a new tab) -
Claude APINew
We’ve released new versions of the client SDKs and the ant CLI that send API version 2026-10-21 by default: Python SDK…
We’ve released new versions of the client SDKs and the ant CLI that send API version 2026-10-21 by default: Python SDK 2.0.0, TypeScript SDK 1.0.0, C# SDK 13.0.0, Go SDK 2.0.0, Java SDK 3.0.0, PHP SDK 1.0.0, Ruby SDK 2.0.0, and ant CLI…
platform.claude.com (official source, opens in a new tab) -
Claude APIBreaking
The new SDK and CLI versions also have breaking changes that don’t depend on the API version, and they are licensed…
The new SDK and CLI versions also have breaking changes that don’t depend on the API version, and they are licensed under Apache 2.0 instead of the MIT License. See SDK and CLI changes.
platform.claude.com (official source, opens in a new tab) -
Claude APINew
We’ve added the enforcement_status and enforcement_actions fields to user profiles, so you can see whether Anthropic…
We’ve added the enforcement_status and enforcement_actions fields to user profiles, so you can see whether Anthropic has restricted or banned one of your end customers.
platform.claude.com (official source, opens in a new tab) -
ChatGPTPricing
MoMo payments in Vietnam
You can now use MoMo to pay for ChatGPT Go, Plus, and Pro subscriptions purchased on chatgpt.com in Vietnam. Subscriptions purchased through the iOS or Android app continue to be managed by the Apple App Store or Google Play.
help.openai.com (official source, opens in a new tab) -
ClaudeNew
Claude Duet research preview for Pro and Max plans
We just opened a research preview for users on Pro and Max plans: Claude Duet, a new app where Claude works as a proactive agent. For more information, see our blog post: Introducing Claude Duet .
support.claude.com (official source, opens in a new tab) -
Claude CodeNew
Claude Code v2.1.307
43 changes (4 added, 11 improved/changed, 24 fixed). Added /claude-api api-version to move Claude API code to API version 2026-10-21 · Added the claude_code.safety_event OpenTelemetry event for each tool call a permission rule, auto mode, a safety check, a hook or the…
github.com (official source, opens in a new tab) -
Claude CodeFix
Claude Code v2.1.306
2 changes (0 added, 0 improved/changed, 2 fixed). Fixed claude -p inside cloud sessions reporting "Not logged in" when started without the session's environment variables
github.com (official source, opens in a new tab) -
LovableNew
See adoption by department without SCIM
Workspace admins and owners on Business and Enterprise plans can now see adoption by department in Insights when your workspace uses SSO without SCIM. To set it up, map the department attribute in your SAML or OIDC app.
docs.lovable.dev (official source, opens in a new tab) -
OpenAI APINew
You can now choose which service tiers projects can use in Platform settings.
Organization settings can restrict service tiers for all projects. See service tier errors.
platform.openai.com (official source, opens in a new tab)
Tuesday
-
Claude APINew
Inference hooks are out of beta for Claude Enterprise organizations.
Inference hooks are out of beta for Claude Enterprise organizations.
platform.claude.com (official source, opens in a new tab) -
Claude APINew
We’ve launched user profiles, so you can tell Anthropic which of your end customers each API request is for.
If you operate a platform or gateway, or resell API access, a safety enforcement action can then apply to one end customer instead of your whole organization. The SDK and the ant CLI support the new /v1/user_profiles endpoints.
platform.claude.com (official source, opens in a new tab) -
Claude APINew
We’ve added organization webhooks to the Admin API, in beta with the webhooks-2026-10-07 beta header.
Its /v1/organizations/webhooks endpoints register webhook endpoints for two event types: one for when Anthropic restricts or bans one of your organization’s user profiles, and one for when the restriction or ban ends.
platform.claude.com (official source, opens in a new tab) -
Claude APINew
Organization admins can now turn off web fetch for their organization on the Capabilities page of the Claude Console.
With web fetch off, a Messages API request that includes the web fetch tool fails with a 400 error. In a Claude Managed Agents session, web_fetch calls return an error result to the agent instead.
platform.claude.com (official source, opens in a new tab) -
ChatGPTNew
Introducing locked chats
Locked chats let you keep selected conversations in your account while hiding them from regular chat history, pinned chats, and search. Open them with your 4-digit account PIN or supported device authentication.
help.openai.com (official source, opens in a new tab) -
Claude CodeNew
Claude Code v2.1.305
38 changes (4 added, 11 improved/changed, 19 fixed). Added sandbox.allowNestedUserNamespaces so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets… · Added CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS so unattended retry mode ( CLAUDE_CODE_RETRY_WATCHDOG ) notices a usage limit that…
github.com (official source, opens in a new tab) -
CursorNew
Agent SDK
Define an agent as a folder of code, test it with evals, and deploy it to Cursor or your own infrastructure. The Agent SDK is available today.
cursor.com (official source, opens in a new tab) -
LovableNew
Group your workspaces into an organization
Enterprise companies that run several Lovable workspaces can now manage them together in an organization . The company sets up SSO once for all of them, and with SCIM the identity provider adds and removes members automatically.
docs.lovable.dev (official source, opens in a new tab) -
LovableNew
Let Lovable create your Supabase project
You can now ask Lovable to create a Supabase project for an app that has no backend. You choose the organization and the region, and Lovable creates the project there and connects it to your app.
docs.lovable.dev (official source, opens in a new tab) -
LovableNew
App + chat connectors: LlamaParse Platform and n8n
LlamaParse Platform lets apps parse documents and extract structured data from them, such as the parties and dates in a contract. Use it for document review tools, knowledge base assistants, and apps that read the files your users upload.
docs.lovable.dev (official source, opens in a new tab) -
LovableNew
Seedream 5 Pro and Seedance 2.5 for your app's AI features
Your app's AI features can now use two new ByteDance models: Seedream 5 Pro ( bytedance/seedream-5-pro ) generates and edits images from a text prompt and up to 10 reference images, for posters, ads, and designs.
docs.lovable.dev (official source, opens in a new tab) -
OpenAI APINew
You can now choose 12-hour prompt caching in the API.
12-hour prompt caching keeps shared instructions, tools, and context cached longer to benefit from lower cached-input pricing, even when requests are hours apart. 12-hour cache writes cost 2.5x the input token price. Read more here.
platform.openai.com (official source, opens in a new tab)
Monday
-
Claude CodeBreaking
Claude Code v2.1.304
76 changes (10 added, 19 improved/changed, 43 fixed). Added a transcript line when a plugin that runs first skips one of your mod's hooks, naming the event and the plugin · Added decider: "person" to a mod's tool.check answer: only the permission dialog or a host's callback can approve the ask, and it is…
github.com (official source, opens in a new tab) -
ElevenLabsNew
Eleven Realtime
Eleven Realtime is a new family of models for ElevenAgents voice agents, rolling out gradually across workspaces. Each one is a complete voice agent configuration.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
Realtime Translation
Realtime Translation turns speech in one language into speech in another while the speaker is still talking. It's a WebSocket API, available now for enterprise workspaces.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
Video to Music
Video to Music writes a soundtrack for your video. The Video to music API is now available: you upload a video and get back music that fits it, without writing a music prompt from scratch.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
ElevenAgents
Alerts: Alerts notify a workspace when agent error rates exceed a threshold or rise sharply above their recent baseline.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
Music and Sound Effects
Zero Retention Mode: Music generation, composition plan, stem separation and video to music endpoints, plus Sound Effects, accept enable_logging=false to use Zero Retention Mode. Zero Retention Mode is available to enterprise customers.
elevenlabs.io (official source, opens in a new tab) -
PerplexityNew
Ultrafast Computer models, Decisions API, and connector controls
Choose Ultrafast models in Computer, classify and score content with the Decisions API, and control connector access by role.
perplexity.ai (official source, opens in a new tab) -
v0New
Connect Slack to v0
Connect your Slack workspace to v0 to bring team conversations into your work. With the Slack MCP integration, v0 can find relevant messages and post updates to Slack when you ask.
v0.app (official source, opens in a new tab)
Sunday
-
BoltNew
Do more in Bolt from your phone
Bolt on mobile now covers more of your workflow, so you can keep building away from your desk: Preview your app: A preview card now appears in the chat after each build. Tap it to open the preview in full screen.
support.bolt.new (official source, opens in a new tab) -
BoltPricing
Billing through Link starts November 1
Starting November 1, 2026, Link, a payment service built by Stripe, will handle billing for Bolt plan and domain subscriptions. Your plan and token allowance stay the same, and you don't need to do anything.
support.bolt.new (official source, opens in a new tab) -
BoltPricing
Pay in your local currency
When you subscribe through Link, you might see your local currency at checkout alongside USD. Checkout shows the exchange rate and your total, including any tax.
support.bolt.new (official source, opens in a new tab) -
Claude CodeFix
Claude Code v2.1.303
1 changes (0 added, 0 improved/changed, 0 fixed). Bug fixes and reliability improvements
github.com (official source, opens in a new tab)
Friday
-
ChatGPTNew
Create and collaborate on slides in ChatGPT
ChatGPT Slides lets you create presentations and keep working on them with your team in Space. Start from a conversation, files, or an outline, or share an example deck to guide the style and layout. Create and refine.
help.openai.com (official source, opens in a new tab) -
ChatGPTNew
Updates to GPT-6 Pro model in ChatGPT
GPT-6 Pro in the chat tab now offers: Faster responses Improved use of plugins and tools to carry out tasks. Multiple agents that can work on different parts of a task in parallel.
help.openai.com (official source, opens in a new tab) -
CursorNew
Cloud Agent Canvases and Environment Improvements
Cloud agents can now build and share interactive canvases. The Environments API is available in beta, environments support up to 300 repos, and large environments load 5x faster.
cursor.com (official source, opens in a new tab) -
OpenAI APINew
Released prompt-to-voice for all API customers. Create a custom voice from a text description through the API…
Released prompt-to-voice for all API customers. Create a custom voice from a text description through the API or voice Playground, then reuse it in GPT-Live sessions.
platform.openai.com (official source, opens in a new tab) -
OpenAI APINew
OpenAI-hosted sandboxes in the Agents API now include the Artifact SDK and skills for creating and editing…
OpenAI-hosted sandboxes in the Agents API now include the Artifact SDK and skills for creating and editing spreadsheets, presentations, and Word documents. Added Ultrafast mode to the Agents API.
platform.openai.com (official source, opens in a new tab) -
ReplitNew
Claude Haiku 5.5 in the model selector
Builders on Core and Pro can now choose Claude Haiku 5.5 from the model selector in Power Mode. Learn more about choosing a model.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
Find a Replit Solutions Partner
You can now browse the Replit Solutions Partners directory to find agencies, consultants, and systems integrators that build with Replit. Firms that want to join can apply through the new program. Explore the Solutions Partners directory.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
Bring Your Own Cloud to Replit
Bring Replit to your enterprise cloud environment for greater control over where your platform and apps run. Choose how you build and run with Replit in your own cloud: Full BYOC (private preview): Run the full Replit platform in your…
docs.replit.com (official source, opens in a new tab) -
v0New
Downloads in the Code tab, new iOS pickers, and preview fixes
What's new Large files that cannot be previewed can be downloaded from the Code tab, which shows a clear message and keeps a Download action in the file header.
v0.app (official source, opens in a new tab)
Thursday
-
Claude APINew
We’ve added capabilities.thinking.types.between_tools to the Models API.
GET /v1/models and GET /v1/models/{model_id} now report whether each model accepts thinking: {type: "between_tools"}, which turns off up-front thinking. See Using the Models API.
platform.claude.com (official source, opens in a new tab) -
Claude APINew
The Compliance API now returns the text each organization member saved as Instructions for Claude in claude.ai and as…
The Compliance API now returns the text each organization member saved as Instructions for Claude in claude.ai and as Global instructions in Cowork, in beta for Claude Enterprise organizations.
platform.claude.com (official source, opens in a new tab) -
Claude APINew
Fast mode is out of research preview for Claude Opus 5.5, and you no longer need to request access.
Requests to Claude Opus 5.5 no longer require the fast-mode-2026-02-01 beta header, and requests that still send it keep working. Claude Opus 5.5 now has a default fast mode rate limit in the Start, Build, and Scale usage tiers.
platform.claude.com (official source, opens in a new tab) -
Claude APINew
Fast mode for Claude Opus 5.5 is now available on Claude in Microsoft Foundry for deployments hosted on Azure.
Fast mode for Claude Opus 5.5 is now available on Claude in Microsoft Foundry for deployments hosted on Azure.
platform.claude.com (official source, opens in a new tab) -
ChatGPTNew
GPT-Live-1.1 and new voices in ChatGPT
We’re rolling out GPT-Live-1.1 and GPT-Live-1.1 Quip, a mini version of the model, in ChatGPT Voice, with more natural accents across languages. Live also uses a wider range of short phrases to let you know when it’s searching.
help.openai.com (official source, opens in a new tab) -
ChatGPTNew
Applications for the Rosalind Academic Plan
The Rosalind Academic Plan helps eligible academic labs use ChatGPT for life sciences research. Approved labs can receive up to 30 ChatGPT Business Standard seats at no cost for up to 12 months, with GPT-Rosalind access subject to…
help.openai.com (official source, opens in a new tab) -
ChatGPTFix
Site limits (Plus and Pro)
There is no longer a fixed limit on the number of Sites you can create. Usage and storage limits continue to apply. For usage and limits, see: Creating and using ChatGPT Sites .
help.openai.com (official source, opens in a new tab) -
OpenAI APINew
Added native Decisions integration in GPT-Live. Your app can act while your user is speaking or react to what…
Added native Decisions integration in GPT-Live. Your app can act while your user is speaking or react to what Live says.
platform.openai.com (official source, opens in a new tab)
Tuesday
-
CursorNew
Origin App Marketplace
Origin integrates with over 20 apps for deployments, CI, code review, security, monitoring, and project management, and the marketplace is now open to public submissions.
cursor.com (official source, opens in a new tab) -
GeminiNew
Introducing Gemini 4 Argon: our frontier model for complex tasks
Starting today, Gemini 4 Argon is rolling out globally for Google AI Pro & Ultra subscribers in the Gemini app. 4 Argon is our newest frontier model, built to take your most complex tasks from start to finish.
gemini.google (official source, opens in a new tab) -
GeminiNew
Code, prototype, and build with Google Antigravity in the Gemini macOS app
Google Antigravity is now built into the Gemini macOS app, so go straight from brainstorming in chat to coding apps, building web experiences, and prototyping ideas.
gemini.google (official source, opens in a new tab) -
GeminiNew
An easier way to customize how Gemini works for you and more connected apps
Open the left menu and click Customize to tailor how Gemini responds and connects to your everyday tools in one place.
gemini.google (official source, opens in a new tab) -
Gemini APINew
Gemini 4 Argon (gemini-4-argon) generally available (GA)
Released Gemini 4 Argon (gemini-4-argon), our most capable model built for complex coding, agentic, math, and science tasks. For API changes, pricing, and migration guidance, see What's new in Gemini 4 Argon.
ai.google.dev (official source, opens in a new tab)
Monday
-
ElevenLabsNew
ElevenAgents
Merge and search triage tickets: Merge tickets folds up to 50 open tickets from the same agent into one target ticket. Merged tickets keep the status merged and reference the target through merged_into_ticket_id.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
Text to Speech
Audio effects: Text to Speech and Text to Dialogue requests accept an optional audio_effects object. It applies a filter preset, perceived distance, a reverb environment, a looped background noise bed and stereo panning to the generated…
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
Speech to Text
Turn prediction commit strategy: The realtime Speech to Text WebSocket adds turn_prediction as a commit_strategy value.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
Voices
Voice collections API: Voice collections can now be managed through the API. Create, list, update and delete collections, and add or remove voices. See List voice collections.
elevenlabs.io (official source, opens in a new tab) -
ElevenLabsNew
Workspaces
Basic seat fallback: Update member accepts allow_downgrade_to_basic_seat. When unlocking a user whose original seat type has no seats available, the user is moved to a basic seat instead of the request failing.
elevenlabs.io (official source, opens in a new tab) -
WindsurfFix
Windsurf v3.10.67
Added support for connecting to MCP servers on protocol revision 2026-07-28 ( server/discover , no initialize ). Enterprise admins can now set an Extension marketplace URL in the Devin Desktop team settings.
windsurf.com (official source, opens in a new tab)
Sunday
-
BoltNew
Comment on your project and send comments to Bolt
You can now leave comments directly on your project's preview. Each comment pins to the spot where you add it, so feedback stays with the part of the page it's about.
support.bolt.new (official source, opens in a new tab) -
BoltNew
Change the preview theme
You can now switch the preview between System, Light, and Dark themes from the More preview controls (…) menu above the preview. Preview theme only changes how the preview looks, not Bolt's own appearance.
support.bolt.new (official source, opens in a new tab)
Friday
-
ChatGPTNew
Composer predictions in Codex
Composer predictions, available in beta, suggests your next message based on the conversation in your current Codex thread. After Codex responds, a suggestion may appear in the message box.
help.openai.com (official source, opens in a new tab) -
OpenAI APINew
You can now pre-warm an OpenAI-hosted sandbox before attaching it to an Agents API session.
Prewarming improves latency by creating and configuring the sandbox before a user finishes sending their message. This means the user doesn't have to wait for all this work to complete.
platform.openai.com (official source, opens in a new tab) -
ReplitNew
Replit Desktop Windows preview with Microsoft and NVIDIA
Replit Desktop can now build and run apps locally on your Windows PC, available in private preview. Agent runs each build in its own isolated sandbox powered by Microsoft Execution Containers (MXC) and NVIDIA OpenShell.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
Work across projects from a chat
You can now ask Replit to find your existing projects, read their files, and send tasks to them, all from a chat. Name a project or describe what it does, then use that context without switching between projects.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
Create and manage TikTok Ads
Create, launch, and track TikTok ads from a chat in Replit. Connect your TikTok Ads account through MCP, then ask Replit to set up a campaign with your budget and schedule and report on its performance.
docs.replit.com (official source, opens in a new tab)
Thursday
-
Gemini APIBreaking
Gemini 3.7 Flash deprecation
gemini-3.7-flash is deprecated and has been replaced by gemini-3.8-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.7-flash are automatically routed to gemini-3.8-flash.
ai.google.dev (official source, opens in a new tab) -
Gemini APIBreaking
Gemini 3.5 Flash deprecation
gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. It is no longer available to select in Google AI Studio, and API requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash.
ai.google.dev (official source, opens in a new tab) -
Gemini APIBreaking
Deep Research Agent deep-research-pro-preview-12-2025 deprecation
The deep-research-pro-preview-12-2025 agent is deprecated and will be shut down on October 23, 2026. Migrate your requests to one of the newer Deep Research agent versions: deep-research-preview-04-2026: Designed for speed and efficiency,…
ai.google.dev (official source, opens in a new tab) -
MidjourneyNew
Testing Thinking Mode
hi everyone! We're testing a new "Thinking Mode" for image generation on our Alpha website ( alpha.midjourney.com ) and we'd love your feedback.
updates.midjourney.com (official source, opens in a new tab) -
MidjourneyNew
Alpha Changelog - 10/7/26
Hi everyone, here's this week's round of changes on alpha.midjourney.com . The highlight this week is shared folders, a new way to collaborate on Midjourney.
updates.midjourney.com (official source, opens in a new tab) -
OpenAI APINew
Added Ultrafast mode for GPT-6.1 Sol in the Responses API.
Use gpt-6.1-sol with service_tier: "ultrafast" to reduce the time between generated output tokens. It is available to all API users, subject to rate limits, with global processing and US and EU data residency. See Ultrafast pricing.
platform.openai.com (official source, opens in a new tab)
Wednesday
-
ChatGPTNew
GPT-6 and Intelligent UI in ChatGPT
We’re introducing GPT-6 with Intelligent UI in ChatGPT . ChatGPT can now combine text, visuals, and interactive elements to fit your question, from side-by-side comparisons and diagrams to tools you can use directly in the conversation,…
help.openai.com (official source, opens in a new tab) -
ClaudeNew
Claude Haiku 5.5 launch
We just launched Claude Haiku 5.5, the cheapest, fastest, and most capable small model we’ve released, designed for high-volume, cost-sensitive tasks. For more information, see our blog post: Claude Haiku 5.5 .
support.claude.com (official source, opens in a new tab) -
OpenAI APINew
Updated the chat-latest snapshot, which points to the latest model available in ChatGPT for Plus, Pro,…
Updated the chat-latest snapshot, which points to the latest model available in ChatGPT for Plus, Pro, Business and Enterprise users.
platform.openai.com (official source, opens in a new tab)
Tuesday
-
ChatGPTNew
Audio uploads in ChatGPT
Upload audio files to ChatGPT to create transcripts, summarize recordings, and ask questions about their contents. You can turn a meeting, interview, or lecture into structured notes or a follow-up email draft.
help.openai.com (official source, opens in a new tab) -
CursorNew
Remote control for local agents
See and reply to the local agents running on your computer from the Cursor iOS app. You can now see and reply to the local agents running on your computer from the Cursor iOS app.
cursor.com (official source, opens in a new tab) -
Gemini APINew
Gemini Nano Banana 2.1 generally available (GA)
Released Gemini Nano Banana 2.1 (gemini-nano-banana-2.1), the latest high-efficiency image generation and conversational editing model.
ai.google.dev (official source, opens in a new tab) -
Gemini APIBreaking
Deprecation announcement
The gemini-3.1-flash-image model is deprecated (no shutdown date announced). Migrate to gemini-nano-banana-2.1.
ai.google.dev (official source, opens in a new tab) -
OpenAI APINew
Released the Decisions API in beta with gpt-6-luna.
Turn text and images into typed answers 10x faster than the Responses API.
platform.openai.com (official source, opens in a new tab) -
OpenAI APINew
Simplified API usage tiers from five to three: Build, Launch, and Grow.
Organizations automatically upgrade as total credit purchases reach tier minimums. See usage tiers for monthly usage limits and how to view rate limits for each model.
platform.openai.com (official source, opens in a new tab) -
v0New
Personal accounts are now team workspaces
Personal v0 accounts are now team workspaces, giving everyone access to v0's collaboration features. If your account was migrated, your chats, projects, and settings moved automatically to your new team workspace.
v0.app (official source, opens in a new tab)
Monday
-
OpenAI APINew
Added an in-product flow for HIPAA compliance support in API Organization settings > General.
Admins of eligible organizations can now accept the standard Business Associate Agreement (BAA) and enable HIPAA compliance support for their organization.
platform.openai.com (official source, opens in a new tab) -
PerplexityNew
Automations, inline visualizations, and GPT-6.1 Sol
Run ongoing work with Automations, explore interactive visualizations in your thread, use GPT-6.1 Sol and Claude Opus 5.5, create videos with MiniMax H3 and Seedance 2.5, and run Amex-curated business Skills.
perplexity.ai (official source, opens in a new tab)
Sunday
-
BoltNew
Control whether Bolt uses your content for model training
A new Model training setting in your account settings lets you choose whether Bolt can use your projects and chats to train AI models. It's on by default, except for accounts based in the EU, UK, or Switzerland, where it's off by default.
support.bolt.new (official source, opens in a new tab)
Friday
-
ChatGPTNew
Finances expands to Free and Go users
Finances in ChatGPT is rolling out to Free and Go users in the U.S. on web, iOS, and Android. You can securely connect your financial accounts to find ways to save, understand your spending, and make sense of your investments, with answers…
help.openai.com (official source, opens in a new tab) -
MidjourneyNew
Alpha Changelog - 10/1/26
ICYMI – last week, we launched a few features on alpha.midjourney.com that we're really excited about: style previews in the sidebar so you can see what you’ll get before you generate, larger images in create, and setting default…
updates.midjourney.com (official source, opens in a new tab) -
ReplitNew
Jev is now available through Replit AI Integrations
Build apps that classify content, route requests, and score leads with fast, structured AI decisions, without managing API keys. To get started, ask Agent to use jev-latest through OpenRouter in Replit AI Integrations.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
New models from OpenAI and Anthropic
You can now choose GPT-6.1 Sol and Claude Sonnet 5.5 when building with Agent. Sonnet 5.5 is available in Power Mode, and GPT-6.1 Sol is available in Max Mode. To learn more about our approach to models, see our recent blog post.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
New Settings page
Settings now opens as its own page instead of a modal. Integrations and Security get their own pages too. Your project or chat stays open underneath, so leaving Settings puts you right back where you were.
docs.replit.com (official source, opens in a new tab) -
ReplitNew
Workspace settings
Set rules company-wide, make exceptions for specific teams (Workspaces), and let team admins (Workspace admins) manage certain settings on their own. Learn more about advanced settings.
docs.replit.com (official source, opens in a new tab)
Wednesday
-
GeminiNew
Let skills in Gemini tackle your most repetitive tasks
Today we’re rolling out skills directly into the Gemini chat globally 1 . Skills are a reusable set of instructions that tell Gemini how to handle specific tasks. Think of them as saved shortcuts to faster prompting.
gemini.google (official source, opens in a new tab)
Tuesday
-
OpenAI APINew
Added computer use to the Agents API. Agents can complete tasks in an OpenAI-hosted browser, with website…
Added computer use to the Agents API. Agents can complete tasks in an OpenAI-hosted browser, with website access approvals and sign-in handled by your application.
platform.openai.com (official source, opens in a new tab) -
v0New
Use your ChatGPT subscription in v0
ChatGPT Plus and Pro subscribers can now use their ChatGPT subscription to build in v0. Once connected and enabled, eligible AI responses count towards your ChatGPT plan instead of using v0 credits.
v0.app (official source, opens in a new tab) -
WindsurfNew
Windsurf v3.10.48
Sign in with ChatGPT You can now sign in to Devin with ChatGPT and use your eligible ChatGPT Plus or Pro plan for GPT model usage in Devin Desktop.
windsurf.com (official source, opens in a new tab)
Tags (New, Breaking, Pricing, Fix) are assigned by simple keyword rules, not by reading the change the way a person would. Pricing is a breaking change whose rule matched a money word such as pricing, billing, credits or quota. Hover a tag to see why it was given. Always check the official source before acting on a change.
Only your tools' changes, once a week
One short email with what changed in AI tools that week, straight from official changelogs. No spam, unsubscribe any time.
Where this data comes from
17/17 sources fetched 2026-10-29 15:39 UTC
| Tool | Official source | Status | Entries | Newest |
|---|---|---|---|---|
| Cursor | Cursor changelog (RSS) | ok | 12 | Oct 20, 2026 |
| Claude Code | anthropics/claude-code GitHub releases | ok | 10 | Oct 27, 2026 |
| Windsurf (Devin Desktop) | Windsurf / Devin Desktop changelog | ok | 14 | Oct 26, 2026 |
| GitHub Copilot | GitHub Changelog — Copilot label (RSS) | ok | 10 | Oct 28, 2026 |
| ChatGPT | ChatGPT release notes (OpenAI Help Center) | ok | 15 | Oct 28, 2026 |
| Claude (apps) | Claude release notes (Claude Help Center) | ok | 11 | Oct 21, 2026 |
| Gemini (app) | Gemini Apps release notes | ok | 6 | Oct 13, 2026 |
| Perplexity | Perplexity changelog | ok | 5 | Oct 19, 2026 |
| v0 | v0 changelog | ok | 11 | Oct 19, 2026 |
| Lovable | Lovable changelog (RSS) | ok | 15 | Oct 27, 2026 |
| Bolt | Bolt release notes (support.bolt.new) | ok | 15 | Oct 25, 2026 |
| Replit | Replit docs — weekly updates | ok | 15 | Oct 23, 2026 |
| Midjourney | Midjourney updates (RSS) | ok | 11 | Oct 8, 2026 |
| ElevenLabs | ElevenLabs changelog | ok | 15 | Oct 26, 2026 |
| OpenAI API | OpenAI API changelog | ok | 15 | Oct 28, 2026 |
| Anthropic (Claude) API | Claude Platform release notes | ok | 15 | Oct 23, 2026 |
| Gemini API | Gemini API changelog | ok | 15 | Oct 27, 2026 |
Collected by npm run refresh from each vendor's own changelog, release notes, RSS feed or docs. Entries keep the vendor's date and link. Nothing is written by hand or generated.
About the change digest
Where does the change data come from?
Only from each vendor's official changelog, release notes page, RSS feed or docs changelog (17 of 17 sources fetched in the last refresh). Each entry keeps the vendor's own title, date and link; nothing is written by hand or generated.
How current is it?
A refresh script re-reads every source and rebuilds the site. The last refresh was 2026-10-29 15:39 UTC, covering the last 90 days.
How are New, Breaking, Pricing and Fix assigned?
By keyword rules, or by the vendor's own label where it has one. Words like "deprecated", "removed" or "billing" mean breaking or pricing; "fixed" or "bug" mean fix. Hover a tag to see which rule fired. Tags can be wrong, so check the official source before acting.
Can I follow changes without visiting the site?
Yes: subscribe to the Atom feed for all tools, or the feed on any tool's changelog page. A weekly email is coming soon.