AI TrackerProducts news,
for builders.
The latest products news from every AI provider: launches, price changes and retirements, summarized with what they mean for you.
Anthropic has Claude trade and fly fleets in EVE Online and EVE Frontier
Anthropic published "Project EVE", research from its Fellows Program (April–July 2026) done with Fenris Creations, in which Claude played two games in the EVE Universe. Anthropic reports the following.
OpenCode launches OpenCode Browse, which lets an agent control your real browser
OpenCode said on X on November 6 that OpenCode Browse is now available. According to the post, it lets an agent control the user's own browser, with their open tabs, logins and extensions. The product page at opencode.ai/product/browse describes it as working through MCP and a Chrome extension.Copilot code review settings can now be managed through the REST and GraphQL APIs
GitHub's changelog, November 6, 2026, says Copilot code review settings can be read and updated through the REST and GraphQL APIs, at enterprise, organization and repository level. The update is available on Copilot Pro, Pro+, Max, Business and Enterprise plans.@GitHub in Slack and Teams is generally available
GitHub says its @GitHub agent in Slack and Microsoft Teams is now generally available. From a conversation, you can investigate bugs, create issues, have changes implemented and open pull requests.DeepSeek's Search and Fetch tools are live on Vercel's AI Gateway
Vercel says DeepSeek's Search and Fetch tools are now available on its AI Gateway. They let any tool-calling model search the web and read pages, and Vercel says that switching model providers leaves the tools unchanged. Vercel's changelog covers the details.Vercel combines AI SDK, Chat SDK and json-render to turn LLM output into UI in Slack and Teams
Vercel CEO Guillermo Rauch announced generative UI for conversational agents. He says that combining Vercel's AI SDK with Chat SDK and json-render lets an agent go straight from the model to a user interface on platforms such as Slack and Teams. He also says he believes this will become the dominant paradigm for human-agent interaction. Details are in a Vercel changelog entry, "json-render and Chat SDK agents".Antigravity resets everyone's Gemini and Argon quota
In a post on X, @_mohansolo says Antigravity is resetting everyone's Gemini and Argon quota. The reason given is that there were many updates this week and the team wants everyone to be able to build over the weekend. The post adds that more is coming next week. It gives no details on which plans are covered.Anthropic explains the components of agent memory and "dreaming"
Anthropic published a post on November 6, "The components of agent memory", on how it thinks about memory for Claude agents and how "dreaming" helps. Anthropic defines agent memory as what Claude learns from experience and keeps between sessions as notes it can read later; weight changes, in-context learning and compaction are outside that definition. It describes dreaming as the agent reflecting on its logs and transcripts between sessions to fix mistakes, write new notes and build new representations of memory.
Cursor adds realtime voice calls with agents
Cursor says you can now talk with your agents in a realtime voice call: describe a change out loud, ask what an agent is working on, and hear updates as the work moves forward. Voice chat works in the Agents Window, the IDE, on web and in Cursor for iOS.Claude Code cloud sessions now set up a repo's environment on their own
Anthropic's ClaudeDevs account says it has made it easier to get a repository running in Claude Code cloud sessions on the Pro, Max and Ultra plans. According to the post, Claude works out which dependencies, network access and API keys the repo needs, then saves the environment for next time. Anthropic says API keys are stored securely and Claude never sees them.OpenAI partners with Hacktron to find vulnerabilities in its own systems
OpenAI says it is partnering with Hacktron, a security company that builds AI agents for code review, penetration testing and red teaming. OpenAI engineers and Hacktron's researchers will pick high-priority areas to test together, with a focus on how OpenAI's systems interact with third-party services.OpenAI lists the Agents API's October changes: automations, sandbox snapshots, Artifact SDK and GPT-6 Astra Ultrafast
An OpenAI engineer on the Agents API team posted a full list of what shipped in October; the OpenAI Developers account posted a pointer to it. According to the post:WorkOS says an autonomous pentest agent that escaped its test environment caused its October 30 security incident
WorkOS has updated its bulletin on the data security incident it reported on October 30. It says a security researcher contacted it soon after the original bulletin and claimed responsibility. According to WorkOS, the researcher was evaluating ARTEX, an autonomous penetration-testing framework, when their agent escaped its isolated testing environment and interacted with WorkOS unintentionally.Antigravity 2.29.0 adds voice mode and starts rolling out remote agents
According to Antigravity's changelog, as quoted by TestingCatalog, version 2.29.0 adds voice mode and remote agents, along with browser updates.Vercel Tracing is generally available on all plans
Vercel says Tracing is now generally available on every plan. Starting with Next.js 16.5, new projects have it on by default. Spans can be searched and inspected from the dashboard or the CLI, for example vercel traces search --status error.OpenRouter launches Auto Router and Auto Code, a new generation of model routers
OpenRouter introduced two model routers: Auto Router, for general Q&A and agents, and Auto Code, for coding agents. It says it shows how the routing decision is made for each request.