https://shiprank.co.uk/weekly/Verified AI tool launches for vibe coders and builders.en-gbTue, 10 Nov 2026 13:38:24 +0000 https://github.blog/changelog/2026-11-09-claude-fable-5-5-in-github-copilot/2026-11-09-claude-fable-5-2Mon, 09 Nov 2026 09:00:00 +0000Anthropic's newest Fable model, now the default Fable model in Claude Code (2.1.321) and generally available in GitHub Copilot for Pro+, Max, Business and Enterprise users. 1M context; API price $8/$40 per 1M input/output tokens, down from $10/$50 on Fable 5.1. Also on Vercel AI Gateway. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w46/) https://www.ycombinator.com/launches/Wp5-boxes-dev-move-your-ai-coding-to-the-cloud2026-11-09-boxes-dev-launch-ycMon, 09 Nov 2026 09:00:00 +0000Cloud environment for AI coding: run unmodified Claude Code and Codex on parallel cloud machines with your full dev environment, using your existing subscriptions. Start agents from a desktop app, phone, Slack or Linear; each agent gets its own machine to test its work. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w46/) https://github.com/codenotary/agentmon-live2026-11-09-codenotary-agentmon-live-open-sourceMon, 09 Nov 2026 09:00:00 +0000Free Apache-2.0 plugin for Claude Code (2.1.308+) with a live dashboard of agent and subagent activity, token and cost visibility, and a 'Done Gate' that checks for failed tests or unfinished tasks before the agent says it's done. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w46/) https://cursor.com/changelog2026-11-06-cursor-voice-chat-with-agentsFri, 06 Nov 2026 09:00:00 +0000Talk to Cursor agents in a realtime voice call from the Agents Window, IDE, web or Cursor for iOS. The voice agent hands coding work to the chat agent and gives spoken progress updates; runs on Grok Voice, with zero data retention in Privacy Mode. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://github.blog/changelog/2026-11-06-github-copilot-in-slack-and-teams-is-generally-available2026-11-06-github-in-slack-and-teams-gaFri, 06 Nov 2026 09:00:00 +0000Mention @GitHub in Slack or Teams to investigate bugs, create issues, implement changes and open pull requests from a conversation. Adds Canvas in Teams for reviewing plans, diffs and previews, plus automatic repo detection. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://github.com/openai/codex/releases/tag/rust-v0.167.02026-11-06-openai-codex-cli-0-167-agent-command-centerFri, 06 Nov 2026 09:00:00 +0000OpenAI's Codex CLI rust-v0.167.0 adds codex agents --no-daemon for an agent command center with unread markers, lets you switch backends from the session picker without losing drafts, and adds local image previews plus a Google Cloud Vertex AI setup path. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://github.com/anthropics/claude-code/releases/tag/v2.1.3192026-11-06-claude-code-2-1-319-background-mcp-tasks-deny-instead-of-promptingFri, 06 Nov 2026 09:00:00 +0000Anthropic's Claude Code 2.1.319 backgrounds MCP tool calls that run as tasks, adds permissions.denyInsteadOfPrompting so a blocked tool call fails closed instead of waiting, and ships /claude-api latency-optimize plus CLAUDE_CODE_DISABLE_FEATURE_FLAGS. It also hardens auto mode behind LLM gateways and fixes sandbox-escape and Bash permission-bypass bugs. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://github.com/NousResearch/hermes-agent/releases/tag/v0.23.02026-11-05-hermes-agent-v0-23-0-full-desktop-workspace-in-a-browserThu, 05 Nov 2026 09:00:00 +0000NousResearch's open-source Hermes Agent can now serve its full Desktop workspace in a browser tab from your own gateway (off by default). One gateway owns every session, and the release adds /rewind, pluggable delegation, plugin auto-updates and spend limits for paid MCP tools. Check the breaking changes before upgrading. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://cursor.com/changelog/build-live-apps2026-11-05-cursor-build-live-apps-from-cloud-agentsThu, 05 Nov 2026 09:00:00 +0000Cursor cloud agents can scaffold a web app, spin up Postgres when needed, configure Cursor SSO auth, run publish-time security checks, and return a live shareable link. Available on paid plans with cloud agents enabled; local agents cannot publish. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://www.perplexity.ai/hub/blog/teammates-are-agents-for-complex-ongoing-work2026-11-04-perplexity-teammates-research-previewWed, 04 Nov 2026 09:00:00 +0000Always-on agents built on Perplexity Computer that own ongoing work: they plan tasks, coordinate other agents, watch connected tools like Slack, GitHub and Linear, and follow up on things like PR review comments. Research preview on the web for individual Perplexity Max subscribers. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://github.blog/changelog/2026-11-04-github-copilot-is-now-available-in-xcodes-coding-assistant/2026-11-04-github-copilot-in-xcode-s-coding-assistant-public-previewWed, 04 Nov 2026 09:00:00 +0000GitHub Copilot is now available inside Xcode's built-in coding assistant as a public preview starting with Xcode 27.3 beta on macOS Tahoe 26.6+. The existing Copilot for Xcode extension remains a separate option; all Copilot plans are supported. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://github.com/anthropics/claude-code/releases/tag/v2.1.3182026-11-04-claude-code-2-1-318-cloud-sessions-without-a-repo-sign-in-expiry-warningsWed, 04 Nov 2026 09:00:00 +0000Anthropic's Claude Code 2.1.318 lets a cloud session on an Anthropic-hosted environment start with no repository picked, shows when a stored claude.ai sign-in ends (in claude auth status and claude -p JSON, plus a warning 10 days before), and adds an effort option for quick side jobs. It also fixes lost --continue history, macOS stalls with many Bash commands, and config and login corruption on shared network home directories. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://vercel.com/changelog/vercel-security-review-public-beta2026-11-03-vercel-security-review-public-betaTue, 03 Nov 2026 09:00:00 +0000Vercel Security Review is in public beta for Pro and Enterprise teams. Once enabled, every push to a connected GitHub repo is reviewed for vulnerabilities, with findings (summary, suggested fix and AI-rated severity) in a Vulnerabilities dashboard, a GitHub check and PR comments. Fix with Vercel Agent opens a PR, or pull findings into your own coding agent with vercel security vulnerabilities. Reviews are free until 10 November 2026, then billed at the Vercel Agent rate. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://github.blog/changelog/2026-11-03-github-copilot-is-now-available-in-jetbrains-air/2026-11-03-github-copilot-in-jetbrains-airTue, 03 Nov 2026 09:00:00 +0000GitHub Copilot is now available as an agent in JetBrains Air through the Agent Client Protocol. Pick Copilot in Air's agent picker to delegate coding tasks on your existing Copilot subscription, track several agent sessions in parallel and review changes next to your code. Cloud tasks run in isolated containers through Air Teams and use your Copilot plan rather than JetBrains AI credits. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w45/) https://docs.lovable.dev/changelog2026-11-01-lovable-download-an-sbom-for-your-projectSun, 01 Nov 2026 09:00:00 +0000Lovable now lets you download a software bill of materials for your project from the dependency list in the Security view, in SPDX 2.3 or CycloneDX 1.5 format. It lists production dependencies and their known vulnerabilities, so you can hand it to a security or procurement team. Downloading is free. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.com/deepseek-ai/dsh-superagent-prototype2026-10-31-deepseek-dsh-superagent-open-source-research-prototypeSat, 31 Oct 2026 09:00:00 +0000DeepSeek's Harness team open-sourced dsh-superagent under the MIT licence: a proactive coding agent for one GitHub repository that listens to GitHub (and optionally Feishu), turns authorised requests into work items, runs each in its own agent session and directory, and replies with results such as pull requests. A web panel shows what needs a person. DeepSeek labels it research code, not production-ready, and it runs as a bundle for DeepSeek Harness. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://code.claude.com/docs/en/changelog2026-10-31-claude-code-2-1-316-subagent-effort-control-opus-4-8-fast-mode-deprecatedSat, 31 Oct 2026 09:00:00 +0000Claude Code added CLAUDE_CODE_SUBAGENT_EFFORT to set the effort level subagents run at, a CLAUDE_CODE_DISABLE_ULTRATHINK switch, and pooled group budgets in the Claude apps gateway. Fast mode for Opus 4.8 is deprecated and will be removed on 30 Nov 2026 (requests will error, not fall back); Anthropic says to move to Opus 5.5. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://docs.replit.com/updates2026-10-30-replit-cloud-agents-for-company-codebases-enterprise-agent-chat-messagingFri, 30 Oct 2026 09:00:00 +0000Replit Enterprise customers can describe a change in plain language and a Cloud Agent finds the relevant code, makes the change, tests it in the running app and opens a GitHub pull request or GitLab merge request with screenshots and video, working in isolated cloud sandboxes for engineers to review. On Pro and Enterprise, Agent can now send messages to other chats or start new ones, and GPT-6.1 Terra is in the model selector for Agent in Power Mode. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://opencode.ai/changelog2026-10-30-opencode-2-2-3-use-your-claude-code-login-inside-opencodeFri, 30 Oct 2026 09:00:00 +0000The open-source OpenCode agent added a built-in Claude Agent provider: install Claude Code, run claude auth login, then pick Claude Agent in /connect to use your Claude Code login and models while OpenCode keeps its own tools and permissions. Desktop also got faster on long, streaming sessions. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://docs.lovable.dev/changelog2026-10-30-lovable-project-and-personal-memoryFri, 30 Oct 2026 09:00:00 +0000Lovable now remembers preferences, decisions and facts you state while building and applies them in later conversations. Project memory is shared by everyone who can edit a project; personal memory covers how you like to work across all projects. Memory settings show a plain-language summary you can correct or switch off. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://code.claude.com/docs/en/changelog2026-10-30-claude-code-block-writes-outside-working-directories-idle-compactionFri, 30 Oct 2026 09:00:00 +0000Claude Code added a permissions.blockWritesOutsideWorkingDirectories setting so Write, Edit and NotebookEdit refuse paths outside your working directories in every permission mode, plus idle compaction in VS Code and Claude Desktop's Code tab that summarises long (200K+ token) idle conversations before your next message. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://support.bolt.new/release-notes2026-10-30-bolt-database-tables-private-by-defaultFri, 30 Oct 2026 09:00:00 +0000From 30 October, new Bolt database tables are private by default, so your app needs explicit permissions to read or write data. Existing databases aren't affected, and Bolt sets up permissions when it creates a new database; if you hit a permissions error you can ask Bolt to fix the table permissions. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.com/openai/codex/releases/tag/rust-v0.166.02026-10-29-openai-codex-cli-0-166Thu, 29 Oct 2026 09:00:00 +0000Codex CLI 0.166.0 adds keyboard-driven transcript selection with search, codex queue --resume for unloaded threads, codex doctor --network-only diagnostics, clearer safety-block explanations, and GPT-6.1 Terra in the bundled, Vertex AI and Amazon Bedrock catalogs. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://huggingface.co/blog/mistral-large42026-10-29-mistral-large-4-open-weightsThu, 29 Oct 2026 09:00:00 +0000Mistral released the weights of its improved Mistral Large 4 (Le Chonk), a ~1T-parameter multimodal MoE model with a 1M-token context, which Mistral calls the best open-weight model for coding. Download from Hugging Face or use it via the Mistral API and OpenRouter at $0.70/$2.10 per 1M input/output tokens; commercial model-as-a-service use needs a separate licence. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://docs.lovable.dev/changelog2026-10-29-lovable-import-apps-from-replit-bolt-base44-v0-or-manus-or-an-existing-websiteThu, 29 Oct 2026 09:00:00 +0000You can now bring a project built elsewhere into Lovable and keep building: upload a ZIP export from Replit, Bolt, Base44, v0 or Manus, or enter the address of an existing site, including Wix, Squarespace or Webflow sites. The first import is free; later imports use standard build credits. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://factory.com/news/frontier-harness2026-10-29-factory-droid-1-0Thu, 29 Oct 2026 09:00:00 +0000Factory released Droid 1.0, a rebuilt harness for its model-agnostic coding agent. Programmatic tool calling is now on by default: the model writes a sandboxed JavaScript program that can run hundreds of tool calls in one request, keeping raw outputs out of context. Factory reports higher Terminal-Bench 4 scores at lower cost than other harnesses (self-reported). (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.com/vercel-labs/agent-desktop/releases2026-10-28-vercel-labs-agent-desktop-1-0-computer-use-for-any-coding-agentWed, 28 Oct 2026 09:00:00 +0000agent-desktop is a free, open-source (Apache 2.0) Rust CLI that lets agents like Claude Code or Codex operate desktop apps on macOS, Windows and Linux by reading the OS accessibility tree instead of screenshots, returning JSON element references and retry-safe error codes. Version 1.0 (adding Linux) shipped 28 Oct, with 1.0.2 on 30 Oct; it installs via npm. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://particle.ai/blog/introducing-particle-12026-10-28-particle-1-coding-modelWed, 28 Oct 2026 09:00:00 +0000New company Particle launched Particle-1, post-trained on DeepSeek V4.1 Flash to use about 45% fewer tokens on software-engineering tasks while keeping accuracy close to the base model, so tasks finish sooner and cost less. Available today through the Particle API. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://blogs.microsoft.com/blog/2026/10/28/introducing-the-microsoft-copilot-harness-unlocking-the-potential-of-truly-multi-model-agentic-work/2026-10-28-microsoft-copilot-harness-in-foundryWed, 28 Oct 2026 09:00:00 +0000The multi-model agent harness behind Copilot Code, the GitHub Copilot app, the CLI and VS Code is now available through Microsoft Foundry, with 20+ frontier models plus bring-your-own-key. Download the SDK or run the harness in the cloud, managed by Foundry, to build agents for long-running tasks. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.blog/changelog/2026-10-28-introducing-replica-an-open-source-ai-prototyping-tool/2026-10-28-github-replica-open-sourceWed, 28 Oct 2026 09:00:00 +0000GitHub Design open-sourced Replica, an MIT-licensed AI prototyping tool: describe an idea in natural language in the GitHub Copilot app and it builds an interactive prototype using your team's own design system components and docs. An optional self-hosted Replica Hub lets teammates explore prototypes and comment. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.blog/changelog/2026-10-28-copilot-code-review-merge-with-confidence-with-max-and-approvals/2026-10-28-github-copilot-code-review-max-public-previewWed, 28 Oct 2026 09:00:00 +0000Copilot code review gained a Max tier in public preview: several independent review agents using models from different providers review a pull request, then an aggregation agent reconciles their findings into one review. It's meant for high-risk changes and takes longer and uses more AI credits than Lite or Balanced. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.blog/changelog/2026-10-28-github-copilot-app-universe-releases/2026-10-28-github-copilot-app-projects-and-computer-use-previewWed, 28 Oct 2026 09:00:00 +0000Copilot Projects (public preview) give Copilot an ongoing goal that can span several repositories or none, running as many agents as needed and returning pull requests for review, with project automations for repeat tasks. Computer use, in public preview on macOS and Windows, lets Copilot click and type in desktop apps after asking your approval. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.blog/changelog/2026-10-28-route-and-orchestrate-models-with-github-copilot-fusion/2026-10-28-github-copilot-fusion-gaWed, 28 Oct 2026 09:00:00 +0000Pick Copilot Fusion in the model picker and Copilot routes and orchestrates models for each task, with Standard, High and Max effort levels. GitHub says Fusion Max scored within two points of Claude Code with Opus 5.5 Max on the Artificial Analysis Coding Agent Index at about half the cost. On all Copilot plans in VS Code, the Copilot app, Copilot CLI and JetBrains. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.blog/changelog/2026-10-28-github-agentic-workflows-generally-available/2026-10-28-github-agentic-workflows-gaWed, 28 Oct 2026 09:00:00 +0000Write automations such as issue triage, CI failure analysis, docs updates and test writing as natural-language Markdown files, and GitHub compiles them into standard Actions YAML run by Copilot or your own coding agent. Runs read-only and sandboxed by default; available on GitHub Free, Team and Enterprise (the default Copilot CLI engine needs a Copilot licence). (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-carbon/2026-10-28-gemini-4-carbon-limited-accessWed, 28 Oct 2026 09:00:00 +0000Google announced Gemini 4 Carbon, its strongest model for long-horizon coding and cybersecurity, ranked #1 on the Artificial Analysis Intelligence Index v5.0. Not yet open to developers: access starts with selected cyber defenders via the Fairwind Program. Google says it will launch at $2/$10 per 1M input/output tokens (introductory), then $4/$20. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://developer.android.com/blog/posts/ai-agents-android-studio-integration2026-10-28-android-studio-rabbit-2-bring-your-own-agent-stableWed, 28 Oct 2026 09:00:00 +0000Android Studio Rabbit 2 is stable with Bring Your Own Agent: plug in 40+ ACP-compatible coding agents, including Claude Agent, OpenAI Codex, Junie and Google Antigravity, with access to the emulator, build tools and Logcat. You sign in with your own subscription or API key; the built-in agent stays free. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.com/openai/codex/releases/tag/rust-v0.165.02026-10-27-openai-codex-cli-0-165Tue, 27 Oct 2026 09:00:00 +0000Adds a built-in Google Cloud Vertex AI provider (model_provider = "gcp"), GPT-6.1 Terra in the model catalogs, a repository filter in the session picker, reasoning-effort changes mid-conversation by default, and memory v2 by default for fresh profiles. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://docs.lovable.dev/changelog2026-10-27-lovable-events-hooksTue, 27 Oct 2026 09:00:00 +0000Business and Enterprise workspace admins can connect their own services: Events notify your HTTPS endpoint when a project is created, published, transferred or deleted, and Hooks let your endpoint allow or block an action first, such as screening chat messages for sensitive data. Also new: a Scrive connector for e-signatures and eID. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://runway.com/news/company-news/introducing-runway-app-studio2026-10-26-runway-app-studioMon, 26 Oct 2026 09:00:00 +0000Describe a creative tool in plain language and Runway builds, tests and deploys a custom app that generates images, video and audio using your Brand Kits and Workflows. Share it with your team or publish a link; code stays visible and you can roll back versions. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.blog/changelog/2026-10-26-github-copilot-assisted-permissions-generally-available/2026-10-26-github-copilot-assisted-permissions-gaMon, 26 Oct 2026 09:00:00 +0000When Copilot asks to run a command, touch a path or open a URL, a model evaluates the request: clearly safe ones proceed automatically, the rest still need your approval. Generally available in Copilot CLI (/permissions), the Copilot app and VS Code, with enterprise controls. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://github.blog/changelog/2026-10-26-gpt-6-1-terra-in-github-copilot/2026-10-26-gpt-6-1-terra-in-github-copilotMon, 26 Oct 2026 09:00:00 +0000OpenAI's newest model is generally available in Copilot for everyday agentic coding and terminal work at a lower cost than GPT-6.1 Sol. Available on Pro, Pro+, Max, Business and Enterprise across VS Code, Copilot CLI, cloud agent, JetBrains, Xcode and more; billed at provider list pricing. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://entire.com/news/entire-launches-an-independent-git-forge-for-agent-human-collaboration2026-10-26-entire-git-forge-for-agents-and-humansMon, 26 Oct 2026 09:00:00 +0000Former GitHub CEO Thomas Dohmke's Entire launched a Git-compatible forge built for coding agents. It replaces pull requests with Trails (agent-scored evals on every push), adds Continuous Memory that syncs agent sessions into the repo, and integrates with Buildkite and Depot CI. Available to every developer today. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w44/) https://tanstack.com/blog/tanstack-ai-1-02026-10-23-tanstack-ai-1-0Fri, 23 Oct 2026 09:00:00 +0000The open-source, provider-agnostic AI toolkit hits 1.0 with stable core APIs, 23 provider adapters, support for coding agents like Claude Code, Codex and OpenCode in sandboxes, plus a new experimental agent harness. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://docs.replit.com/updates2026-10-23-replit-agent-workspace-skills-keep-apps-running-past-creditsFri, 23 Oct 2026 09:00:00 +0000Replit Agent can now suggest new or improved workspace skills from your chats and projects, which you review and approve before they land. The same update lets eligible top-up customers keep published apps running when credits run out, up to an overage limit, and adds Stripe Atlas on Replit. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://github.com/openai/codex/releases/tag/rust-v0.164.02026-10-23-openai-codex-cli-0-164Fri, 23 Oct 2026 09:00:00 +0000Adds /presets (ten saved prompt and slash-command slots), inline arguments for /model and /permissions, image previews on Kitty/Sixel terminals, enterprise MCP sign-in, and credential masking in remote Bash, plus sandbox hardening. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://community.openai.com/t/introducing-scheduled-automations-to-the-agents-api/14092232026-10-23-openai-agents-api-scheduled-automationsFri, 23 Oct 2026 09:00:00 +0000Schedule a message into an existing agent session or have it start a new one, using a cron expression for recurring jobs or a timestamp for one-offs. Add the automations tool and agents can create, update or remove their own schedules from natural-language requests. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://simonwillison.net/2026/Oct/23/kimi-k31-pro/2026-10-23-kimi-k3-1-pro-moonshot-apiFri, 23 Oct 2026 09:00:00 +0000Moonshot's new flagship model is live on the Kimi API at $2/$10 per 1M input/output tokens, plus a 2-3x faster Highspeed tier at twice the price. Moonshot says full open weights follow by 4 Nov 2026; Artificial Analysis scored it 55, behind only Claude Opus 5.5. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://github.blog/changelog/2026-10-23-turn-notifications-into-code-with-github-copilot-in-teams/2026-10-23-github-app-for-microsoft-teams-with-copilotFri, 23 Oct 2026 09:00:00 +0000The new consolidated GitHub app in Teams brings notifications and Copilot together: @mention GitHub on an issue notification and Copilot investigates, fixes the bug and opens a pull request. The legacy app retires on 16 November. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://windsurf.com/changelog2026-10-23-devin-desktop-windsurf-new-agent-windowFri, 23 Oct 2026 09:00:00 +0000v3.11.212 rebuilds the Agent Window on the Devin web app UI: up to 8 sessions side by side, per-session Files, Changes and terminal views, cloud app previews with an element picker, and Enter to steer a running turn. v3.11.216 (24 Oct) fixes Local sessions and CLI install. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://www.linkedin.com/posts/cursorai_cursor-can-now-control-your-computer-with-activity-7519427217731444736-1aBg2026-10-23-cursor-computer-useFri, 23 Oct 2026 09:00:00 +0000Cursor's agents can now click and type across any desktop app on your computer, not just the browser, for example driving the iOS Simulator to test a feature they just built. The agent uses it when a task needs it, or you can @-mention Computer Use; update Cursor to get it. Desktop-app release notes weren't out yet at announcement. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://aws.amazon.com/blogs/opensource/introducing-infinity-a-runtime-for-extreme-agent-concurrency/2026-10-23-aws-infinity-agent-runtime-open-sourceFri, 23 Oct 2026 09:00:00 +0000An Apache-2.0 research runtime from AWS and UC Berkeley's Hydro project that suspends an agent during each tool call and resumes it when the result arrives, so idle agents cost little more than their history and can run on serverless platforms. AWS says 75,000 concurrent agents fit in a Raspberry Pi 5's 8 GB. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://wodby.com/blog/vibe-coding-with-wodby-agent2026-10-22-wodby-agent-for-vibe-codingThu, 22 Oct 2026 09:00:00 +0000Describe an app and Wodby Agent picks a stack, creates a private repo in your own GitHub/GitLab/Bitbucket, builds it in a live workspace with previews, opens a PR and deploys to infrastructure you control or Wodby Cloud. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://vercel.com/changelog/deploy-without-an-account-using-vercel-cli2026-10-22-vercel-deploy-without-an-accountThu, 22 Oct 2026 09:00:00 +0000Run vercel deploy --temporary to get a live tmp.now URL for a project or a single file without signing in. Temporary deployments expire after one hour unless you claim the project via the link in the CLI output. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://replit.com/blog/replit-monitoring-agent2026-10-22-replit-monitoring-agentThu, 22 Oct 2026 09:00:00 +0000An autonomous on-call agent for apps published on Replit: it reads production logs and metrics, investigates alerts, validates a fix and can auto-publish it, then emails you a summary. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://techcommunity.microsoft.com/blog/microsoft-copilot-blog/copilot-code-make-the-power-of-coding-accessible-to-everyone/45623582026-10-22-microsoft-copilot-code-frontier-previewThu, 22 Oct 2026 09:00:00 +0000A natural-language coding agent in the Microsoft Copilot app that builds apps, dashboards, tools and scripts from a description, using your work context, with a live preview, local or cloud runs, GitHub draft PRs and publishing to Copilot Managed Runtime. Rolling out via the Frontier program. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://opensource.googleblog.com/2026/10/introducing-elephant-goldfish-model-plugin.html2026-10-22-google-elephant-goldfish-model-plugin-open-sourceThu, 22 Oct 2026 09:00:00 +0000Google open-sourced its internal design-first AI coding plugin: a long-context 'Elephant' session co-designs a spec, then stateless 'Goldfish' sessions review it before any code is written. Apache 2.0, built for Antigravity first. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://techcrunch.com/2026/10/21/recursive-launches-flint-a-laptop-coding-model-it-says-was-largely-built-by-ai/2026-10-21-recursive-flintWed, 21 Oct 2026 09:00:00 +0000Free, Apache 2.0 coding model small enough to run on a laptop (40B-parameter MoE, 2.5B active), so you can code offline and keep your code private. Download on Hugging Face. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://openai.com/index/openai-models-google-cloud/2026-10-21-openai-models-and-codex-on-google-cloud-private-previewWed, 21 Oct 2026 09:00:00 +0000OpenAI's frontier models and Codex workflows are coming to Google Cloud's Model Garden, billed via Google Cloud Marketplace; private preview now, GA planned in the coming weeks. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://www.businesswire.com/news/home/20261021228398/en/GemDB-Makes-Code-the-Schema-Eliminating-Database-Migration-Bottlenecks-to-Accelerate-AI-Driven-Development2026-10-21-gemdb-code-vs-code-extensionWed, 21 Oct 2026 09:00:00 +0000Free VS Code extension with an object database where your code is the schema, so you or your coding agent change a class and commit with no migration scripts. Python only at launch; includes an MCP server. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://claude.com/resources/articles/claude-duet2026-10-21-claude-duet-research-previewWed, 21 Oct 2026 09:00:00 +0000Anthropic's proactive agent app: runs tasks on its own cloud computer, sends a morning brief from your connected apps, can prototype and build web apps, and asks before sending, paying or deleting. Waitlist for US Pro and Max. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://vercel.com/changelog/websocket-support-is-now-generally-available2026-10-20-vercel-websockets-in-functions-gaTue, 20 Oct 2026 09:00:00 +0000WebSocket support in Vercel Functions is generally available, for AI chat, streaming and realtime multiplayer apps, at normal Function pricing (CPU billed only while processing messages). (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://mistral.ai/news/voxtral-3/2026-10-20-mistral-voxtral-3-voice-agent-sdkTue, 20 Oct 2026 09:00:00 +0000New speech-to-text and text-to-speech models (50+ languages) plus a voice agent SDK that listens, reasons, calls tools and speaks in one real-time pipeline. Transcription from $0.0035/min. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://docs.lovable.dev/changelog2026-10-20-lovable-can-create-your-supabase-projectTue, 20 Oct 2026 09:00:00 +0000Ask Lovable to create a Supabase project for an app with no backend: pick the organisation and region and Lovable creates and connects it, billed to your own Supabase org. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://cursor.com/changelog2026-10-20-cursor-agent-sdk-gaTue, 20 Oct 2026 09:00:00 +0000Cursor's Agent SDK is generally available: define an agent as a folder of code (instructions, typed tools, skills, MCP connections, channels), test it with evals, and deploy it to Cursor with agent-sdk deploy or run it on your own infrastructure. Agents can wake on GitHub, GitLab, Bitbucket, Slack, webhook and cron events. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://v0.app/changelog2026-10-19-v0-slack-mcp-integrationMon, 19 Oct 2026 09:00:00 +0000Connect Slack to v0 so it can use team discussions as context for a change and post updates to Slack when you ask. Available on all v0 plans. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w43/) https://www.tao.media/perplexity-computer-adds-rea-to-inspect-and-rebuild-apps-without-source-code/2026-10-17-perplexity-computer-rea-reverse-engineering-skillSat, 17 Oct 2026 09:00:00 +0000New /reverse-engineer skill lets Computer inspect an existing app without its source and rebuild a working version, using the open-source REA MCP toolkit. Tasks free up to 10,000 credits per user until 31 Oct. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://cursor.com/changelog2026-10-16-cursor-canvases-from-cloud-agents-environments-api-betaFri, 16 Oct 2026 09:00:00 +0000Cloud agents can build shareable interactive canvases; Environments API in beta; environments now support up to 300 repos and load 5x faster. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://www.infoq.com/news/2026/10/chainguard-workspaces-checks/2026-10-16-chainguard-workspaces-and-checks-betaFri, 16 Oct 2026 09:00:00 +0000Hardened microVM dev environments for developers and coding agents, plus fast in-loop CI checks agents can call via MCP or SDK. 30-day beta trials. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://vercel.com/changelog/introducing-token-pass2026-10-15-vercel-token-pass-early-accessThu, 15 Oct 2026 09:00:00 +0000$30/month for $80 of GLM 5.3 and Kimi K3 credit via AI Gateway, for Pro teams. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://vercel.com/blog/vercel-ship-2026-recap2026-10-15-vercel-ai-sdk-7Thu, 15 Oct 2026 09:00:00 +0000AI SDK becomes a provider-agnostic toolkit for building multi-turn agents, announced at Vercel Ship 2026. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://developer.nvidia.com/blog/scale-agentic-coding-workflows-with-metas-muse-spark-open-on-nvidia-gb300-nvl72/2026-10-15-meta-muse-spark-openThu, 15 Oct 2026 09:00:00 +0000Coding-optimised open-weight MoE model (816B, 42B active) with 1M-token context. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://lovable.dev/blog/ai-models-and-tools-in-lovable2026-10-15-lovable-ai-models-and-tools-inside-your-appsThu, 15 Oct 2026 09:00:00 +0000Apps built in Lovable can now use GPT-Live voice, the latest Claude models, Gemini 4 Argon, Gemini Omni, Lyria, Perplexity, Firecrawl, Parallel and Jev without leaving Lovable. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://github.blog/changelog/month/10-2026/2026-10-15-github-agentic-autofix-for-code-scanning-gaThu, 15 Oct 2026 09:00:00 +0000Agents propose fixes for code scanning alerts. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://github.blog/changelog/month/10-2026/2026-10-15-github-ai-scan-for-prs-gaThu, 15 Oct 2026 09:00:00 +0000AI vulnerability scanning on pull requests, complementing CodeQL. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://claude.com/resources/articles/code-review-is-now-generally-available2026-10-15-claude-code-review-gaThu, 15 Oct 2026 09:00:00 +0000Multi-agent review of GitHub pull requests is out of research preview for Claude Team and Enterprise, with reviews ~3x faster (6-10 min) and Quick, Standard or Deep levels per repo. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://madrobot.blog/2026/10/16/bluesky-attie-ai-site-builder-vibe-code-games-polls-websites/2026-10-15-bluesky-attie-site-builderThu, 15 Oct 2026 09:00:00 +0000"Social vibe coding": describe a poll, quiz, guestbook or game and Attie builds a shareable page on attie.site that Bluesky followers can sign in to and use. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://siliconangle.com/2026/10/16/band-launches-desktop-app-for-developer-collaboration-and-control-of-multiple-ai-coding-agents/2026-10-15-band-for-developersThu, 15 Oct 2026 09:00:00 +0000Desktop app and CLI for managing a team of coding agents at once: projects, ownership, blockers, questions and progress in one view. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://docs.lovable.dev/changelog2026-10-14-lovable-growth-toolsWed, 14 Oct 2026 09:00:00 +0000Set a goal like 'my first 100 signups' and Lovable builds a growth plan from your app and traffic, then can create and launch ad campaigns on Google, YouTube, Facebook and Instagram with tracking set up, plus generate launch videos and ad creative. No extra Lovable fee; ad spend is billed by Google or Meta. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://digestai.news/story/karlex-ai-releases-graphicle-to-give-coding-agents-local-code-graphs-a2026-10-14-graphicle-karlex-aiWed, 14 Oct 2026 09:00:00 +0000Open-source Rust tool giving coding agents local code graphs and memory via MCP. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://www.builder.io/blog/introducing-agent-native2026-10-14-builder-io-agent-native-betaWed, 14 Oct 2026 09:00:00 +0000Open-source TypeScript framework for agentic apps where the agent and UI share actions, data and state; every app is also an MCP server and supports A2A. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/) https://github.blog/changelog/month/10-2026/2026-10-13-gemini-4-argon-in-github-copilotTue, 13 Oct 2026 09:00:00 +0000Google's newest frontier model now GA in Copilot. (ShipRank weekly roundup: https://shiprank.co.uk/weekly/2026-w42/)