AI news

Dub Automated application screening

Dub can now screen partner program applications automatically against criteria described in plain language. Its AI reviews each applicant's profile and application answers and automatically rejects applications that clearly match the exclusion criteria, such as coupon or discount code sites.

Product updateDubProduct release notes

Polar v2.1.0

Version 2.1.0 of @polar-sh/better-auth passes the customer's IP address when a checkout is created, letting Polar display local currency, and resolves it with Better Auth's getIP. A new customerIpAddress option lets you supply the IP yourself or turn it off with false.

Product updatePolarGitHub Releases

Paperclip v2026.1005.0

Paperclip v2026.1005.0 runs Grok Build on the native runner through ACP, for both local and Daytona execution. Agents keep their own files across tasks, company skills sync from GitHub repositories, and Browser Use Cloud supplies a live browser that people can watch and take over. Mentioning an agent in a task comment no longer starts a run, so workflows must assign the task or request a review. Keyboard shortcuts are always on with their settings removed, and the PAPERCLIP_CLOUD_UI_SNIPPET settings no longer inject HTML.

Product updatePaperclipGitHub Releases

Coolify v4.4.0

Coolify v4.4.0 adds built-in traffic analytics for Traefik and Caddy, with the Rust version of Sentinel rolling up access logs per server and the feature off by default. SQLite arrives experimentally as a standalone database that connects to apps on the same server in one click and supports scheduled backups, and secrets can come from Doppler, Infisical or HashiCorp Vault without being stored in Coolify's database. The release also brings Cloudflare DNS record management, OpenID Connect sign-in, a team audit log and Docker registry logins. Build-only servers can run GitHub Actions self-hosted runners in beta.

Product updateCoolifyGitHub Releases

Folo v1.15.0

Folo Desktop v1.15.0 moves to Electron 44, and settings sync once again carries every appearance, general and AI setting, leaving only device-bound ones such as interface language, fonts and launch at login on each machine. Translations into Simplified Chinese, Traditional Chinese, Japanese and French are now complete. The update fixes a bug, present since 1.6.0, where only device-specific settings were synced, and AI settings and chat no longer stay in English for Chinese users.

Product updateFoloGitHub Releases

Introducing marimohub

A self-hostable notebook platform to store, manage, and run marimo notebooks on your own infrastructure.

From the buildermarimoOfficial blog

Impeccable v4.5.0

Impeccable skill v4.5.0 has dashboards, boards and tools commit to a real palette while keeping familiar controls, and documentation keeps body text in a plain readable column. Landing pages now show the task visitors came for, such as a flight search or open appointment slots, instead of a button that leads elsewhere. Rules for each page type print as soon as directions are dealt, so comps made in parallel follow them too. Fixes put ignore entries where git reads them in linked worktrees and keep live-mode checkpoints in order across tabs.

Product updateImpeccableGitHub Releases

Paperclip v2026.1001.0

Paperclip v2026.1001.0 focuses on reliability, hardening the native runner and chat recovery around approval and Stop races, session continuity and sandbox reconnection. Agents can review GitHub pull requests as scheduled review bots, and Railway joins the connector catalog. Execution harnesses now default to full auto, so operators who relied on unconfigured agents inheriting strict gates should set an explicit mode. The legacy Composio broker is removed, and existing connections stop working with no automated migration.

Product updatePaperclipGitHub Releases

AnythingLLM v1.17.0

AnythingLLM v1.17.0 adds Gemini and llmman as image generation providers and Firecrawl as an agent web-search provider. Workspace settings now save automatically on edit, and reasoning effort controls are available. AWS Bedrock gains support for OpenAI models. Multi-sheet XLSX uploads keep every sheet.

Product updateAnythingLLMGitHub Releases

Impeccable v4.4.0

Impeccable skill v4.4.0 lets you review components one by one in the browser, comparing each illustration, photo and rendered component with its crop of the comp before approving it or asking for fixes. Once the page is assembled you review the first viewport against the comp, and an unattended review waits rather than approving itself. A new /impeccable generate command turns a one-sentence request into variants of an element on the open page, and an accepted variant becomes source code. Line-length, padding and other rendered checks now measure what the browser actually draws and name the screen width that triggered them.

Product updateImpeccableGitHub Releases

Obsidian October 2026

In May, we launched the new Obsidian Community , and since then the number of plugins and themes has more than doubled to over 8,000 projects!

From the builderObsidianOfficial blog

shadcn/ui v0.1.0

Version 0.1.0 introduces @shadcn/registry, the registry engine that powers the shadcn CLI, which now depends on it while shadcn/registry and shadcn/schema re-export it. Existing users do not need to change anything.

Product updateshadcn/uiGitHub Releases

Latitude v9.15.0

Latitude python-sdk 9.15.0 leaves the timeout to a custom httpx_client passed without an explicit timeout, instead of copying its timeout.read onto each request. Behavior is unchanged when timeout is set or when the SDK builds its own client. The SDK is regenerated on newer Fern versions with no change to the HTTP API or method signatures, and the runtime gains SSE reconnect handling and TCP keepalive options. The docs now note that LATITUDE_PROJECT_SLUG is read only by the Latitude CLI and has no effect in the SDK.

Product updateLatitudeGitHub Releases

Zed v1.22.0

In Zed v1.22.0, spawn_agent accepts an optional model parameter so each new subagent can run on its own model, and subagents now support compaction. GPT-6.1 Sol can be used with your own OpenAI key, and Grok 4.7 becomes the recommended default for the SuperGrok and xAI providers. Diffs opened with zed --diff can switch between unified and split layouts, and the OpenCode model list is now fetched live.

Product updateZedGitHub Releases