dalao.ai

AI news

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

Polar v1.0.0

Version 1.0.0 of @polar-sh/nextjs moves to the new Polar SDK (@polar-sh/sdk/2026-10) and its standalone functions, so app bundles carry only the API operations each adapter calls. Checkout requests now accept discount_code, which is applied before the redirect or the embedded checkout opens.

Product updatePolarGitHub Releases

Ollama now supports Jev-style decision models

Decision models on Ollama are fast, as requests don’t have to travel over a network. Nimble 9B averaged 91ms per decision in the Pac-Man example below when running locally on an M5 Max.

From the builderOllamaOfficial blog

Documenso v2.19.0

Documenso v2.19.0 introduces a team document analytics dashboard and inbox filters, and documents created from templates can follow naming options. The signing reason can be overridden, and template view tabs give way to a filter pill. PDFs protected by an owner password are now accepted, and action authentication works better for passwordless users.

Product updateDocumensoGitHub Releases

Ollama v0.35.0

Ollama v0.35.0 serves decision models through /v1/systemone; instead of text they return choices, probabilities and scores, which suits ticket triage, model routing and content classification. Nimble from Bespoke Labs and Tev1 from Together AI are the first models available. Settings also open without waiting for model discovery, and MLX downloads no longer hang.

Product updateOllamaGitHub Releases

Easydict v2.24.0

Easydict 2.24.0 adds GitHub Copilot CLI translation with dynamic model selection, saves looked-up words to a local vocabulary notebook and adds pronunciation to Youdao English word lookups. OCR once again recognizes QR code payloads. DeepL now supports Vietnamese. A problem with input translation being cleared has been fixed.

Product updateEasydictGitHub Releases

Ollama v0.40.0

On Apple Silicon, Ollama v0.40.0 automatically runs model architectures that the MLX runtime supports on MLX, with gemma4, qwen3.6 and qwen3.5 among the added models. Decision models and the embeddinggemma-2 embedding model now run on MLX as well.

Product updateOllamaGitHub Releases

Zed v1.21.0

Zed v1.21.0 lets SuperGrok subscribers sign in and use Grok models in the Agent Panel, and a new agent.prevent_idle_sleep setting, on by default, keeps the machine awake while agent threads run. You can now bring your own key for Claude Opus 5.5 and for GPT-6 Astra, Sol and Luna. Syntax-highlighted files and Markdown code blocks draw faster, and a picker for language server commands has been added.

Product updateZedGitHub Releases

See what we're shipping at Latitude.

Latitude is launching Agent Score in early access, enabled per organization, which rates a project from 0 to 100 over a rolling window. The composite weights five dimensions (outcome, reliability, cost, speed and safety) at 35%, 25%, 15%, 15% and 10%, and is withheld when any dimension cannot be measured. A daily sweep picks the shortest whole-week window that meets the session floor, from 7 to 28 days, and published snapshots never change. The score is readable through the REST API, MCP, the TypeScript and Python SDKs, and the CLI.

Product updateLatitudeProduct release notes 1 more update