v13.2.0 ## What's new ### `wowerpoint` skill — kawaii NotebookLM slide-deck generator Turn one source document into a kawaii NotebookLM slide-deck PDF. Wraps the `notebooklm` CLI with the kawaii-prompt + `--format detailed` defaults and a spawn-subagent pattern so generation (~10 min) never blocks the main conversation. - **Single-source-per-deck** is enforced by the workflow shape: confirm or write the source doc *before* adding it to NotebookLM. Don't paper over a weak source by stacking more sources — write a comprehensive doc first. - **Slide-deck only.** Videos and podcasts from the same
今日精选
- bytedance/ui-tars-desktop32,978 星标
UI-TARS-desktop:技术项目简述
TypeScript - cloakhq/cloakbrowser6,089 星标
CloakBrowser:技术项目简述
Python - yikart/aitoearn10,713 星标
AiToEarn:技术项目简述
TypeScript - playcanvas/supersplat7,333 星标
supersplat:技术项目简述
TypeScript - datawhalechina/easy-vibe9,876 星标
easy-vibe:技术项目简述
JavaScript
技术动态流
v1.42.0 ## Added ### Security & planning gates - **Package legitimacy gate against slopsquatting** - researchers now audit recommended packages with registry checks and `slopcheck`, planners add human-verification checkpoints for assumed or suspicious packages, and executors no longer auto-retry failed package installs. The gate degrades safely when `slopcheck` is unavailable by tagging packages as assumed and requiring human verification. (#3215) - **End-of-phase human verification mode is now the default** - `workflow.human_verify_mode = end-of-phase` reduces mid-flight interruption while pr
- v4.20.3 · ArcKit v4.20.3 ### Fixed - Validate-arc-filename emits {decision,reason} JSON instead of exit 2 (#4...
- v4.20.2 · ArcKit v4.20.2 ### Changed - **Wardley Mermaid rendering now targets Mermaid 11.15.0.** Generated A...
- +1 条更多动态
v1.60.0 ## 🌐 HAR recording on Tracing [tracing.startHar()](https://playwright.dev/docs/api/class-tracing#tracing-start-har) / [tracing.stopHar()](https://playwright.dev/docs/api/class-tracing#tracing-stop-har) expose HAR recording as a first-class tracing API, with the same `content`, `mode` and `urlFilter` options as `recordHar`. The returned [Disposable](https://playwright.dev/docs/api/class-disposable) makes it easy to scope a recording with `await using`: ```js await using har = await context.tracing.startHar('trace.har'); const page = await context.newPage(); await page.goto('https://play
- v0.4.3 · v0.4.3 v0.4.3
- v0.4.2 · v0.4.2 - embed tweets - redesigned Live-note sidebar
v2.1.139 ## What's changed - Added agent view (Research Preview): a single list of every Claude Code session — running, blocked on you, or done. Run `claude agents` to get started. See https://code.claude.com/docs/en/agent-view - Added `/goal` command: set a completion condition and Claude keeps working across turns until it's met. Works in interactive, `-p`, and Remote Control. Shows live elapsed/turns/tokens as an overlay panel - Added `/scroll-speed` command to tune mouse wheel scroll speed with a live preview - Added `claude plugin details <name>` to show a plugin's component inventory and
v4.1.6 ### 🐞 Bug Fixes - **browser**: Provide project reference in `ToMatchScreenshotResolvePath` - by @macarie and @sheremet-va in https://github.com/vitest-dev/vitest/issues/10138 [<samp>(31882)</samp>](https://github.com/vitest-dev/vitest/commit/31882607c) - Global `sequence.concurrent: true` with top-level `test(..., { concurrent: false })` + depreacte `sequential` test API and options - by @hi-ogawa, **Codex** and @sheremet-va in https://github.com/vitest-dev/vitest/issues/10196 [<samp>(2847d)</samp>](https://github.com/vitest-dev/vitest/commit/28
T3 Code Nightly 0.0.24-nightly.20260511.260 (447236d51f4d) ## What's Changed * fix(codex): use longer and shared auth probe timeout for provider status check by @UtkarshUsername in https://github.com/pingdotgg/t3code/pull/2616 * Alias stable releases to the router domain by @juliusmarminge in https://github.com/pingdotgg/t3code/pull/2636 * Remove outline styling from git success toast action by @juliusmarminge in https://github.com/pingdotgg/t3code/pull/2639 * Preserve Codex probe results across scoped teardown by @juliusmarminge in https://github.com/pingdotgg/t3code/pull/2638 * Optimize VCS
v0.2.30 ## Changelog * 15c388630241f024c49b1a6c0a16541af3f5ffd3 docs(daemon): refresh stale comment for inline system prompt path (#2362) * 02310d083e96e80b1b531530fccfef1fccd3034a docs(util): clarify EnsureHiddenConsole call-order contract (#2399) * b26f850d4e8176ddcbd343b020005a7e66526d38 feat(agents): gate private-agent surfaces with allowed_principals predicate (#2359) * 00415de4630eee17b5fe2fd1fb23f88c19ba9bdf feat(editor): render mermaid diagrams inside issue descriptions (#2297) * 448e75ce53869e8ada1bb5c9cea6fac3817eaf35 feat(issues): inline status & assignee pickers + batch select on s
v13.1.0 ## Server-beta event pipeline (phases 4–13) This release lands the full server-beta track developed on `server-beta-phase-4-event-pipeline` — a self-contained Postgres + BullMQ event-to-observation pipeline with API-key auth, team/project scope, audit log, three AI providers (Anthropic, OpenAI, Google), a dedicated MCP server, legacy compat adapters for existing worker clients, a Docker/Compose stack, and a generation-job retry/cancel surface. ### Highlights - **Event pipeline**: `agent_event` → `observation_generation_jobs` (outbox) → BullMQ worker → `observation` row. Idempotent enqu
v8.0.12 Please refer to [CHANGELOG.md](https://github.com/vitejs/vite/blob/v8.0.12/packages/vite/CHANGELOG.md) for details.
v0.17.1 ## What's Changed ### Sandboxes * fix: include sandbox provider error details by @seratch in https://github.com/openai/openai-agents-python/pull/3326 * fix: #3274 limit sandbox archive extraction by @Aphroq in https://github.com/openai/openai-agents-python/pull/3278 * fix: #3273 validate git repo subpaths by @Aphroq in https://github.com/openai/openai-agents-python/pull/3276 * fix: allow empty GitRepo subpaths as repository root by @seratch in https://github.com/openai/openai-agents-python/pull/3299 * fix: preserve GitRepo root subpath aliases by @seratch in https://github.com/openai/o
Nightly Build v0.1.96-nightly.20260511 ## Nightly Build v0.1.96-nightly.20260511 **Warning:** This is an automated nightly build and may be unstable. Use at your own risk. ### Downloads Download the appropriate installer for your platform below. - **Windows**: `.msi` or `.exe` installer - **macOS**: `.dmg` installer (Intel and Apple Silicon) - **Linux**: `.AppImage`, `.deb`, or `.rpm` package --- For stable releases, please visit the [latest release](../../releases/latest).
v16.3.0-canary.19 ### Misc Changes - Proof of concept: task eviction after snapshot for turbo-tasks-backend: #91790 ### Credits Huge thanks to @lukesandberg for helping!
- v1.42.0 · v1.42.0-rc2 ## What's Changed * docs(CONTEXT.md): codify release-notes formatting standard for AI a...
- v1.41.2 · v1.41.2 **Full Changelog**: https://github.com/gsd-build/get-shit-done/compare/v1.41.1...v1.41.2
Release v0.1.96 ## Release v0.1.96 ### Downloads Download the appropriate installer for your platform below. - **Windows**: `.msi` or `.exe` installer - **macOS**: `.dmg` installer (Intel and Apple Silicon) - **Linux**: `.AppImage`, `.deb`, or `.rpm` package ### Release Notes _Add your release notes here_ --- **Note:** iOS builds are deployed separately via the iOS Release workflow.