我的收藏提交工具
FOXAI SEARCH

全站搜索

新闻报道 302

funding

Oumi’s Frontier AI Engineer now builds AI agents and retrains the models behind them

Enterprise artificial intelligence platform company Oumi PBC today extended its Frontier AI Engineer agent so it can build AI agents for customers and retrain the models those agents run on. The release goes after a problem that tends to surface once agents leave the demo stage. A failing agent might have a bad prompt, a […] The post Oumi’s Frontier AI Engineer now builds AI agents and retrains the models behind them appeared first on SiliconANGLE.

翻译服务暂未运行，当前显示原文。
SiliconANGLE AI
design-workflows

v0.44.0

ComfyUI v0.44.0 introduces multiple new partner nodes for tools like Patina, VEED, BFL, Ideogram, Pruna, MiniMax, Topaz, Sonilo, and OpenAI, adding features such as higher resolution video upscaling, context window editing, and new models. Enhancements include support for ProRes and custom chroma subsampling in video saving, improved frontend handling with pinned versions, optimized tensor comparisons, and better VAE compute dtype control. Performance optimizations address redundant concatenations and memory management, while bug fixes resolve crashes related to VAE decoding and prefetch queue cleanup. The release also updates workflow templates, embedded documentation, and default settings, with contributions from new developers.

翻译服务暂未运行，当前显示原文。
ComfyUI releases
agent-frameworks

v1.19.0 - Trace Your Workflows, Layer by Layer

Dify 1.19.0 enhances observability with nested workflow tracing, allowing users to follow execution steps inside Workflow Tools, inspect LLM calls, and maintain context across nested invocations. The release also enables portable app packages via App packages, improves Agent file uploads and previews, introduces Skill Hub automation through CLI commands, and upgrades the bundled plugin daemon to version 0.6.14-local. Key changes include support for format v2 app packages, enhanced security, improved editing workflows, and updated environment variables and API endpoints.

翻译服务暂未运行，当前显示原文。
Dify releases
coding-engineering

无需共享 SDK 密钥，即可从另一个项目评估 Vercel Flags。

Project Connections 允许应用在不管理 SDK 密钥的情况下，使用部署身份进行身份验证，从而评估同一团队内另一个 Vercel 项目中的标志。访问权限通过 Connections 页面或 CLI 进行管理，可在所有环境中授予只读访问权限，并且无需重新部署即可撤销。需要 @flags-sdk/vercel 1.6.0 或更高版本，或 @vercel/flags-core 1.11.0 或更高版本，以及用于 CLI 管理的 Vercel CLI 63.0.0 或更高版本。

尚无对应语言译文，当前显示原文。
Vercel
coding-engineering

How Mercor ships internal apps and billions of production tokens on one platform

Mercor reduced batch job processing time from 12 hours to 2–3 hours by using Vercel AI Gateway, which provided increased inference capacity and failover routing across providers. In its first 10 days on the platform, Mercor routed 18 million requests and 63 billion tokens without hitting rate limits. The company also leveraged Vercel Passport and its internal Audiences product to provision secure access for hundreds of business teams and over 2,000 projects in seconds, enabling rapid deployment of client-specific applications while maintaining strict usage controls and automated offboarding.

翻译服务暂未运行，当前显示原文。
Vercel
coding-engineering

How Zapier turns ideas into working software in hours with Vercel

Zapier leverages Vercel to rapidly develop interactive partner demos in under two hours, build internal applications like Marketing Hive and Marketing OS in a day each, and securely share sensitive data through SSO-protected deployments. The platform enables non-developers to deploy applications, supports AI orchestration via AI Gateway, and facilitates scalable, secure code execution with 3.3 million sandboxes created monthly. Vercel's speed, security, and ease of use have become central to Zapier’s innovation across engineering, marketing, and sales teams.

翻译服务暂未运行，当前显示原文。
Vercel
coding-engineering

Add liveness checks to your Daemons

Vercel has introduced support for HTTP liveness checks in daemons, allowing users to define a health endpoint that returns a 200 status if the daemon is healthy or a 500 status if it is not. The daemon configuration now includes a livenessProbe option pointing to this endpoint, enabling Vercel to periodically check its health and restart the container when the check fails, ensuring the daemon remains functional even if it's running but unresponsive.

翻译服务暂未运行，当前显示原文。
Vercel
coding-engineering

Data Cache is moving to Runtime Cache

Data Cache is being phased out and replaced by Runtime Cache in Next.js, with automatic migration for all versions. Pro teams receive 8x more storage per project, while Enterprise projects get 10x their previous allocation. Post-migration, previously unbilled reads and writes will be charged at $0.40 per million read units and $4.00 per million write units, varying by region. Hobby teams receive 1 million free read and 200,000 free write units monthly. Pro teams use a $20 infrastructure credit before billing applies. Teams created on or after October 30, 2026, will default to Runtime Cache. Migration dates: November 29, 2026 for Hobby; Pro and Enterprise teams will be notified separately. Early opt-in is available starting October 30, 2026, with immediate pricing application. Teams can disable caching in CDN settings without affecting migration. Optimization guidance is available via Observability and the Vercel Agent.

翻译服务暂未运行，当前显示原文。
Vercel