OpenRouter: Server Tools Marketplace
OpenRouter launched a Server Tools Marketplace that gives models access to web search, code execution, image generation, URL fetching, and other hosted tools. The marketplace lets developers compare p…
OpenRouter launched a Server Tools Marketplace that gives models access to web search, code execution, image generation, URL fetching, and other hosted tools. The marketplace lets developers compare p…
Modal detailed how it scaled inference for Moonshot AI's Kimi K2.6 coding-agent model, achieving 2.8x per-user and 5.6x across-user performance gains per replica, with one service processing hundreds …
A developer built an invisible CAPTCHA that replaces puzzles with behavioral analysis, using TypeSafe's Jev "System One" model to score mouse movement, typing rhythm and button presses on a waitlist f…
A developer used OpenRouter to run GLM 5.3 Flash on two Rust functions generated from written specs, paying about $0.03 total for the work. The developer reported the model coded the functions well, w…
A developer has released the first alpha of ForgeDesigner, a desktop app for macOS (Apple Silicon) and Linux (x86_64) that lets users describe a website in plain language and have an AI assistant gene…
Soter, an open-source Discord moderation bot built in TypeScript on Bun and MIT licensed, scans every message for hate speech and spam using Jev, a model by TypeSafe AI that returns typed answers with…
An independent review of TypeSafe AI's Jev, a hosted "System One" model launched September 15, 2026 that returns typed answers (choice, score, noul) rather than generated text, finds it level with mid…
GPT-6 Astra scored 87.4% on the Part Catalog Bench, the highest of 13 models tested on 119 questions drawn from the 5,445-page Ford 1960–68 Car Master Parts and Accessories Catalog, according to bench…
AssemblyAI's Universal-3.5 Pro speech-to-text model is now available on OpenRouter as `assemblyai/universal-3-5-pro`, served through AssemblyAI's Sync Speech-to-Text API at AssemblyAI's published rate…
Rabbit Inc. unveiled OS3 on Tuesday, a cloud-based personal AI agent that installs on up to five machines via a single command and connects to Windows, macOS and Linux computers, cloud virtual machine…
ComfyUI launched Comfy Router, a unified API that lets its 3M+ users run generative media models such as Seedance 2.5, MiniMax H3, Nano Banana Pro, ChatGPT Images 2.5, KlingAI 3.0 and Flux 3 across pr…
Google announced the availability of Agent Substrate on Google Kubernetes Engine (GKE), an open-source, secure-by-default agent execution runtime that runs millions of sandboxes at 10x higher density …
A developer is building GoodVibes, a Chrome extension that uses the Jev API to analyze and filter negative or unwanted content on social media feeds in real time. The tool lets users choose which topi…
A developer integrated the jev model into n8n workflows via OpenRouter and Opper AI, replacing OpenAI 5.6 Luna in two decision-making processes. The developer reports that jev is cheaper and faster fo…
Nous Research's Hermes Agent, an open-source general-purpose AI agent written primarily in Python, has reached 248,000 stars on GitHub and was last updated in September 2026. The agent builds skills f…
OpenAI, Anthropic and SpaceX all released new models this week that they said are cheaper than their prior top systems, a trend experts say could give AI labs a financially viable path to slow develop…
Developer Kevin-Zhouu released Jevify, a skill that scans a repository and converts existing LLM calls already using structured data to run on Jev, TypeSafe, OpenRouter, or Vercel. The tool can be inv…
Cisco Talos researchers statically analyzed CLOSEDQUORUM, a Go-based Windows implant that queries up to four commercial LLMs — DeepSeek, Qwen, Mistral, and Gemini — with host information and then exec…
Fireworks AI released Ember-1 on September 23, 2026, a post-trained version of Moonshot's open-weight Kimi K3 that Fireworks says delivers K3's quality with 35 to 50% shorter reasoning across seven be…
TypeSafe launched Jev, a specialized "System One" model, on September 15, 2026 alongside disclosure of a $40 million seed round, claiming end-to-end response times of 70 ms to 500 ms versus 3 s to 329…