Crafting released Crafting Express Edition, a free local evaluation build of its AI agent execution and orchestration platform that runs inside a single Docker container, launched with the command "cs…
Microsoft released three MAI voice models on October 1st: MAI-Transcribe-2-Streaming, MAI-Voice-2.1 and MAI-Voice-2.1-Flash, announced in a Microsoft AI post on X. The streaming transcription model ac…
Google's Firebase iOS SDK crashed after a backend change, taking down all apps that used Firebase analytics for 2 to 6 hours, and Google did not update its status page or publish a postmortem. Separat…
Sail Research retired B3IT monitoring for the deepseek/deepseek-v4.1-flash endpoint on the fp4 provider as of 2026-10-03, citing insufficient border inputs, while LT tracking remains active. The endpo…
Yash, founder of TabX, launched a Chrome side-panel extension that recalls closed tabs by meaning, auto-groups tabs by inferred intent, and offers an AI web search returning 3-5 ranked link results wh…
NVIDIA released OpenShell, an open source runtime that isolates autonomous AI agents in per-agent sandboxes with kernel-level file and syscall controls and a policy gateway that checks every outbound …
A developer replaced the Rust `clap` crate with LLM-generated argument-parsing code written by Gemini 3.8 Flash via OpenRouter, cutting the compiled executable size by 300 kB and argument parsing time…
A daily latency benchmark of the DeepSeek API run from six cities between 27 August and 22 September 2026 found that direct access beat OpenRouter from Singapore and Mumbai (direct 621–664 ms versus 7…
The deepseek/deepseek-v4.1-flash endpoint on OpenRouter has been placed under B3IT monitoring, with a measured total-variation level shift of 0.21, while its LT tracking status remains pending and une…
NEAR AI Cloud added Anthropic's Claude Sonnet 5.5 to its model lineup, offering the model through its unified gateway at cloud-api.near.ai with a 1 million token context window, adaptive reasoning ena…
DiggerHQ released OpenDots, an open-source, model-agnostic personal agent framework positioned as an alternative to OpenAI's Dots, running on OpenComputer Serverless Agents. OpenDots is a TanStack Sta…
Qlty released SlopOne, a free research preview AI model that scores code maintainability by combining traditional static analysis statistics with classifications from TypeSafe AI's new Jev decision mo…
A developer published a Python script that measures a brand's AI share of voice by routing identical buyer-style prompts to multiple models through OpenRouter and counting brand mentions sentence by s…
A developer spent a day calling the public model-list endpoints of four LLM gateways twice, twenty minutes apart, and compared the responses against vendor documentation, finding that these lists chan…
OpenCode, an MIT-licensed open-source AI coding agent built by Anomaly, runs in the terminal and connects to 75-plus LLM providers or local models via Ollama and LM Studio, with credentials added thro…
SourceBento outlined engineering guidance for adding an AI assistant to its self-hosted Python HR and payroll platform WorkBento, arguing that a read-only database connection alone does not enforce wh…
Middleware is being built to train open-weight models on the corrections developers already make to recurring AI tasks, letting teams replace or supplement calls to OpenAI, Anthropic or Google APIs th…
A developer built bpy-compass, a version-aware Blender Python assistant that answers scripting questions for a user-selected Blender release by drawing on a Sanity Context Knowledge Base of official r…
Jevgrep, a new CLI from developer dzhng that uses the Jev model to locate relevant files for coding agents, matched a no-Jev baseline by solving 8 of 10 SWE-bench tasks while cutting full Sol cost fro…
Fabian Both released Jevpipe, an open-source Unix-pipe CLI that lets AI coding agents run fast, cheap yes/no and choice judgments over thousands of files, lines or records in one shell command. In a r…