Aura, a self-hosted, multi-user AI agent written in Go, ships as a single binary hosting the runtime, tools, CLI, Telegram gateway and embedded web cockpit, with each user getting their own memory dat…
A developer built DockForge, an AI-powered tool that analyzes a GitHub repository and generates a tailored Dockerfile, then builds the image and iterates on failures. The Next.js application uses open…
An open-source Lego AI generator now turns LDraw source into editable LEGO CAD models, combining a Python toolset and agent instructions with GPT-6 Astra or Opus 5.5 in a Docker web app offering OpenA…
Developer kouhxp released gutsy-0.8b v0.4, a fine-tune of Qwen3.5-0.8B that returns calibrated probabilities for typed yes/no, choice, and score questions on CPU via llama.cpp, under an Apache 2.0 lic…
A developer's comparison found that generating complicated Rust functions on a local LLM took 30 to 60 minutes of 100% CPU and 100% GPU usage at an estimated electricity cost of $0.02 to $0.04, while …
Prime Intellect launched Prime Inference, a serverless and reserved-capacity serving platform for frontier open-source models that processed nearly a trillion tokens per day internally before public r…
A developer built JSXDock, a free, web-based AI workstation that generates production-grade TypeScript components for React Native and Expo projects. The tool synthesizes copy-paste-ready .tsx code al…
A developer published a video and written guide showing how to run local AI models on a 16GB M1 MacBook Pro using the mlx-serve command-line utility, which is optimized for Apple's Metal architecture.…
Of eight AI vendors checked on October 3, 2026, six let a team set a cap that stops usage when spend reaches it, while Microsoft's Azure budgets only send alerts and AWS Budgets stops usage only throu…
The Ethereum Foundation and the Open Anonymity Project launched zkAPI on Ethereum mainnet on October 1, letting users prepay in ETH or USDC and receive capped, short-lived API keys through zero-knowle…
A developer released an open-source, dockerized web app that uses GPT-6 Astra and Opus 5.5 to generate LDraw source code, which renders as LEGO CAD models in tools such as LDView, LeoCAD and Studio. T…
TypeSafe's structured decision model Jev, benchmarked as a quality judge on the 1,000-rubric Feedback-Collection dataset, was tested against two low-cost general-purpose LLMs on a 750-example held-out…
A developer built EscrowLens, a passkey-native peer-to-peer escrow protocol on Monad, with a provider-agnostic AI arbiter that returns schema-validated, EIP-712-signed verdicts while holding no funds …
Inception released Mercury Decide, a structured decision model it says is the most intelligent on OpenRouter's JevBench v1.4 and among the fastest, handling up to 14 decisions per second. The model is…
Microsoft AI released MAI-Transcribe-2-Streaming, a real-time transcription model that Microsoft says ranks first for accuracy on Artificial Analysis, transcribes 60 languages, and returns first parti…
Janus, an MIT-licensed single Go binary from the Vibra-Ingenn project, launched as a Show HN on October 1 with 42+ points, wrapping llama.cpp's Vulkan backend to run GGUF models on AMD, Intel, or NVID…
A developer built SVGMotion, a free, local-first SVG motion studio that exports self-contained, callable .svg files with no proprietary runtime. The tool bakes physics into keyframes at export time, p…
A study of 503 profession-specific AGENTS.md profiles found that loading full scientific-agent profiles by default did not improve accuracy and cost 2.2 to 4.5 times more per successful call, accordin…
Self-hosting the open-weight Qwen3.8 27B model costs $619 per full Artificial Analysis Intelligence Index run through the cheapest zero-data-retention provider, versus $67 for OpenAI's GPT-6 Luna, acc…
A developer released Grist, an open-source coding harness built on Opencode v2, which routes tasks across four tiers — easy, medium, hard and frontier — to cheaper models such as DeepSeek for simple w…