The MicroLLM Lab experiment from State of Utopia demonstrates seven tiny language models (25M–360M parameters) loaded, benchmarked, and chatted with entirely in the browser using WebGPU, with Q4 quant…
A developer released v0.7.0 of PR Tour, an open-source skill for Codex and Claude Code that generates guided walkthroughs of pull requests, adding an optional "transition" field that lets readers insp…
A developer built DF-Analyzer, a serverless deepfake image forensics dashboard, and deployed it on Tencent EdgeOne Makers during the DevHandal 2026 Batch 2 program. The tool uses Edge Functions to kee…
Lite4MariaDB, a new open-source project, compiles MariaDB 13.1 to WebAssembly, enabling a full embedded MariaDB server with InnoDB storage to run in browsers and Node.js without a separate server. The…
A developer has created a privacy-first personal finance assistant that runs entirely offline in the browser using LiteRT's LM Web API and the Gemma 4 E2B small language model. The application caches …
Tablinum, a local-first database for the browser, has been released as an npm package, offering encrypted sync via NIP-59 and built-in collaboration with zero backend. The database stores data in Inde…
BlazorMemory 1.0 has been released, a .NET library that brings AI chat memory to Blazor WebAssembly without requiring a server or vector database. The library offers four storage backends and four AI …
A developer built a private, local mental health AI assistant using WebLLM and React, running Llama-3-8B directly in the browser via WebGPU to ensure sensitive data never leaves the user's device. The…
A developer built a private health consultation bot that runs entirely in the browser using WebLLM and WebGPU, eliminating the need for backend servers and ensuring zero data leakage. The system execu…
Ternlight, a 7 MB embedding model using ternary quantization and WebAssembly, enables fully client-side semantic search in browsers, bypassing server round-trips and API costs. The model runs locally …
Nirnam, a browser-native message bus and AI agent framework for micro-frontends, has been released as an open-source npm package. It provides a three-layer hybrid message bus enabling pub/sub, request…
A developer built NoFlattery, a single-file React SPA that hosts a council of AI agents with different reasoning biases to debate user decisions. The app generates a Decision Record with a verdict, re…
Mozilla has integrated an on-device ML inference runtime into Firefox, using ONNX Runtime and Transformers.js, to power features like PDF.js alt text generation and Smart Tab grouping. The runtime run…
Prompt Flow is a visual side project built with React, ReactFlow, and Zustand that allows users to design and trace algorithmic flows on a canvas, replacing spoken explanations or flat text notes. Dat…
The article describes how GitHub's Issues Performance team modernized navigation by shifting from server-rendered pages to a client-side caching system. They built a caching layer using IndexedDB, imp…