MR Office open-sources six browser editors under AGPL-3.0
MR Office has published the source of its six browser editors on GitHub under AGPL-3.0, with a hosted embed, an MCP server and npm React packages for developers.
Open models, libraries and tools.
MR Office has published the source of its six browser editors on GitHub under AGPL-3.0, with a hosted embed, an MCP server and npm React packages for developers.
A new MIT-licensed Python project on GitHub cuts long videos into captioned 9:16 clips using audio signals and a local LLM, with no account and no uploads.
simplexai-labs/linger drew 1,622 stars in ten days for an open-source personal agent that claims a 125B model on a 12 GB GPU, with nightly memory and proactive follow-ups.
thesysdev/opendashboards, an MIT-licensed TypeScript project, offers question-to-dashboard generation over Postgres, BigQuery and MCP sources, self-hosted or hosted.
A new MIT-licensed repo turns whiteboard tutoring into a JSON protocol any LLM can drive, then benchmarks six models across 288 runs and 64 blind-reviewed boards.
Cloudflare says Clairic has left preview and Clairic-flash has arrived on Workers AI, with both extraction models getting an open-weight release.
Gezhi Sheets, an MIT licensed AI spreadsheet assistant, reached 300 GitHub stars in eight days. It runs locally on Windows and connects to five Chinese model providers.
The huawei-csl project MACaQ shipped an Apache-2.0 quantization toolkit that writes GGUF files for llama.cpp and covers text, image, video and audio models.
Legwork is a Windows app that answers research questions from public sources and cites a page for every sentence. It reached 326 GitHub stars in two days.
A repository calling itself a general-purpose AI agent system reached 300 GitHub stars one day after creation, with a README that promises sandboxed code and browser control but no install steps.
sand3d, a Python library for writing 3D objects as short programs over Blender's bpy, drew 1,969 GitHub stars in 11 days, with one-call exports to GLB, URDF, USD and IFC.
The smolmaxxing repo patches llama.cpp to page experts from flash, reporting a 16B model on a 1 GB TV box and an 80B model on a 2022 Android phone.