Trending archive for Oct 9, 2026

openai/math

OpenAI's model-generated math proofs, with Lean formalizations in progress — A collection of 719 mathematical manuscripts in 372 families produced by an internal OpenAI model tackling open research problems, released as model-development evaluations saturated on existing benchmarks. About 42% of top-line results have Lean formal proofs so far, with reasoning summaries and a comparator tool included for verification.

Niko1221/Strata

A 125B-parameter model, squeezed onto your gaming PC — Strata is a one-click Windows/Linux installer that runs Qwen3.8-Flash-Next, a 125-billion-parameter model, locally on consumer NVIDIA, AMD or Intel GPUs. It exposes an OpenAI/Anthropic-compatible API on localhost, supports image input, and keeps chats and files on-device, useful for coding agents and local app integrations without cloud dependency.

Qwen3.8-Flash-Next on any consumer hardware: one-click install for Windows / Linux. Strata inference engine, OpenAI/Anthropic API on localhost, optional image input.

omlahore/RemoveMacAI

A reversible, GUI-friendly way to strip Apple Intelligence from macOS — RemoveMacAI offers a native app and CLI to disable Apple Intelligence, delete its models, stop analytics and ads, and quiet pop-ups on macOS, reclaiming disk space. Every change is previewed and reversible. It builds on pared's research into Apple's asset service and settings, and has been covered by The Verge, Ars Technica and The Register.

Debloat macOS: turn off Apple Intelligence, analytics, ads and pop-ups. A native app and CLI, and every change can be undone.

franzenzenhofer/big-arrow-on-the-screen

A CLI that lets AI agents literally point at your screen — bigarrow is a macOS CLI and Claude Code/Codex skill that draws a click-through arrow, box, or text over any window so an AI agent can show you exactly what to click. It needs no macOS permissions, runs as a single Swift binary with no daemon or telemetry, and disappears on its own.

Let your AI agents paint big arrows, boxes and text on your Mac screen. One CLI, click-through, gone by itself. Skill for Claude Code and Codex. MIT.

szabadkai/c64-keyboard-font

A font that recreates the actual lettering on C64 keycaps — Built from photographs of a real Central European Commodore 64 keyboard, this font reproduces the printed key legends, including all 63 PETSCII graphic symbols and function-key labels, as clean geometric outlines rather than the screen bitmap font. Useful for retro-computing designers, emulator UIs, or print projects needing authentic C64 keycap typography.

Photo-based reconstruction of classic Commodore 64 keycap lettering, with desktop fonts, webfont, editable outlines, and a specimen.

coji/natural-japanese

An Agent Skill that strips AI stiffness out of Japanese work writing — This Claude/Codex Agent Skill rewrites AI-generated Japanese reports, minutes, and PR descriptions into natural phrasing without adding facts or changing certainty levels. Tests across 25 documents show bold-text overuse dropping from 551 to 13 instances, aimed at writers polishing AI drafts.

仕事の日本語を、読みやすくわかりやすく書く・直すための Agent Skill です。

nanaism/yomiyasu

An Agent Skill that cleans up AI-sounding Japanese prose — A Claude Code/Codex/Cursor skill that fixes the structural tics of AI-generated Japanese—vague metaphors, unclear subject-predicate links, inanimate subjects—rather than just banning buzzwords. Aimed at writers of technical docs, specs, PR descriptions, and internal reports who need naturally readable Japanese.

AI生成の日本語を自然な日本語へ推敲するAgent Skill / Agent Skill for Refining AI-Generated Japanese into Natural Japanese

apache/seatunnel

SeaTunnel extends data integration to multimodal and LLM workloads — Apache SeaTunnel syncs huge data volumes across 160+ connectors, now covering video, images, and unstructured text alongside structured data for embeddings and LLM pipelines. It runs on Zeta, Flink, or Spark engines, supporting batch, streaming, and CDC with a distributed snapshot algorithm for consistency. Useful for teams needing flexible, multi-engine data pipelines.

SeaTunnel is a multimodal, high-performance, distributed, massive data integration tool.

nekorobiaws-maker/jev-graphrag-poc

GraphRAG without embeddings, driven by score thresholds — A proof-of-concept GraphRAG system that skips vector search and embeddings entirely, using Jev (TypeSafe AI) scores and thresholds to decide entity registration, graph traversal entry points, and when to stop hopping. Claude Haiku 4.5 is used only for final answer generation from the gathered evidence chunks. Built on AWS with DynamoDB, Lambda, and CDK.

エンベディングを使わない判断特化型GraphRAGのPoC（判定はJev、回答はClaude Haiku 4.5）

cursor/plugins

Official spec and plugin registry for extending Cursor agents — Defines the manifest format for Cursor plugins and ships a growing collection of official ones, from CI workflows and PR review canvases to self-referential AI loops and repo compatibility scanners. Useful for developers who want to extend Cursor's agent behavior or build their own plugins.

Cursor plugin specification and official plugins