New Generation

Custom firmware for Bambu Lab X1 and X1 Carbon 3D printers

Action for generating build provenance attestations for workflow artifacts

Unofficial ROS2 SDK support for Unitree GO2 AIR/PRO/EDU

[ECCV 2024] The official code of paper "Open-Vocabulary SAM".

Fastest SQLite library for react-native by @ospfranco

The official CodeStitch Intermediate kit, featuring 11ty, Decap CMS and SASS - all set up for you! Perfect for websites of all sizes.

表情包生成器，用于制作各种沙雕表情包

Web & desktop (Electron) client for the OCTO open workplace — one React + TypeScript codebase shipping browser and PC surfaces, with first-class AI agent UX.

The MATLAB Agentic Toolkit brings trusted MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.

♾️ 开源数字永生框架 — 从聊天记录蒸馏任何人的七维数字分身。支持微信/飞书/iMessage/Telegram等12+平台，7种角色模板，对齐 OpenClaw Soul Spec 标准。一行指令让你的AI学会蒸馏。

A comprehensive guide to running autonomous AI coding loops using Geoff Huntley's Ralph methodology. View as formatted guide below 👇

learn docker in your terminal, with bite sized exercises

Representation Engineering: A Top-Down Approach to AI Transparency

AutoEvals is a tool for quickly and easily evaluating AI model outputs using best practices.

mac code — Claude Code, but it runs on your Mac for free. 35B AI agent at 30 tok/s via Apple Silicon flash-paging. $0/month.

LINGUISTIC ENGINE FOR AI

GLM-Image: Auto-regressive for Dense-knowledge and High-fidelity Image Generation.

The fast and secure Load Balancer / API Gateway / Reverse Proxy with built-in service discovery, GeoIP, WAF, bot protection and much more - https://pingoo.io

leetcode and programming guides from Bitflip's youtube tutorials

[ICLR 2025 Oral] Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models

Googles NotebookLM but local

An intuitive app icon generator that lets you customize colors, borders, shadows, and more to create unique app icons effortlessly.

A lightweight multilingual LLM

电报自动执行（签到、发送消息、点击键盘、AI回复等）；个人、群组、频道消息监控、转发与自动回复。Automated Telegram tasks (check-ins, sending messages, keyboard clicks, AI replies, etc.); monitoring, forwarding, and auto-replying to private, group, and channel messages.

Long-term memory runtime for AI agents — plain Markdown as the source of truth, local ranked retrieval, and an independent sleep-time Manage layer. Claude Code and Codex share one store. No API key.

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

Open-source universal artifact registry. Drop-in Artifactory/Nexus alternative with 40+ package formats, security scanning, WASM plugins, and edge replication.