An open roadmap project for building world models to evaluate robot policies, sharing training and inference pipelines, model weights, datasets, and evaluation leaderboards.
A fast wiki for people who think in folders, not feeds. Fast editing. Tree navigation. Markdown on disk. ([Demo](https://demo.leafwiki.com)) `MIT` `Docker/Go`
Skill package for AI agents that generates cover images and avatars, encapsulating multi-platform sizing and stylized image workflows behind simple mountable commands.
A TypeScript library for programmatic video editing in the browser, offering layers, GLSL filters and keyframe animation for developers building web video tools.
Multimodal model for embodied and edge vision delivering fine-grained open-world visual understanding, supporting object localization with abstention on missing targets for robotics developers.
🔥一个高效的多媒体支持操作库,可多方面的简单配置操作相册、拍照、录制、录音等功能。也支持配套使用的展示图片、视频、音频的九宫格功能。 (An efficient multimedia support operation library, can be a variety of simple configuration operation album, photo, recording, recording and other functions.Also support supporting the use of the display of pictures, video, audio of the nine grid function.)
Offers a privacy-first desktop client for Elasticsearch, OpenSearch, DynamoDB, MongoDB, and EasySearch, combining visual data management, monitoring, and natural-language querying for human operators.
一款lcx.exe在golang下的实现, 可用于内网穿透, 建立TCP反弹隧道用以绕过防火墙入站限制等, This tool is used to establish reverse tunnel in NAT network environment, it can bypass firewall inbound restriction, support all functions of lcx.exe
[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support Llama-3/3.1, Llama-2, LLaMA, BLOOM, Vicuna, Baichuan, TinyLlama, etc.
Coordinates Claude Code and Codex agents inside VS Code as a collaborative coding team, organizing brainstorming, debate, and synthesis to select stronger implementation approaches for developers.
An agent skill packaging more than ten thousand curated image-generation prompts compatible with models such as Midjourney, DALL-E, Flux, and Stable Diffusion, with semantic search and tailored recommendations for creators.
Your AI forgets. This remembers. Spec-driven coding harness for vibecoders, product owners, CEOs and real builders - self-improving context memory, 15 agents, 33 skills working with /goal, agent-team, & workflow on autopilot loops with 0 need for human gate. Kills context rot, ships features, not spaghetti. Claude Code & Codex. Any stack
Unofficial desktop wrapper for the open-source Penpot design tool offering multi-instance management and offline batch export capabilities for designers daily.
Local visual document parser that converts diverse files into AI-ready, searchable Markdown, supporting batch CLI processing and configurable models for knowledge workflows.
Reusable writing skill that standardizes style for Chinese technical documentation and product copy, providing lint scripts and mounts for popular coding assistants.
A browser-based batch subtitle translator for SRT/ASS/VTT/LRC that keeps timing intact while using 35+ engines to deliver bilingual output in 120+ languages with local caching.
Executable memory tool giving coding agents instant recall over local machine history, searching past agent sessions with source attribution like git blame for AI work.
Open-source API service for developers needing WeChat public-account articles, providing content fetching, RSS subscriptions, multi-format export, and proxy-pool handling for reliable access.
🚀 MassGen is an open-source multi-agent scaling system that runs in your terminal, autonomously orchestrating frontier models and agents to collaborate, reason, and produce high-quality results. | Join us on Discord: discord.massgen.ai
A fast cross-platform CLI that runs shell jobs in parallel with ordering, retries, timeouts, and resume support built for bioinformatics and complex workflows.
Real-time control room for agent societies that can pause, replay, interrogate, rewrite narratives, and export reproducible bundles for observers inspecting language-agent clusters.
Spring-based personal AI operating system where a single agent serves web admin, desktop app, embeddable widget, and eight IM channels from one JAR deployment.
A fast production-ready static web server with TLS (HTTPS), routing, hot reloading, caching, templating, and security in a single-binary you can set up with zero code.