EDDiscovery
Captains log and 3d star map for Elite Dangerous
HYSEN LABS ディレクトリ
正確な分類、検証済みメタデータ、実用的な文脈で注目プロジェクトを整理します。
Captains log and 3d star map for Elite Dangerous
ID-based RAG FastAPI: Integration with Langchain and PostgreSQL/pgvector
VLESS+XHTTP+TLS Auto-Installer for Ubuntu — Vercel / Netlify relay
Zero-copy, content-addressed Rust build cache for Rust, C/C++ and more. No copies, no wasted disk — just hardlinks locally and S3 for sharing.
Backend that powers the dataset viewer on Hugging Face dataset pages through a public API.
Croissant is a high-level format for machine learning datasets that brings together four rich layers.
Turn vague or complex Codex tasks into strong `/goal` commands with outcome, verification, constraints, boundaries, iteration policy, completion evide
プロジェクト概要:ブラウザー内で動作する、オープンソースのトランスクリプトベースのビデオ/オーディオ エディター。
Open karaoke party system
An inference server for your machine learning models, including support for multiple frameworks, multi-model serving and more
A code-driven presentation generation framework. 像构建软件工程一样生成演示文稿。
A simple but powerful self-hosted finance tracker
A self-hostable personal AI agent with vector memory, Composio tools, and Telegram.
Atom Agent, Open-Source Governed AI Agent Platform for Self-Hosted Automation
科研绘图skill、论文绘图skill、图片转visio等可编辑格式,将生成图转化为论文可编辑图,便于作者调整绘图细节
AgentChat 是一个基于 LLM 的智能体交流平台,内置默认 Agent 并支持用户自定义 Agent。通过多轮对话和任务协作,Agent 可以理解并协助完成复杂任务。项目集成 LangChain、Function Call、MCP 协议、RAG、Memory、HITL、Skill、Milvus 和 ElasticSearch 等技术,实现高效的知识检索与工具调用,使用 FastAPI 构建高性能后端服务。
A self-hosted web dashboard for the Hermes AI agent stack. Provides a browser-based terminal, file explorer, session overview, cron management, system metrics, and an agent status panel — all behind a single password gate.
Open deep learning compiler stack for Kendryte AI accelerators ✨
面向 iOS 定位服务行为研究和开发测试的虚拟定位工具,支持地图选点、本地与第三方代理、WGS-84 / GCJ-02 双坐标、环境检测和问题诊断。
A minimalist SOTA LaTeX OCR model with only 20M parameters, running in browser. Full training pipeline available for self-reproduction. | 超轻量SOTA LaTeX公式识别模型,仅20M参数量,可在浏览器中运行。训练全流程代码开源,以便自学复现。