AI 开源项目

Open-source voice typing for Windows — a Wispr Flow / Superwhisper alternative. Press a shortcut, speak, and AI-polished text lands at your cursor. Local models, your own API keys, or a self-hosted backend.

Embeddable RAG library for Elixir/Phoenix with agentic pipelines and dashboard

AI-powered Vibe Investing for NASDAQ, S&P500 & crypto: LLM quant trading tools, multi-agent backtesting, and data-driven market columns (mNAV arbitrage, BTC-Nasdaq coupling, Alpha Arena). 미국 주식·가상화폐 AI 투자 큐레이션·칼럼·트레이딩 봇.

AI 每日新闻简报 · GitHub 热门 + X 热门文章 + 行情技术分析 · 23 个数据源聚合 + LLM 中文摘要 · 本地或 GitHub Actions 部署

🌱 Argus 是一个基于 RAG 架构的开源知识库平台，后端采用 Java 21 + Spring Boot + MyBatis-Plus + PostgreSQL/pgvector，前端采用 Vue 3 + TypeScript + Element Plus，AI 层基于 Spring AI Alibaba（通义千问）+ ReactAgent 图引擎，以 MinIO + Elasticsearch 为存储与检索引擎。

The fastest workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.

FoJin-powered Buddhist AI persona framework — source-grounded, boundary-aware, fidelity-tested, runtime-ready.

Lightweight AI Agent Harness for agentic coding: let strong models explore while humans steer with minimal specs, checkpoints, approval, validation, and reverse sync.

다이소를 MCP로! 뿐만 아니라 한국 로컬 리테일과 영화관 조회를 MCP, CLI, Codex Skill로 가능하게 해줍니다.

🤖 AI News Aggregator - 自动聚合 80+ AI/科技资讯源，支持 RSS 订阅导入，智能过滤 AI 相关内容，双语标题翻译，每 2 小时自动更新

AI-writing humanizer for KO/EN/ZH/JA

Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Discord, Feishu, DingTalk, WeCom, WeChat — with any LLM provider.

Provider-neutral control plane for durable-state agent swarms: subprocess workers, leases, artifacts, memory, and deterministic stitching.

本地优先的知识库桌面应用。Markdown 编辑器 + 全文搜索（FTS5） + 双向链接 / 知识图谱；多端同步（WebDAV / S3 / 同步盘，单笔记粒度增量 + 自动双向调度，含整库 ZIP 备份）；AI 问答与智能规划（OpenAI 兼容 / Ollama / 自定义 provider，工具调用框架）；支持导入 .md / .txt / .pdf / .docx（自动嗅探编码）；笔记加密 Vault + 隐藏笔记 PIN；自定义数据目录；跨平台 Win/macOS/Linux + 应用内自动更新。Tauri 2.x + React 19 + Rust + SQLite，零云端依赖。

Yet another coding agent harness, lightweight and written in go.

Open-source memory runtime for AI agents — reproducible, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hosted on Postgres + pgvector, Python + TypeScript SDKs.

audio.cpp with a full-task WebUI - pure C++ audio-model inference engine powered by ggml. TTS, ASR/STT, VAD, voice conversion, speaker diarization, music generation. No Python dependency.

[TMLR 26] EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

The OKF toolkit for Claude Code — author, maintain, validate & visualize Open Knowledge Format bundles. Plugin, agent skills, and a GitHub Action.

The semantic layer that makes enterprise data understandable to AI agents — model entities and relations once, query through SPL/MCP/REST, and connect telemetry, services, and business objects in one object graph.

High-performance LLM/VLM inference runtime and server for Apple Silicon / NVIDIA CUDA devices

Local-first AI conversation memory hub to capture, search, summarize, and export chats across major AI platforms. 本地优先的 AI 对话记忆与知识中台。

memra is a Rust + CUDA inference engine built for NVIDIA RTX PRO 6000 Blackwell and RTX 5090. It serves GGUF models over an OpenAI-compatible API, and every default it ships was measured on those two cards — both Blackwell sm_120a, with a separately compile-gated Hopper/H100 (sm_90a) lane alongside.

暂无项目简介。