開源專案目錄

WSTxda

SwitchAI

★ 1,430

在 Android 上輕鬆選擇、啟動和管理您首選的 AI 數位助理。

exoharness

exo

★ 1,430

Exo is an agent + harness architecture that is fully recursive, able to safely edit all aspects of itself at runtime to get better at your tasks.

phronesis-io

eigenflux

★ 1,429

Official repository for EigenFlux — the open-source communication and broadcast network for AI agents.

winedarksea

AutoTS

★ 1,428

Automated Time Series Forecasting

tejaswigowda

ffmpeg-webCLI

★ 1,428

A browser-based video editor powered by ffmpeg.wasm. No uploads, no servers -- all processing happens locally in your browser using WebAssembly.

icebird1998

drawio-scientific-illustrator

★ 1,427

Live MCP control of the visible draw.io canvas for step-by-step scientific illustration in Codex.

inkeep

agents

★ 1,425

Create AI Agents in a No-Code Visual Builder or TypeScript SDK with full 2-way sync. For shipping AI assistants and multi-agent AI workflows.

debops

debops

★ 1,424

DebOps - Your Debian-based data center in a box

ovg-project

kvcached

★ 1,424

Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond

yohey-w

multi-agent-shogun

★ 1,423

Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigaru hierarchy.

nagisanzenin

engram

★ 1,423

Evidence-based learning engine — first-principles curricula, free-recall verification with receipts, FSRS-scheduled memory, and explorable artifacts. Learn anything; keep it.

benman1

generative_ai_with_langchain

★ 1,422

Build production-ready LLM applications and advanced agents using Python, LangChain, and LangGraph. This is the companion repository for the book on generative AI with LangChain.

mythrantic

ollama-docker

★ 1,422

Welcome to the Ollama Docker Compose Setup! This project simplifies the deployment of Ollama using Docker Compose, making it easy to run Ollama with all its dependencies in a containerized environment

syv-ai

qwen38-27b-rtx3090

★ 1,422

Qwen3.8-27B on a single RTX 3090 with vLLM: ~1,000 tok/s at 64 concurrent (int8 tensor-core GEMMs, fp16 DeltaNet state), ~114 tok/s single-user at default sampling / ~124 greedy (MTP drafts, own-output draft vocab, calibrated int4 lm_head, split-KV verify attention), 150k-262k context; patches, requant scripts, benchmarks

WPeace-HcH

WPeGPT

★ 1,421

An IDA plugin for binary file analysis, powered by AI models such as OpenAI and DeepSeek.

nextcloud

deck

★ 1,421

🗂 Kanban-style project & personal management tool for Nextcloud, similar to Trello

aquasecurity

trivy-action

★ 1,421

專案速覽：將 Trivy 作為 GitHub 操作運行以掃描 Docker 容器映像是否有漏洞。

fergiemcdowall

search-index

★ 1,421

A persistent, network resilient, full text search library for the browser and Node.js

apple

swift-system

★ 1,420

Swift 的低階系統呼叫和類型。 Swift 系統 Swift 系統為系統呼叫和低階貨幣類型提供了慣用的介面。

mnemox-ai

tradememory-protocol

★ 1,420

Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.