ToolAI.io · GitHub 채널
GitHub의 전체 ToolAI 오픈 소스 AI 프로젝트 디렉터리를 주제, 언어 및 라이선스별로 살펴보세요.
공개 리포지토리 데이터
oomol-lab/open-connector
An open-source authentication gateway that connects over 1,000 SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI interfaces.
openagents-org/openagents
An open-source platform providing a collaborative operating system for AI agents, enabling unified workspace management, multi-agent coordination, and network integration without vendor lock-in.
agentscope-ai/reme
ReMe is a local-first memory layer for AI agents that transforms conversations and resources into readable, editable, and searchable Markdown memory files.
modelscope/evalscope
A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.
makecindy/cindy
Cindy is an open-source desktop and mobile AI-agent client that works with local files, signed-in applications, browsers, computers and phones. It supports Claude Code and Codex harnesses, multiple model-access options, persistent workspace context, automation and MCP integrations.
future-agi/future-agi
An open-source, self-hostable platform for evaluating, tracing, simulating, protecting, routing, and optimizing LLM and AI-agent applications.
taichuy/1flowbase
An open-source AI gateway that allows local agent clients to publish fusion-style multi-model workflows as OpenAI and Claude-compatible virtual models, providing full observability into traces, tokens, latency, and costs.
hal0ai/hal0
An open-source, self-hosted home AI inference platform designed to turn a Linux box into an OpenAI-compatible inference appliance, with native optimization for AMD Strix Halo hardware.
dotharness/dotcraft
An open-source, self-hosted, project-scoped AI agent runtime that provides persistent sessions, memory, background work, and automations shared across Desktop, CLI, bots, and applications.
QwenLM/qwen-code
An open-source AI coding agent that lives in your terminal
cloudgeni-ai/opengeni
An open, self-hostable agentic runtime for organizations that provides durable, replayable agent sessions, human approvals, governed credentials and memory, and flexible compute targets including managed sandboxes and enrolled user hardware.
mtrnix/metronix-memory
Self-hosted memory infrastructure for AI agents featuring MCP-native integration, hybrid RAG, a temporal knowledge graph, and an ontology layer, designed for local-model friendliness and durable, agent-scoped context.
3 / 4페이지 · 프로젝트 38개
