エージェントとマルチエージェント
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.
★ 56⑂ 5TypeScript
Apache-2.0Q86
MCPとツール呼び出し
soapbucket/sbproxy
An open-source, self-hosted Enterprise AI Gateway and LLM proxy written in Rust, providing an OpenAI-compatible API for over 60 providers and supporting local model hosting, MCP tool federation, and robust traffic governance.
★ 49⑂ 1Rust
Apache-2.0Q86
MCPとツール呼び出し
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.
★ 39⑂ 7Python
Apache-2.0Q86
MCPとツール呼び出し
mycelium-hq/ai-brain-starter
An operating system and verification harness for Claude Code that provides persistent memory, accountability, journaling, and knowledge graph capabilities, ensuring context compounds across sessions rather than corrupting.
★ 33⑂ 25Python
MITQ86
エージェントとマルチエージェント
pwrdrvr/pwragent
An open-source desktop coding agent that runs locally on a laptop and can be driven remotely via messaging platforms like Telegram, Discord, Slack, Mattermost, Feishu, Lark, or LINE.
★ 29⑂ 4TypeScript
MITQ86
MCPとツール呼び出し
gethuman-sh/human
An open-source AI Software Factory that integrates tickets, docs, designs, and analytics into a secure pipeline, outputting shipped code via Claude-driven agents.
★ 62⑂ 6Go
MITQ85
AIコーディングと開発者ツール
openai/openai-python
The official Python library for the OpenAI API
★ 31.2K⑂ 5KPython
Apache-2.0Q84
評価・オブザーバビリティ・安全性
NVIDIA/garak
the LLM vulnerability scanner
★ 8.9K⑂ 1.2KPython
Apache-2.0Q84
エージェントとマルチエージェント
anthropics/claude-agent-sdk-python
An open-source project focused on python sdk for agent applications.
★ 7.9K⑂ 1.2KPython
MITQ84
LLMと基盤モデル
QwenLM/Qwen3
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud
★ 27.5K⑂ 2KPython
ライセンス未検出Q82
評価・オブザーバビリティ・安全性
openai/evals
Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks
★ 19.2K⑂ 3.1KPython
NOASSERTIONQ82
LLMと基盤モデル
QwenLM/Qwen3-Coder
Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team
★ 16.8K⑂ 1.2KPython
ライセンス未検出Q82