Skill ディレクトリ

AI Agent のための再利用可能な Skill を見つける。

タスクで実際の GitHub Skill を検索し、利用前に Stars、Trust、監査、カテゴリ、インストール経路を確認できます。

すべての推奨は、リポジトリ、監査、インストール経路に明確につながっています。

検索結果: agi-agents

英語版ディレクトリ

Build, run, and manage agent platforms.

42K
Stars
84/100
信頼
カテゴリ: agent-frameworks監査

AI suite powered by state-of-the-art models and providing advanced AI/AGI functions. Includes AI personas, AGI functions, world-class Beam multi-model chats, text-to-image, voice, response streaming, code highlighting and execution, PDF import, presets for developers, much more. Deploy on-prem or in the cloud.

7.0K
Stars
84/100
信頼
カテゴリ: agent-frameworks監査
Agi77

The first distributed AGI system. Thousands of autonomous AI agents collaboratively train models, share experiments via P2P gossip, and push breakthroughs here. Fully peer-to-peer. Join from your browser or CLI.

1.9K
Stars
77/100
信頼
カテゴリ: agent-frameworks監査

Semantica 🧠 — AI-native knowledge graph intelligence framework for semantic retrieval, ontology reasoning, context graphs, and explainable AI systems.

1.3K
Stars
84/100
信頼
カテゴリ: agent-frameworks監査

Open-source, end-to-end platform for evaluating, observing, and improving LLM and AI agent applications. Tracing · Evals · Simulations · Datasets · Gateway · Guardrails. Self-hostable. Apache 2.0.

1.2K
Stars
85/100
信頼
カテゴリ: devops監査

Recursive-Open-Meta-Agent v0.1 (Beta). A meta-agent framework to build high-performance multi-agent systems.

5.1K
Stars
74/100
信頼
カテゴリ: agent-frameworks監査

EvoSkill — An open-source framework that automatically discovers and synthesizes reusable agent skills from failed trajectories to improve coding agent performance.

892
Stars
73/100
信頼
カテゴリ: agent-skills監査

A repo lists papers related to LLM based agent

2.3K
Stars
67/100
信頼
カテゴリ: agent-frameworks監査

🤖 Awesome list of AGI Agents. Agents 精选资源合集.

538
Stars
67/100
信頼
カテゴリ: agent-frameworks監査

Common interface for interacting with AI agents. The protocol is tech stack agnostic - you can use it with any framework for building agents.

1.5K
Stars
72/100
信頼
カテゴリ: agent-frameworks監査

AGI-oriented, hallucination-resistant AI coding runtime grounded in evidence, tools, memory, agents, and verification.

340
Stars
70/100
信頼
カテゴリ: agent-frameworks監査

Learn from your vibe coding instead of just clicking Accept. AhaDiff turns each AI diff into a code-verified lesson, quiz, and review. · 别再无脑 vibe coding 啦!让你从 vibe coding 中学到真东西。每次改动都变成能查证的课程、测验和复习。

216
Stars
70/100
信頼
カテゴリ: coding-agents監査