AI チャンネル
AI エージェント

オープンソースの AI エージェント

AI エージェントとは、言語モデルを使って次に何をするかを決め、ブラウザーやコードインタープリター、API などのツールを呼び出し、タスクが終わるまでそれを繰り返すプログラムです。ここには、独自のエージェントを作るためのフレームワークから、コードを書く・Web を閲覧する・業務フローを実行するといった完成済みのエージェントまでが揃っています。

選び方

比べるポイントは三つです。使えるモデル(特定の一社だけか、ローカルモデルを含む OpenAI 互換のエンドポイントなら何でも使えるか)、エージェントにできることをどう制限するか(サンドボックス、承認ステップ、権限リスト)、そしてステップ間やセッション間で記憶を保持できるか。コードやシェルコマンドを実行するエージェントはサンドボックスで動かすべきなので、自分のマシンへのアクセスを許可する前に必ず確認しましょう。

スターの多いプロジェクト

425 件中 97–120 件
luhengshiwo

LLMForEverybody

7,329

每个人都能看懂的大模型知识分享,LLMs春/秋招大模型面试前必看,让你和面试官侃侃而谈

Jupyter Notebook
Zipstack

unstract

7,238

LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows

Python
zai-org

GLM-5

7,190

GLM-5: From Vibe Coding to Agentic Engineering

plastic-labs

honcho

7,180

Memory library for building stateful agents

Python

TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to communicate with Figma for reading designs and modifying them programmatically.

JavaScript
Gentleman-Programming

gentle-ai

6,829

Gentle-AI configures the AI coding agents you already use: Claude Code, Cursor, OpenCode, Codex, Pi, and more. Choose persistent memory, Spec-Driven Development, curated skills, MCP servers, personas, and optional bounded review. Open source, no agent lock-in.

Go
6,746

《大模型与智能体》电子书与 6 个编程任务:Transformer、mini-GPT、SFT/DPO、RAG、工具调用与编程智能体。

Python
BlockRunAI

ClawRouter

6,603

The agent-native LLM router for autonomous agents. Every frontier model behind one wallet, <1ms local routing, USDC payments on Base & Solana via x402.

TypeScript
j3ssie

osmedeus

6,566

A Modern Orchestration Engine for Security

Go
genkit-ai

genkit

6,441

Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google

TypeScript
haifengl

smile

6,414

Statistical Machine Intelligence & Learning Engine

Java
Arthur-Ficial

apfel

6,384

The free AI already on your Mac. CLI tool, OpenAI-compatible server, and interactive chat — all on-device via Apple Intelligence. No API keys, no cloud, no downloads.

Swift
PrefectHQ

marvin

6,199

an ambient intelligence library

Python
Helicone

helicone

6,158

🧊 Open source LLM observability platform. One line of code to monitor, evaluate, and experiment. YC W23 🍓

TypeScript
UfoMiao

zcf

6,084

Zero-Config Code Flow for Claude code & Codex

TypeScript
netease-youdao

LobsterAI

6,034

Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram.

TypeScript
5,976

The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.

Python
Mai-with-u

MaiBot

5,960

MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in the style of a real human. She does not pursue perfection, nor does she seek efficiency; instead, she values warmth, authenticity, and genuine connection.

Python
fengshao1227

ccg-workflow

5,889

多模型协作工作流引擎 — /ccg:go 一个命令,AI 自动分析意图、选择策略、编排 Codex + Gemini + Claude 协作执行

Go
AgentOps-AI

agentops

5,819

Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI

Python
Giskard-AI

giskard-oss

5,815

🐢 Open-Source Evaluation & Testing library for LLM Agents

Python
PySpur-Dev

pyspur

5,786

A visual playground for agentic workflows: Iterate over your agents 10x faster

TypeScript
areal-project

AReaL

5,762

The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.

Python
generalaction

emdash

5,748

Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.

TypeScript