ClaudeWave
hotjp
hotjp

long-run-agent

View on GitHub

🔧 LRA - AI Agent长任务超稳定执行框架 ⚡ 轻量 | pip一键安装｜突破上下文限制 📌 7种状态管理 | Long-Running AI Agent Framework • One-click pip install｜Break context barriers • 7-status management. 5.0全面支持CLAUDE/OPEN CLAW/OPEN CODE/CUSOR/TREA 等全部Agent编程工具，仅需运行 lra init命令，就会生成Agent.md/CLAUDE.md/lra.md. 你的agent会自动学会如何使用

Subagents17 stars3 forks● PythonMITUpdated today
ClaudeWave Trust Score
79/100
✓ Trusted
Passed
  • ✓Open-source license (MIT)
  • ✓Actively maintained (<30d)
  • ✓Clear description
Last scanned: 4/14/2026
Install in Claude Desktop
Method detected: Manual
{
  "mcpServers": {
    "long-run-agent": {
      "command": "node",
      "args": ["/path/to/long-run-agent/dist/index.js"]
    }
  }
}
1. Copy the snippet above.
2. Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (Mac) or %APPDATA%\Claude\claude_desktop_config.json (Windows).
3. Replace any <placeholder> values with your API keys or paths.
4. Restart Claude Desktop. The MCP server appears automatically.
💡 Clone https://github.com/hotjp/long-run-agent and follow its README for install instructions.
About

Subagents overview

README preview not available. Visit the repo on GitHub for full documentation.
Related

More Subagents

affaan-m
everything-claude-code
·73

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

155.8k24.2kJavaScript· yesterday
Subagentsai-agentsanthropic
Snailclimb
JavaGuide
✓91

Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发

154.9k46.2kJava· yesterday
Subagentsagentcontext-engineering
langgenius
dify
✓97

Production-ready platform for agentic workflow development.

137.8k21.6kTypeScript· today
Subagentsagentagentic-ai
langchain-ai
langchain
✓94

The agent engineering platform

133.5k22.1kPython· today
Subagentsagentsai
NousResearch
hermes-agent
✓76

The agent that grows with you

83.5k11.2kPython· today
Subagentsaiai-agent
infiniflow
ragflow
✓95

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

78k8.8kPython· today
Subagentsagentagentic