{
  "markdown": "# Agentic Loop Memory Server ♾️\n\n[![Agent Skills](https://img.shields.io/badge/Agent%20Skills-open%20standard-111827)](https://agentskills.io/specification)\n[![skills.sh](https://skills.sh/b/meharajM/agent-loop-mcp)](https://skills.sh/meharajM/agent-loop-mcp)\n\n**The industry-standard persistent memory and state manager for long-running agentic workflows.**\n\nEnable any AI model—especially smaller ones with limited context windows—to function with the persistence of high-end models. This project works as a two-part ecosystem: an **MCP Server** for state management and an **Agent Skill** for orchestration.\n\n## 🛠 Complete Setup (Required)\n\nFor the best experience, you must install **both** the orchestration skill and the MCP server.\n\n### 1. Install the Skill\nInstall the `agentic-loop` skill into your AI agent (Codex, Claude Code, Cursor, Gemini CLI, GitHub Copilot, and other Agent Skills hosts):\n```bash\nnpx skills add meharajM/agent-loop-mcp@agentic-loop -g -y\n```\n\nPreview the skill before activation:\n\n```bash\ngh skill preview meharajM/agent-loop-mcp agentic-loop\n```\n\n### 2. Configure the MCP Server\nAdd the following to your \\`mcp_config.json\\`:\n```json\n{\n  \"mcpServers\": {\n    \"agent-loop\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"@mhrj/mcp-agent-loop\"]\n    }\n  }\n}\n```\n\n## 🌟 Why this approach is unique\nUnlike passive memory tools, this is an **Active State Manager**. It monitors word counts to trigger compaction cycles and enforces a \"Self-Healing Strategy\" on every failure, preventing AI agents from getting stuck in mindless loops.\n\n## 📂 Project Structure\n\n- `src/`: TypeScript source for the MCP server.\n- `skills/agentic-loop/SKILL.md`: The instruction manual for the AI.\n- `build/`: JavaScript artifacts.\n\n## 📄 License\n\nISC\n",
  "bytes": 1761,
  "sha": "e352c3b4b6b5a36e627779ad02f5ac17080d21e69bfe64107fef1295f8aebac7",
  "repo_slug": "meharajm/agent-loop-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_meharajm_agent_loop_mcp_4f1a67fb/readme"
}