Summary
This is a persistent state manager for long-running agent workflows that you install in two parts: an MCP server for storage and a skill file that teaches the agent when to compact memory. It monitors word counts to trigger compression cycles and includes a self-healing strategy to break infinite loops when agents get stuck. You'd reach for this when working with smaller models that have limited context windows but need to maintain state across extended tasks. The server exposes standard memory operations through stdio transport, while the skill instructions live in SKILL.md and orchestrate when to save, retrieve, and compress context. Think of it as giving any model the persistent memory behavior of larger ones without requiring massive context.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Agentic Loop Memory Server ♾️
The industry-standard persistent memory and state manager for long-running agentic workflows.
Enable 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.
🛠 Complete Setup (Required)
For the best experience, you must install both the orchestration skill and the MCP server.
1. Install the Skill
Install the agentic-loop skill into your AI agent (Codex, Claude Code, Cursor, Gemini CLI, GitHub Copilot, and other Agent Skills hosts):
npx skills add meharajM/agent-loop-mcp@agentic-loop -g -y
Preview the skill before activation:
gh skill preview meharajM/agent-loop-mcp agentic-loop
2. Configure the MCP Server
Add the following to your `mcp_config.json`:
{
"mcpServers": {
"agent-loop": {
"command": "npx",
"args": ["-y", "@mhrj/mcp-agent-loop"]
}
}
}
🌟 Why this approach is unique
Unlike 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.
📂 Project Structure
src/: TypeScript source for the MCP server.skills/agentic-loop/SKILL.md: The instruction manual for the AI.build/: JavaScript artifacts.
📄 License
ISC
Featured
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Categories
Registryactive
Package@mhrj/mcp-agent-loop
TransportSTDIO
UpdatedMar 25, 2026
