Enterprise DNA Enterprise DNA
M MCP Servers Developer low

ihorponom/agentpack

by Various

Local task-state ledger for AI coding agents. Preserve decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, Cursor, and other MCP clients.

MCP

ihorponom/agentpack

Added 3 Sept 2026

#agent-state #ai-agents #claude-code #cli #codex #coding-agents #context-engineering #cursor

Overview

A local task-state ledger for AI coding agents. It preserves decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, Cursor, and other MCP clients. Built in TypeScript, it runs as a developer tool to maintain continuity between sessions.

Best for

Best for
Developers juggling multiple AI coding agents who need persistent task context.

Use cases

  • Track decisions and rationale across multiple AI coding sessions
  • Store evidence and source conclusions for agent-driven changes
  • Sync checkpoints between different MCP-compatible coding tools

How to use

Install

npm install -g agentpack-cli

Tested with

Claude Desktop, Claude Code, Cursor, Continue

Notes

A local task-state ledger for AI coding agents. It preserves decisions, source conclusions, evidence, and checkpoints across Codex, Claude Code, Cursor, and other MCP clients. Built in TypeScript, it runs as a developer tool to maintain continuity between sessions.

17 stars on GitHub. Last updated 2026-08-29. Licensed MIT.

Use cases

  • Track decisions and rationale across multiple AI coding sessions
  • Store evidence and source conclusions for agent-driven changes
  • Sync checkpoints between different MCP-compatible coding tools

Pros

  • Local storage keeps task state private and offline
  • Works across several popular AI coding clients via MCP
  • Simple TypeScript codebase for easy customization

Cons

  • Low star count suggests limited community validation
  • Requires MCP client support, limiting adoption
  • No built-in collaboration or remote sync features

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Local storage keeps task state private and offline
  • Works across several popular AI coding clients via MCP
  • Simple TypeScript codebase for easy customization

Cons

  • Low star count suggests limited community validation
  • Requires MCP client support, limiting adoption
  • No built-in collaboration or remote sync features
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

Running a business, not writing the code? See the MCP servers picked for operators, and get your first one wired up with us.

Operator picks