Agent♥︎Age
Catalog

agentmem

Official

by Thezenmonster · Python

Governed memory for coding agents. Trust lifecycle, conflict detection, health scoring.

io.github.Thezenmonster/agentmem — Model Context Protocol (MCP) Server

agentmem is a governed shared-memory MCP server for coding agents. It manages trust lifecycle, detects conflicts, and assigns health scoring, so agent memory stays aligned with what is still true. It is positioned for saving sessions and preventing repetition of stale or conflicting rules across tools.

🛠️ Key Features

  • Governed memory for coding agents
  • Trust lifecycle management
  • Conflict detection
  • Health scoring
  • Session saving

🚀 Use Cases

  • Shared memory across Claude Code, Cursor, and Codex
  • Catch stale rules and conflicting rules during agent runs
  • Reduce repeated old mistakes in iterative coding workflows

⚡ Developer Benefits

  • Maintains a “knows what’s still true” memory state
  • Supports local-first workflows with memory governance concepts
  • Uses MCP-related integration patterns (includes MCP topic)

⚠️ Limitations

  • Description provided only covers trust lifecycle, conflict detection, health scoring, and session saving; no other capabilities are stated.

Topics

agentagent-memoryaiartificial-intelligenceclifts5llmmcpmemorymodel-context-protocolpythonsqliteclaude-codecoding-agentscursorlocal-firstmemory-governance