Memdebug

Memdebug is a local developer tool that inspects, tracks, and rolls back AI agent memory changes.

Memdebug is a local, agent-neutral tool designed for developers who run AI agents with accessible memory stores like folders, git repositories, Open WebUI, or Mem0. It records what memory holds in a tamper-evident ledger, shows changes and timestamps, catches edits that bypassed store history, and compares snapshots. The tool acts as an independent observer that runs entirely on your computer without sitting between the agent and its memory. It supports command-line operations, browser viewing, and rollback functions for plain folders and git notes. The project is open source under the Apache License 2.0 and includes selftest capabilities to verify platform protections.

Memdebug at a glance

Best for: Software engineer
Runs on: macOS, Windows, Linux, CLI
Pricing: Free and open source under Apache License 2.0
Released: October 2026
Category: AI coding tool
Website: github.com/juraj-jumic/memdebug

Key features

Record memory contents in a tamper-evident ledger
Show memory changes and timestamps
Catch edits that bypassed store history
Compare memory snapshots
Roll back markdown memory safely
Run checks or watch for changes continuously
View memory history in a browser viewer

Use it for

Inspect what an AI agent's memory holds
Track changes and edits in AI agent memory
Roll back compromised or altered agent memory stores
Monitor agent memory for unauthorized modifications

Alternatives to Memdebug

claude-mem — It shares persistent, searchable agent memory across sessions and devices.
ProjectMem — Records project history locally to prevent AI from repeating failed work.
memU — It gives every connected agent a shared and inspectable memory layer.
OptMem — Provides permanent agent memory with fast lookups and no background processes.
memsearch — It shares continuous context across Claude Code, Codex, and other AI coding agents.
MemPalace — Achieves high recall with local-first storage and zero API calls.
AgentMemory — It runs locally with zero external databases and achieves high retrieval recall.
MuscleMemory — It cuts input tokens, tool calls, and execution time while maintaining task success.
AI Memory — Shared memory for coding agents that works across machines and team members.
MemMachine — Provides long-term persistent memory for LLM-based agents.
Agent Beacon — Retains coding agent knowledge across tools so errors do not repeat.
Memmy — Shares one persistent memory foundation across your different AI tools.

All Memdebug alternatives