Skip to content
Back to the index

memdebug

PyPIInfrastructure

PulseGate's liveness check found it on 7 Oct 2026; it is registered on GitHub and PyPI and has been in the index since 7 Oct 2026. How this is checked

memdebug is an Apache-2.0 Python package and CLI for inspecting, comparing, and rolling back the memory held by AI agents. It is local-first and agent-neutral, with capabilities aimed at memory forensics, prompt-injection investigation, and tamper-evident state management.

Inferred · not functionally tested

Open SourceApache-2.0CLISelf-hosted
Visit PyPI

Overview

6 features

Purpose: Inspecting, comparing, and recovering AI agent memory without relying on a hosted service.

Inferred · not functionally tested

Audience: AI agent developers and security researchers

Inferred · not functionally tested

Functions: Unknown

Interfaces: API: unknown · MCP: unknown · CLI: indicated (inferred, not tested) · Self-hosting: indicated (inferred, not tested)

Recorded constraints: pricing: open_source · license: Apache-2.0 · platforms: CLI · deployment: cli, self_hosted

Constraint provenance is unknown; confirm requirements with the publisher.

Record sources: pypi.org · github.com. These links do not verify the individual claims.

memdebug sits in PulseGate's Memory & skills category. Inferred · not functionally tested: Inspecting, comparing, and recovering AI agent memory without relying on a hosted service. Inferred · not functionally tested: memdebug is an open-source project aimed at AI agent developers and security researchers. Basis unknown · not verified: memdebug is open source under the Apache-2.0 license. Basis unknown · not verified: memdebug is available on the command line, and it can be self-hosted.

Juraj Jumic builds and maintains memdebug, and it first shipped in 2026. Development happens publicly on GitHub with 3 commits in the last 90 days. Inferred · not functionally tested: Among its 6 catalogued features are memory inspection, memory comparison, and memory rollback.

Summary written by a language model from the project’s public pages.

Tasks: Inferred · not functionally tested

  • Memory inspection
  • Memory comparison
  • Memory rollback
  • Local-first operation
  • Agent-neutral design
  • Prompt-injection forensics

Topics: Inferred · not functionally tested

Tags
agent-memorymemory-forensicsprompt-injection-defensetamper-evident-logs
AI capabilities
Text
Inference: Local

JSON profile · Text profile · Access guide

Built with & integrations

Runs on
CLISelf-hosted

Trust & compliance

License
Apache-2.0
Public signals
HTTPSOpen SourceFree tierGitHubActive maintenance

Indexing history

2

What PulseGate has recorded for this listing

  1. Indexed7 Oct · 12:58 UTC
    memdebug seen via PyPI Fresh Feed
    Source: PyPI Fresh Feed · Open
  2. Indexed7 Oct · 06:20 UTC
    memdebug seen via PyPI Bulk Enumerator
    Source: PyPI Bulk Enumerator · Open

Frequently asked questions about memdebug

What does memdebug do?
Inferred · not functionally tested: Inspecting, comparing, and recovering AI agent memory without relying on a hosted service. It is catalogued under Memory & skills on PulseGate.
Who should use memdebug?
Inferred · not functionally tested: memdebug is an open-source project built for AI agent developers and security researchers.
Is memdebug free?
Basis unknown · not verified: Yes — memdebug is open source under the Apache-2.0 license and free to use.
What platforms does memdebug run on?
Basis unknown · not verified: memdebug runs on the command line. It can also be self-hosted.
Is memdebug still active?
PulseGate's liveness check found it on 7 Oct 2026. Its GitHub repository shows 3 commits in the last 90 days.
What are alternatives to memdebug?
Similar projects tracked by PulseGate include mem-report, supermem, and memctl.mem-reportsupermemmemctl
Who makes memdebug?
memdebug is developed by Juraj Jumic.
When did memdebug launch?
memdebug first shipped in 2026.

Similar projects

Closest matches by what these projects do