Who is agent-memory-guard for?

agent-memory-guard is an open-source project built for AI security engineers.

What platforms does agent-memory-guard run on?

agent-memory-guard runs on the command line.

Is agent-memory-guard still active?

The GitHub repository shows 252 commits in the last 90 days.

What are alternatives to agent-memory-guard?

Similar projects tracked by PulseGate include AgentGuard, ai-agentguard, and inter-agent-guard.

Who develops agent-memory-guard?

agent-memory-guard is developed by OWASP.

When did agent-memory-guard launch?

agent-memory-guard first shipped in 2026.

Back to the index

agent-memory-guard

Name: agent-memory-guard
Author: OWASP

PyPIInfrastructure

agent-memory-guard is an open-source CLI tool that provides runtime defense for AI agent memory, protecting against poisoning, tool abuse, and privilege escalation. It is designed for AI security engineers and follows OWASP guidelines.

Open SourceApache-2.0CLI

Visit PyPI

57stars

18forks

5features

2026since

Overview

5 features

agent-memory-guard sits in PulseGate's Security & compliance platforms category. It focuses on preventing memory poisoning and privilege escalation in AI agent systems. It is built as an open-source project for AI security engineers. agent-memory-guard is open source under the Apache-2.0 license. It ships for the command line.

Behind agent-memory-guard is OWASP, and it first shipped in 2026. The project is developed in the open on GitHub with 57 stars and 252 commits in the last 90 days. Key capabilities include memory protection, prompt injection defense, and privilege escalation guard.

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

Memory protection
Prompt injection defense
Privilege escalation guard
Agent security
OWASP compliance

Built with & integrations

Framework

FastAPI

Runs on

CLI

Trust & compliance

License

Apache-2.0

Verified signals

HTTPSOpen SourceFree tierGitHub · ★ 57Active maintenance

Indexing history

What PulseGate has recorded for this listing

Indexed30 Jun · 03:16 UTC
agent-memory-guard verified against its public source
Source: PulseGate · Open

Frequently asked questions about agent-memory-guard

What is agent-memory-guard?: Agent-memory-guard focuses on preventing memory poisoning and privilege escalation in AI agent systems. It is catalogued under Security & compliance platforms on PulseGate.
Who is agent-memory-guard for?: agent-memory-guard is an open-source project built for AI security engineers.
Is agent-memory-guard free?: Yes — agent-memory-guard is open source under the Apache-2.0 license and free to use.
What platforms does agent-memory-guard run on?: agent-memory-guard runs on the command line.
Is agent-memory-guard still active?: The GitHub repository shows 252 commits in the last 90 days.
What are alternatives to agent-memory-guard?: Similar projects tracked by PulseGate include AgentGuard, ai-agentguard, and inter-agent-guard.AgentGuard ai-agentguard inter-agent-guard
Who develops agent-memory-guard?: agent-memory-guard is developed by OWASP.
When did agent-memory-guard launch?: agent-memory-guard first shipped in 2026.

At a glance

Platforms: Cli
Languages: English
Open source: Yes · ★ 57
License: Apache-2.0
Built for: AI security engineers
Model: Open source
Solves: Preventing memory poisoning and privilege escalation in AI agent systems.

Registered as

GitHub: OWASP/www-project-agent-memory-guard
PyPI: agent-memory-guard

Developer

OWASP

Team

GitHub

Open source

View on GitHub

Stars: 57
Forks: 18
Open issues: 11
Last commit: 30 Jun 2026
Commits 90d: 252
Contributors: 11
Authorship: Team
Default branch: main
Latest release: v0.3.0 · 10 Jun 2026

Index record

Identity confidence: Low · 64
Indexed: 30 Jun 2026
Lifecycle: Alive
Last seen: 30 Jun 2026

Identity audit (12)

Slug: agent-memory-guard-pypi-org
Lifecycle last checked: 8 Aug 2026
Verification state: Indexed for public listing
Listing state: Listed: yes
Index status: Included in index
Latest evidence snapshot: 30 Jun 2026
Timeline basis: Indexed-at chronology. This listing's first-seen date was written by the catalog backfill, not observed here, so it is not treated as a sighting.
Name from: Written by a language model from the project's public pages.
Category from: Assigned by a language model.
Summary from: Written by a language model from public pages.
Languages from: Detected by a language model from page content.
Canonical URL: https://pypi.org/project/agent-memory-guard

Ship this? Send a correction — no account, and you get a link to follow it.

Similar projects

Closest matches by what these projects do