Score breakdown
Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.
Why it matters
Agent memory is becoming a persistent attack surface, especially when agents read prior notes before calling tools. This project is useful because it focuses on runtime checks and memory hygiene from an OWASP project page instead of only publishing advice.
Who should use it
Who should skip it
Skip OWASP/www-project-agent-memory-guard if the source link, documentation, or setup requirements do not align with your current workflow or stack.
About this signal
OWASP/www-project-agent-memory-guard is tracked by RepoRadar as a code repository in the Agent memory guardrails section. It was first seen on 2026-07-29 and last updated on 2026-07-29. The current verdict is 'try now' with a Gold tier and moderate setup difficulty. The standout signals for OWASP/www-project-agent-memory-guard are workflow potential (9.2) and maturity (8.4), while setup ease (6.5) trails — that balance shapes where it fits best. This page summarizes the evidence RepoRadar captured from https://github.com/OWASP/www-project-agent-memory-guard. The score, tier, risk label, and verdict on this page are never influenced by sponsorship, ads, or tips — they reflect only the usefulness, popularity, novelty, momentum, maturity, and evidence signals described in the RepoRadar methodology.
How this item is evaluated
RepoRadar assigned OWASP/www-project-agent-memory-guard a composite score of 7.7 out of 10, placing it in the Gold tier. This score combines weighted sub-signals: usefulness (35%), novelty (18%), momentum (14%), maturity (10%), open-source/build quality (7%), evidence quality (6%), workflow potential (6%), and setup ease (4%). Popularity is tracked separately at 100.0 and never affects the composite score or tier. The risk label of 'conditional' reflects inherent user-impacting hazards, not generic novelty. Items with no risk flag may still require normal code review before production use.
Putting this into practice? Read How to vet an AI agent or MCP server before you wire it in for the checklist behind this score.
Risk explanation
guardrails reduce risk but do not prove an agent is safe; teams should test with their own memory stores and tool policies; agents with persistent memory can still leak or act on sensitive context if configured poorly.