agentdb-memory-guard

Screen what goes into AgentDB memory for prompt injection with the opt-in aidefence guard (AGENTDB_INJECTION_GUARD=warn|block). Use when agents store text from untrusted sources (web pages, tool output, user uploads) into episodes, patterns or skills; when a recalled memory contains instructions; or when the user asks how to stop memory poisoning in AgentDB.

Jump to install Review files

Repository: ruvnet/agentdb
Last source activity: November 5, 2026 at 23:50
Detected SKILL.md language: English
Stars: 97
Forks: 16

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/ruvnet/agentdb/tree/main/.agents/skills/agentdb-memory-guard.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/ruvnet/agentdb --skill agentdb-memory-guard

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

name	agentdb-memory-guard
description	Screen what goes into AgentDB memory for prompt injection with the opt-in aidefence guard (AGENTDB_INJECTION_GUARD=warn\|block). Use when agents store text from untrusted sources (web pages, tool output, user uploads) into episodes, patterns or skills; when a recalled memory contains instructions; or when the user asks how to stop memory poisoning in AgentDB.

Back to search Back to installation

agentdb-graph-partition

Partition or prune an AgentDB graph in code — exact minimum cut with MincutService (backed by @ruvector/mincut-wasm) and Personalized PageRank sparsification with SparsificationService (backed by @ruvector/graph-transformer). Use when splitting a memory or causal graph at its weakest link, finding the bottleneck between two clusters, keeping only the nodes most relevant to a seed node before attention, or when the user asks which native graph packages AgentDB uses.

2026-11-05

agentdb-quantized-search

Speed up AgentDB's built-in sql.js vector backend on large collections with the opt-in RaBitQ 1-bit quantized index (@ruvector/rabitq-wasm). Use when SqlJsRvfBackend search gets slow past ~10,000 vectors, when choosing between exact and approximate search for a browser or no-native install, or when the user asks about RaBitQ or quantized search in AgentDB.

2026-11-05

agentdb-vector-memory

Store and recall memory with AgentDB's own MCP server — semantic facts (agentdb_insert/agentdb_search), reasoning patterns (agentdb_pattern_store/agentdb_pattern_search) and certified recall. Use when the user says "remember this", "save this for later", "what do we know about X", or before starting a task that may have prior context.

2026-11-01

View all from this repository

agentdb-memory-guard

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository