Alternatives to memory-rag-poisoning-detection
memory-rag-poisoning-detection is an agent skill by Tencent: Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing. If it doesn't fit your setup, these 12 agent skills cover similar ground. They are ordered by how closely they match memory-rag-poisoning-detection and by our rank, which weighs adoption, freshness and documentation; money never changes the order. engram-memory leads the list (repository has 7.6K stars; active in the last 30 days). 2 of them are published by the company behind the product. Each entry shows data reasons to switch, and you can open a side-by-side comparison with memory-rag-poisoning-detection.
Updated Oct 26, 2026 · Built from catalog data; how we rank and grade
You're replacing
memory-rag-poisoning-detection
Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.
12 alternatives
Ordered by how closely each matches memory-rag-poisoning-detection (shared product, category or stated alternative) and by rank.
- 1engram-memory
Gentleman-Programming
ALWAYS ACTIVE — Persistent memory protocol.
- Repository has 7.6K stars
- Active in the last 30 days
★ 7.6KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 2zylos-memory
zylos-ai
Core memory system.
- Supports JavaScript
★ 1.2KLast active Oct 22, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 3hivemind-memory
activeloopai
Global team and org memory powered by Activeloop.
- Repository has 1.6K stars
- Active in the last 30 days
★ 1.6KLast active Oct 24, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 4nautilus-compass-memory
chunxiaoxx
Local-first long-term memory for AI agents via MCP — zero LLM calls at write time, typed retrieval at read time.
- Repository has 1.3K stars
- Active in the last 30 days
★ 1.3KLast active Oct 4, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 5story-memory
haowjy
Creative-writing domain knowledge for durable story state.
- Active in the last 30 days
- Open source (Apache-2.0)
★ 535Last active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 6remember
langchain-aiOfficial
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback —…
- Larger repository (30.6K stars)
★ 30.6KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6Compare →
AFreshness: A–Security: not graded yet - 7memory-poisoning-detection
TencentOfficial
Detect persistent instruction injection or long-term memory poisoning.
- Published by the vendor
- Repository has 7.1K stars
★ 7.1KLast active Oct 22, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 8comet-memory
rpamis
Use when Comet must decide whether a bounded semantic review packet contains a personal memory worth creating, updating, forgetting, or skipping.
- Repository has 3.2K stars
- Active in the last 30 days
★ 3.2KLast active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 9nbj-ob1-agent-memory-openclaw
NateBJones-Projects
Use Nate Jones OB1 Agent Memory from OpenClaw with provenance, scope, review, and use-policy discipline.
- Repository has 4.7K stars
★ 4.7KLast active May 4, 2026Claude Code, Claude apps, Codex, Cursor +6
CFreshness: C–Security: not graded yet - 10working-memory-protocol
Bitterbot-AI
Use when deciding what to record with working_memory_note, when the user says "remember this" or corrects you, or when a Crystal Pointer matches the topic.
- Repository has 2.5K stars
- Active in the last 30 days
★ 2.5KLast active Oct 22, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 11agent-memory
OpenHands
Persist and retrieve repository-specific knowledge using AGENTS.md files.
- Active in the last 30 days
- Open source (MIT)
★ 173Last active Oct 23, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 12experience-memory
robot-agent-exploration
Save successful action tips as soon as they work and retrieve them for later actions under matching observable conditions; distill reusable procedures into…
- Active in the last 30 days
- Open source (Apache-2.0)
★ 184Last active Oct 14, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet