remember vs memory-poisoning-detection
remember and memory-poisoning-detection are both agent skills for agent memory. remember is published by langchain-ai (the vendor) and memory-poisoning-detection by Tencent (the vendor). Both install in Claude Code, Claude apps, Codex and Cursor. On GitHub, remember has 30,550 stars and memory-poisoning-detection has 7,079. Both were last active in Oct 2026. The table lines up where they differ (publisher, license and GitHub stars) and has the install commands for both. Everything here comes from the listings' public sources and is refreshed daily. remember describes itself as: Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback —…. memory-poisoning-detection: Detect persistent instruction injection or long-term memory poisoning. Licenses: remember MIT, memory-poisoning-detection Apache-2.0.
Updated Oct 26, 2026 · Built from catalog data; how we rank and grade
remember
langchain-ai
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback —…
memory-poisoning-detection
Tencent
Detect persistent instruction injection or long-term memory poisoning.
Who should pick which
- remember has the larger community: 30,550 GitHub stars against 7,079.
From listing data only. We don't pick a winner on security beyond the grades; read how grades work.
Side by side
| Fact | remember | memory-poisoning-detection |
|---|---|---|
| Type | Skill | Skill |
| Publisher | langchain-aiOfficial | TencentOfficial |
| License | MIT | Apache-2.0 |
| Pricing | free | free |
| Runs | Not stated | Not stated |
| Auth | Not stated | Not stated |
| Hosts supported | Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf | Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf |
| Tools | Not listed yet | Not listed yet |
| Security grade | –Security: not graded yet | –Security: not graded yet |
| Freshness grade | AFreshness: A | AFreshness: A |
| GitHub stars | 30,550 | 7,079 |
| Weekly downloads | Not measured | Not measured |
| Last release | Oct 23, 2026 | Oct 22, 2026 |
| Last activity | Oct 23, 2026 | Oct 22, 2026 |
Facts from each listing's public sources, checked daily. Tool lists arrive with tool scans.
Install
remember
npx skills add langchain-ai/deepagents --skill remember
Asks which agents to install it for (add -g for all projects). Needs Node.js 22.20+.
memory-poisoning-detection
npx skills add Tencent/AI-Infra-Guard --skill memory-poisoning-detection
Asks which agents to install it for (add -g for all projects). Needs Node.js 22.20+.
Also consider
- 0.849score
memory-rag-poisoning-detection
TencentOfficial
Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.842score
engram-memory
Gentleman-Programming
ALWAYS ACTIVE — Persistent memory protocol.
SkillAFreshness: A★ 7.6KClaude Code +9 - 0.828score
zylos-memory
zylos-ai
Core memory system.
SkillAFreshness: A★ 1.2KClaude Code +9
Questions
- Is remember or memory-poisoning-detection more popular?
- remember has more GitHub stars (30,550 against 7,079). Stars measure attention, not quality, so check freshness and docs too.
- Do remember and memory-poisoning-detection work with Claude Code?
- Yes, both list a Claude Code install; the commands are on this page.
- Are remember and memory-poisoning-detection open source?
- Yes: remember is MIT and memory-poisoning-detection is Apache-2.0.
Related
Cite this page
remember vs memory-poisoning-detection. Agent Mart. https://agentmart.dev/compare/langchain-ai-remember-vs-tencent-memory-poisoning-detection (last updated 2026-10-26)