mem0 is memory infrastructure that lets AI agents and applications store and retrieve information across interactions. It supports agents and developers who need persistent context for AI systems.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/mem0ai/mem0/memory-reviewernpx skills add mem0ai/mem0 --skill memory-reviewergit clone --depth 1 https://github.com/mem0ai/mem0Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mem0ai/mem0/memory-reviewer)<a href="https://agentmods.dev/skills/mem0ai/mem0/memory-reviewer"><img src="https://agentmods.dev/badge/skills/mem0ai/mem0/memory-reviewer.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00040 | $0.00613 |
| Opus 5 | $0.00020 | $0.00307 |
| Sonnet 5 | $0.00008 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00061 |
Grade A, and why
memory-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Reviewer
Audits memory quality for the active project. Finds duplicates, contradictions, and low-confidence entries.
When to use
- User asks "check my memories", "memory quality", "any duplicates?"
- User runs
/mem0:memory-reviewerdirectly - After a session with 5+ memory writes (suggest proactively)
- After
/mem0:health --deepidentifies issues
Steps
-
Fetch all memories for active project via
get_memorieswithfilters={"AND": [{"user_id": "<active_user_id>"}, {"app_id": "<active_project_id>"}]},page_size=200. Paginate if needed — cap at 200 memories. -
Group by
metadata.type. Common types:decision,convention,anti_pattern,task_learning,project_profile,user_preference,session_state. -
Scan each group for issues:
Issue Detection method Near-duplicates >60% noun overlap within same type. Compare memory text after stripping stop words. Contradictions Opposing facts about same topic (e.g., "use PostgreSQL" vs "use MySQL" for same component) Low-confidence metadata.confidence < 0.3Missing type No metadata.typesetStale created_atolder than 180 days with no updates -
Output compact summary:
memory-reviewer: project=<id> total=<N>
duplicates: <N> found
contradictions: <N> found
low_confidence: <N> found
untagged: <N> found
stale: <N> found
- If issues found, list them with memory IDs:
Issues:
[duplicate] "<memory_a>" ≈ "<memory_b>" [mem0:<id_a>, mem0:<id_b>]
[contradiction] "<memory_x>" vs "<memory_y>" [mem0:<id_x>, mem0:<id_y>]
[low_conf] "<memory_z>" (confidence: 0.1) [mem0:<id_z>]
- Suggest action: "Run
/mem0:dreamto consolidate duplicates and resolve contradictions."
Constraints
- Read-only — never modify or delete memories (that's
/mem0:dream's job) - Max 200 memories per scan
- Report findings, let user decide on action
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 60 lines · 40 tokens per session scan A 0353048bdf8a
memory-reviewer is a skill published in the GitHub repository mem0ai/mem0 (64,748 stars, last pushed yesterday), licensed Apache-2.0. It adds 40 tokens to every session and 613 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pinecone-research
Agent RAG and long-term memory with Pinecone.
langchain-orchestration
Comprehensive guide for building production-grade LLM applications using LangChain's chains, agents, memory systems, RAG patterns, and advanced orchestration.
honcho
Configure and troubleshoot Honcho memory for Hermes.
qdrant
Vector search engine for production RAG systems.
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
accelerate
Run PyTorch training across GPUs with minimal changes.