agent-memory-architecture skillA
agent-memory-architecture is agent-read markdown (skill) from akillness/jeo-skills: Design tiered agent memory — core / recall / archival — with backend selection (mem0, Letta, Zep/Graphiti, LangMem) and temporal vs snapshot tradeoffs. Use when an agent needs persistent context across sessions, personalization, or temporal knowledge graphs..
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Agent Memory Architecture ## Overview Conversation history ≠ memory. Production agents need tiered stores: hot in-context, warm vector recall, cold archival, plus temporal knowledge graphs for facts that change over time. This skill picks the backend and tier layout. ## When to use - Agent needs to remember user preferences across sessions - Multi-session task continuity (Ralph, long-running research) - Personalization that survives restarts - Multi-tenant agents with strict isolation - Facts change over time (price, status, relationships) → temporal KG needed ## Backend selection | Backend | Strength | Pick when | |---------|----------|-----------| | **mem0** | Self-improving, fact extraction, OSS | Personalization, conversational memory | | **Letta** (MemGPT) | OS-style tiered memory, persistence | Agent-as-process, long-lived agents | | **Zep / Graphiti** | Temporal knowledge graph, bi-temporal | Facts change over time, need history | | **LangMem** | LangGraph-native, simple | Already on LangGraph, no extra service | | **Postgres + pgvector** | Roll your own, full control | Compliance / on-prem requirements | ## Tier design ``` …
Read the whole file at its exact version.
How to install
mdr add akillness/jeo-skills/agent-memory-architecture@git:20260919.9f2a908mdr add akillness/jeo-skills/agent-memory-architecture@sha256:768857916195e832Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_sisrbqbl3i6n5qn2)
0 badge views in 30 days
Versions
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3797 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
akillness/jeo-skills · 47 stars · license none · pushed 2026-09-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_sisrbqbl3i6n5qn2 GET https://markdownregistry.com/api/v1/resolve?ref=akillness/jeo-skills/agent-memory-architecture GET https://markdownregistry.com/api/v1/blob/768857916195e83251631e2eedba5b9bf162e88db8467d0c36d5ee111cc2aeb0
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.