agent-memory-systems SKILL.md skillA
agent-memory-systems from jnpiyush/agentx is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add jnpiyush/agentx/agent-memory-systems@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- jnpiyush/agentx
- Path
.github/skills/ai-systems/agent-memory-systems/SKILL.md- Versions recorded
- 2
- Latest version
- v1.0.0, committed Sep 15, 2026
- First version recorded
- Apr 30, 2026
- Size
- 5,320 bytes
- Repository stars
- 18
- License
- Apache-2.0
Design agent memory beyond a single context window: short-term (working / scratchpad), long-term (episodic, semantic, procedural), and shared / cross-session memory. Covers mem0, Zep, Letta / MemGPT, LangMem, OpenAI Memory, retrieval and consolidation policies, PII handling, and eviction.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Agent Memory Systems > **Purpose**: Give agents the right amount of memory at the right time. Avoid both amnesia and creepy total recall. --- ## When to Use This Skill - Multi-turn assistants where users expect continuity across sessions - Personalization (preferences, history, profile) - Long-running tasks that exceed a single context window - Multi-agent systems sharing state - Compliance scenarios that require auditable forgetfulness --- ## Memory Types | Type | Purpose | Example | Lifetime | |------|---------|---------|----------| | **Working** (scratchpad) | Within-task reasoning state | Plan, intermediate results | Single task | | **Episodic** | Specific past interactions | "Last Tuesday user asked about X" | Sessions to months | | **Semantic** | Distilled facts and preferences | "User prefers metric units" | Long-term | | **Procedural** | How-to / skills the agent learned | Tool macros, recovery patterns | Long-term | | **Shared** | State across agents / users | Team knowledge base | Long-term | Distinct from RAG corpora: memory is **about the user / agent / task**; RAG is **about external knowledge**. Same vector store can serve both with namespaces. --- …
Read the whole file at its exact version.
How to install
mdr add jnpiyush/agentx/agent-memory-systems@sha256:66a71901d83c9db7The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ebxs5fl4vc36p7sb)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Apr 30, 2026 and Sep 15, 2026, about one every 137 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v1.0.0 latest | 2026-09-15 | f17c505 | 5,320 B | A | view · diff |
| v1.0.0 | 2026-04-30 | 4f38ce8 | 5,318 B | A | view |
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 (5320 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
jnpiyush/agentx · 18 stars · license Apache-2.0 · pushed 2026-11-01 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_ebxs5fl4vc36p7sb GET https://markdownregistry.com/api/v1/resolve?ref=jnpiyush/agentx/agent-memory-systems GET https://markdownregistry.com/api/v1/blob/66a71901d83c9db70daa99a01255e999dbd2c82f870eba1ac0024269b9dcd113
Your AI assistant 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.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.