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/jnpiyush/agentx/agent-memory-systemsnpx skills add jnPiyush/AgentX --skill agent-memory-systemsgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/agent-memory-systems)<a href="https://agentmods.dev/skills/jnpiyush/agentx/agent-memory-systems"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/agent-memory-systems.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 | $0.00072 | $0.01257 |
| Opus 5 | $0.00036 | $0.00629 |
| Sonnet 5 | $0.00014 | $0.00251 |
| Haiku 4.5 | $0.00007 | $0.00126 |
Grade A, and why
agent-memory-systems 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 4d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
Architecture Pattern
[User turn]
|
v
[Retrieve relevant memory] (semantic + filters: user_id, type, recency)
|
v
[Compose prompt: system + retrieved memories + working state + turn]
|
v
[Model + tools]
|
v
[Memory writer]
- Extract candidate memories from turn
- Score importance
- Dedupe / merge with existing
- Persist with type + ttl + privacy tags
Frameworks
| Framework | Strength |
|---|---|
| mem0 | Lightweight, multi-store, easy to drop into existing apps |
| Zep | Knowledge graph + temporal facts, strong search |
| Letta / MemGPT | OS-style memory hierarchy (core / archival), self-managed |
| LangMem (LangChain) | Tight LangGraph integration, long-term store + semantic memory |
| OpenAI Memory | Built-in for ChatGPT-style products; opaque |
| Build-your-own | pgvector + tables + writer agent; max control |
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.
- 4d ago First seen · 159 lines · 72 tokens per session scan A 7fc3c6cc052b
agent-memory-systems is a skill published in the GitHub repository jnPiyush/AgentX (15 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 1,257 once invoked, about $0.0004 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
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
auditing-subgroup-fairness
Audit an OpenMed NER or de-identification model for performance disparities across demographic subgroups (sex, age band, race/ethnicity when available) using openmed.eval.fairnessreport. Use when the user wants per-subgroup recall and leakage, wants to check whether de-identification under-protects a group, wants to…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…