---
title: "LOAM — Linked Open Agent Memory"
description: "LOAM (Linked Open Agent Memory) is a queryable, RDF-based memory layer for AI agents: session history, entities, tasks, execution traces, and preferences kept as Linked Data, so knowledge accumulates across sessions."
url: urn:osdi:this
dateModified: 2026-10-31T16:00:49Z
language: en
---
Persistent Memory · RDF · Linked Data · Part of VOICE

# LOAM

Memory that *accumulates,* instead of disappearing between sessions.

A queryable, RDF-based memory layer for AI agents: session history, entities, tasks, execution traces, and preferences, kept as Linked Data.

LOAM (Linked Open Agent Memory) is a queryable behavioral contract for AI agents, encoded in RDF-Turtle. It defines how an agent retrieves and applies standing instructions, with RDF memory files serving as the authoritative source — so prior interactions become reusable, machine-computable context that any agent or LLM can pick up.

[Get it on GitHub](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory) [How it fits VOICE](urn:osdi:sitevoice/)

What the animation shows  **LOAM keeps memory as a collection of linked graphs.** Not a transcript: facts about the work, kept as Linked Data. **Each kind of memory lands in its own graph.** Session, entity, task, trace, domain and preference graphs. **Every fact is RDF with a hyperlink identifier.** That lets the graphs link to each other and to other data. **Context Storage: plain Turtle files.** Read, versioned and diffed like any other source. **Queried with SPARQL, joined to enterprise data.** An agent that never saw the conversation can reuse it. **A memory any agent can pick up.** Linked, queryable and reusable across sessions.  [Open the full-size animation](http://localhost:8890/skin-openlink-2026/img/native/loam-what-it-keeps.svg)

What it keeps

## An entity relationship graph collective

The memory is a collection of linked graphs rather than a transcript. Because each fact is RDF with a hyperlink identifier, it can be queried with SPARQL, joined to enterprise data, and reused by an agent that never saw the original conversation.

loam-memory-animation:start

loam-memory-animation:end

01 — Session Graph

Conversations, plans, goals

What was asked, what was planned, and what the user was trying to achieve.

02 — Entity Graph

People, organizations, products, assets

The things the work is about, each with a stable hyperlink identifier.

03 — Task Graph

Actions, tools, workflows

What was done, with which tools, in which order.

04 — Trace Graph

Execution traces, provenance

Where each result came from, for auditing, debugging, and reproducing it.

05 — Domain Graphs

Subject-specific knowledge

For example contracts and compliance: knowledge that belongs to one field of work.

06 — Preference Graph

User and agent preferences

Standing instructions an agent applies without being reminded.

Further domain-specific graphs can be added for any field of work.

How an agent uses it

## Load, select, apply, record

01 — Load

Read the memory first

Before acting on a task, the agent lists the memory folders and reads `core.ttl`, `preferences.ttl`, the optional local-only private overlay, `ontology.ttl`, and `index.ttl`.

02 — Select

Pick the relevant context

The agent classifies the prompt’s intent and, when a SPARQL endpoint is configured, uses it to select the preferences, how-to documents, and recent sessions that apply.

03 — Apply

Follow the rule that applies

Where a rule points to a how-to document, the agent reads that document before acting, so the detail comes from memory rather than from recollection.

04 — Record

Write back what was learned

After a meaningful task, the agent writes valid RDF-Turtle to the memory: a session record, new entities, and any rule the user stated. Knowledge accumulates between sessions.

What lives where

## A folder of Turtle files

The memory is plain files, so it can be read, versioned, and diffed like any other source. Each name below opens the file or folder in the repository. The files can also be loaded into [Virtuoso](urn:osdi:sitevirtuoso/) and queried over SPARQL.

| Memory file or folder | Holds |
| --- | --- |
| [`core.ttl`](https://github.com/OpenLinkSoftware/ai-agent-skills/blob/main/agent-rdf-memory/core.ttl) | User identity, agent identity template, and output-routing requirements |
| [`preferences.ttl`](https://github.com/OpenLinkSoftware/ai-agent-skills/blob/main/agent-rdf-memory/preferences.ttl) | The public-safe hub: standing instructions as HowTo steps, grouped by topic |
| `preferences.private.ttl` | An optional local-only overlay whose assertions override the public defaults. It is never published; start from [preferences.private.example.ttl](https://github.com/OpenLinkSoftware/ai-agent-skills/blob/main/agent-rdf-memory/preferences.private.example.ttl) |
| [`ontology.ttl`](https://github.com/OpenLinkSoftware/ai-agent-skills/blob/main/agent-rdf-memory/ontology.ttl) | Vocabulary: prompt intents, retrieval policies, and context-routing rules |
| [`index.ttl`](https://github.com/OpenLinkSoftware/ai-agent-skills/blob/main/agent-rdf-memory/index.ttl) | A session index: one entry per session |
| [`howto/`](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory/howto) | Companion specifications, one per sub-HowTo, linked from preferences.ttl |
| [`sessions/`](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory/sessions) | Episodic memory: one Turtle file per day, model, and agent environment |
| [`entities/`](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory/entities) | The people, organizations, tools, and concepts the work mentions |
| [`scripts/`](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory/scripts) | Validation and utility tools, including the memory-protocol and session-record gates |

### Documentation and tools

| File | Holds |
| --- | --- |
| [`README.md`](https://github.com/OpenLinkSoftware/ai-agent-skills/blob/main/agent-rdf-memory/README.md) | Folder structure, the retrieval protocol, and the sub-HowTo map |
| [`AGENTS.md`](https://github.com/OpenLinkSoftware/ai-agent-skills/blob/main/agent-rdf-memory/AGENTS.md) | The retrieval sequence an agent runs before it acts, step by step |
| [`SESSION-START-HOOK.md`](https://github.com/OpenLinkSoftware/ai-agent-skills/blob/main/agent-rdf-memory/SESSION-START-HOOK.md) | How the memory is loaded automatically when a session starts |
| [`load_memory.py`](https://github.com/OpenLinkSoftware/ai-agent-skills/blob/main/agent-rdf-memory/load_memory.py) | The loader: prefers SPARQL context selection and falls back to reading the files |

In VOICE

## The Recall and Enrich steps

[VOICE](urn:osdi:sitevoice/) pairs [Virtuoso](urn:osdi:sitevirtuoso/)’s federated access with [OPAL](urn:osdi:siteopal/)’s orchestration. LOAM is what lets the next agent session start from what the last one learned: it supplies the Recall step, preserving findings, relationships, and provenance, and the Enrich step, folding new results back into persistent context.

- **Portable.** The context is not tied to one LLM’s conversation history, so models and agent frameworks can change without losing it.
- **Auditable.** Execution traces and provenance are recorded as data, not buried in chat logs.
- **Governed.** Public rules and a local-only private overlay are kept apart, so what is shared is a deliberate choice.

Get it

## Start from the repository

[RepositoryLOAM on GitHub](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory) [ContextVOICE — the whole architecture](urn:osdi:sitevoice/) [OrchestrationOPAL — the harness](urn:osdi:siteopal/)

## Knowledge that compounds

Give every agent session the context the last one earned.

[Get it on GitHub](https://github.com/OpenLinkSoftware/ai-agent-skills/tree/main/agent-rdf-memory) [Talk to an Architect](urn:osdi:sitecontact/?dept=Solutions%20Architect)
