v1.3 · Standards Track · OWF Final
The Open Memory Specificationfor Autonomous Systems A family of three specifications that give AI agents immutable, portable, and verifiable memory — so they can remember, reason, and collaborate across systems.
How it works
Three specs, one memory. OMS defines the container, CAL queries it, and SML renders it. Together they give any AI agent a complete, portable memory stack.
In Practice
Any AI agent. One memory. Portable everywhere. Imagine grains written by different AI systems — and read by others across industries, without any prior arrangement.
Slide 1 of 10: Belief grain by FitCoach
FitCoach
KineticAI
Learned from three months of workout data. Nutrition and scheduling agents use this grain to personalize recovery plans.
Belief · 0x01v1 · COSE Signed
{
"type" : "belief" ,
"subject" : "user:john-smith" ,
"relation" : "preferred_activity" ,
"object" : "morning_run_5k" ,
"confidence" : 0.94 ,
"source_type" : "pattern" ,
"created_at" : 1739980800000 ,
"namespace" : "fitness:preferences"
} CalendarBot
schedule optimization
FitCoach
training progression
Built for Enterprise
Trust at every layer. Immutable by Design Every grain is SHA-256 content-addressed. Once written, it cannot be altered — only superseded. Tamper evidence is built into the format.
Portable Everywhere A .mg file is a self-contained container. Store it in S3, stream it through Kafka, carry it on a drive, or push it to Git. No vendor lock-in.
Audit-Ready COSE Sign1 signatures, DID-scoped consent, and jurisdiction-aware retention. Built for GDPR, HIPAA, and SOX compliance from day one.
Conformance
Implement what you need Declare your conformance level. Start minimal, add layers as requirements grow.
Level 1
Minimal Reader Libraries, tools, verification scripts
Deserialize and verify grain blobs Compute & verify SHA-256 content addresses Field compaction (short keys ↔ full names) All ten grain types (0x01–0x0A) Ignore unknown fields Constant-time hash comparison Level 2
Full Implementation Agent frameworks, edge gateways
All Level 1 requirements Serialize (canonical MessagePack) Validate required fields per schema Pass all test vectors Multi-modal content references Store protocol (get/put/delete/list) Enforce invalidation_policy on supersession & contradiction Atomic supersede operation (distinct from raw put) Validate observer_type non-empty; emit oid/otype (v1.1) Level 3
Production Store Enterprise deployments, cloud platforms
All Level 2 requirements Persistent backend (filesystem, S3, DB) AES-256-GCM per-grain encryption HKDF per-user key derivation Blind-index tokens for encrypted search SPO/POS/OSP index (hexastore) or equivalent Full-text search (FTS5 or equivalent) Hash-chained audit trail Crash recovery and reconciliation Policy engine with compliance presets Partition Observation storage by observer domain (v1.1) cal agent-memory
CAL: The Query Language Your Agent Orchestrator Has Been Missing How the Context Assembly Language turns a raw memory store into a first-class context pipeline for AI agents — from querying relevant grains to assembling token-budgeted context blocks that drop directly into LLM calls.
2026-03-04 14 min read
cal sml
Choosing the Right Context Format: SML, TOON, Markdown, and JSON CAL's FORMAT clause gives you six output options for assembled agent context. Side-by-side token counts, real examples, and a decision guide for when to use SML, TOON, Markdown, or JSON.
2026-03-04 10 min read
sml context-format
SML: The Context Format That Tells LLMs What to Trust Semantic Markup Language (SML) uses grain type tag names as epistemic signals — telling an LLM not just what information is, but what kind of information it is. Hands-on examples across all 10 grain types, from customer support to incident response.
2026-03-04 12 min read
Implement OMS today. The specification is open and licensed under OWF Final. Read the spec, run the test vectors, and build interoperable agent memory in any language.
OMS v1.3 · .mg Container Definition · Standards Track · OWF Final