Open Memory Specification (OMS), Context Assembly Language (Cal)

Open Memory Specification (OMS) is an open standard for immutable, content-addressed agent memory, defining the .mg container format. It provides AI agents with portable and verifiable memory for reasoning and collaboration.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is Open Memory Specification (OMS), Context Assembly Language (Cal)?

The Open Memory Specification (OMS) is an open standard designed to provide AI agents with immutable, portable, and verifiable memory. It defines the .mg container format, which stores content-addressed, cryptographically signed knowledge units called 'memory grains'. Alongside OMS, the Context Assembly Language (CAL) offers a declarative query language for non-destructive context assembly from grain stores, while the Semantic Markup Language (SML) provides a flat, tag-based output format optimized for LLM context consumption. This family of specifications enables AI agents to remember, reason, and collaborate across diverse systems, ensuring data integrity, portability, and auditability for enterprise-grade trust and compliance.

Best used for

Ideal for developers and startup founders who need to implement robust, verifiable memory for AI agents, assemble deterministic context for LLMs, and ensure compliance with data regulations. Especially valuable for building interoperable AI systems that require auditability and data portability across different platforms.

Common actions

define memory standard

manage agent memory

query agent context

ensure data integrity

enable AI collaboration

Capabilities

Key features

Content-addressed memory grains
Cryptographic signing (COSE Sign1)
Declarative query language (CAL)
Tag-based output format (SML)
GDPR/HIPAA compliance
Portable .mg container format

Target Audience

developerstartup founderproduct manager

Integrations

Not yet documented

Pricing & Plans

Open Source

FAQs

What is the Open Memory Specification (OMS)?

OMS is an open standard that defines the .mg container format for immutable, content-addressed memory grains. These grains are cryptographically signed, providing AI agents with verifiable and portable memory. It's designed to enable AI systems to remember, reason, and collaborate across different environments securely.

How do CAL and SML complement OMS?

CAL (Context Assembly Language) is a query language that allows AI agents to deterministically assemble context from OMS grain stores without altering the original data. SML (Semantic Markup Language) is an output format optimized for LLM context windows, using tags to provide epistemic signals about the type of information, enhancing LLM understanding.

What compliance benefits does OMS offer?

OMS is built with enterprise trust in mind, incorporating features like COSE Sign1 signatures, DID-scoped consent, and jurisdiction-aware retention. This design supports compliance with regulations such as GDPR, HIPAA, and SOX from its inception, making it suitable for sensitive data handling in autonomous systems.

Trending

Subcategories trending in Productivity & Business

Workflow Automation Strategy & Planning HR & Recruiting Document Management Legal & Compliance Team Collaboration

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce