Overview Research Convenings Prototypes Writings Talks People
Newsletter

Persistent memory is becoming a core layer of agent infrastructure faster than shared exchange semantics are emerging

Agent memory is persistent context that affects future model or agent behavior: user-provided facts, model- or agent-derived summaries, project instructions, prior decisions and actions, tool outputs, and references to underlying transcripts or artifacts. It is scoped to a user, project, organization, or shared group, and is distinct from a raw chat export. A memory system selects, transforms, organizes, retrieves, and expires information for future use.

Every major coding-agent harness (Claude Code, Codex, goose, OpenClaw, Letta Code) implements memory, but each uses a different convention. A developer cannot move a stateful agent from one harness to another. An enterprise cannot switch memory providers without re-ingesting derived memory objects. Open-source memory projects duplicate one another because there is no shared object model, provenance format, or exchange protocol to converge on.

Fragmented memory has real engineering and security costs. Developers write bespoke adapters. Users and enterprises cannot reliably move accumulated context. Provenance is often lost when memory is copied. Permissions that were meaningful in one system may not survive export, and security review is harder when each integration defines its own exchange behavior. A common open layer addresses these costs without dictating how each agent internally reasons, summarizes, indexes, or retrieves information.

The Open Memory Protocol (OMP) closes this gap. The Open Memory Protocol Initiative (OMPI) is the working group hosted at the AI Disclosures Project that develops, maintains, and grows the ecosystem around it.

The smallest interoperable layer over existing memory primitives

Backends, ownership, and internal architecture stay with implementers

What a portable OMP record contains

The working object model is developed openly and tested against real implementations. The expected minimum fields are design hypotheses, not fixed requirements at the start of the project.

Element Purpose
Identity and version Stable record identifier and schema/protocol version, for migration and de-duplication.
Scope / namespace User, project, organization, or shared-group scope; separates memory that may be portable from memory that must remain local.
Type and payload A small typed envelope plus implementation-extensible content, so systems can interoperate without forcing one internal memory taxonomy.
Source and provenance Originating system, underlying event/transcript/artifact reference where available, transformation history, and authorship/derivation metadata.
Lifecycle Creation and update times, retention or expiry information, and optional decay/recency semantics.
Permissions and consent Who or what may read, export, modify, or share a record; preserves access constraints during exchange.
Integrity metadata Hashes, signatures, or other integrity information supporting chain of custody and tamper detection.

Security enters the protocol at the object and exchange layers

Memory is security-sensitive because it persists information and can influence later agent actions. Security and privacy therefore enter the protocol design at the object and exchange layers, not as deployment-only concerns.

Risk Mitigation
Memory poisoning or malicious modification Provenance and integrity metadata; permissioned writes; immutable source links where possible; adversarial fixtures; review of high-impact write paths.
Unauthorized disclosure Explicit scope and permission fields; least-privilege export; redaction and filter hooks; secure defaults; no assumption that all memory is exportable.
Permission mismatch across systems Minimum interoperable permissions; fail closed when semantics cannot be preserved; record non-portable policy metadata alongside the payload.
Loss of provenance or chain of custody Source and derivation metadata; transformation history; stable identifiers; integrity checks; conformance tests for provenance across import/export cycles.
Software supply-chain risk Signed releases; dependency manifests and SBOMs; coordinated-disclosure process; continuous-integration security checks on the reference implementation.

What is available today

Draft specification

Agent Memory Specification, v0.1

Draft authored by Charles Packer (CEO, Letta) with feedback from the AI Disclosures Project team. Circulating in the working group in advance of the September 9 kickoff.

Read the draft
Reference implementation

Python package (pre-alpha)

A minimal Python implementation of the loader, validator, and harness contract. Runs against any spec-conformant memory directory.

View on GitHub
Governance

Working-group governance model

Steering committee, RFC process, licensing, and long-term stewardship plan (target: standards-body handoff after production adoption).

Read governance
Ecosystem scoping

State of agent memory (2026)

A survey of production and open-source memory systems (Letta, Mem0, Zep, Graphiti, AWS AgentCore Memory, Google OKF, and coding-agent harnesses) and where OMPI fits.

Read the survey

Formal in-kind partners and implementation collaborators

In-kind partner

Mozilla

Co-hosts working-group convenings and leads ecosystem recruitment across Mozilla's open-source and AI-developer network.

Raffi Krikorian (CTO) · Matt Harris
In-kind partner

IBM

Co-hosts convenings, contributes enterprise-adoption pathways, and advises on standards-body process.

Gabe Goodhart (Chief Architect) · Anna Lisa Gentile · Rynne Whitnah
Specification collaborator

Letta

Author of the draft OMPI specification. Contributes MemGPT / Letta memory-object model and the open-source Trajectory package.

Charles Packer (Co-founder and CEO)
Implementation collaborator

Block / goose

Open-source agent harness built on the Model Context Protocol. First-vertical implementation target for OMPI conformance.

goose maintainer team

From kickoff to IETF handoff

Sept 9, 2026
Kickoff technical convening (online). Co-hosted by AI Disclosures Project, Mozilla, and IBM. Working-group participants update the group on their memory work and identify areas for cross-stack coordination.
Oct 2026
In-person session at the O'Reilly open-source unconference (Berkeley). Reference-implementation v0.1 published and installable.
Year 1 (2026–27)
Two coding-agent harnesses shipping conformant memory export/import. First cloud-provider technical spike. Quarterly public adoption reports.
Year 2 (2027–28)
Written specification v1.0. Six coding-agent harnesses conformant. End-to-end benchmark passing across ten harness pairs. Preliminary IETF engagement (Birds-of-a-Feather session or working-group formation).
End of award
IETF Internet-Draft submitted. Long-term stewardship handed to standards-body home (target: Agentic AI Foundation).

Join the working group

If you build agent memory, maintain a coding-agent harness, run a memory-layer service, or work on standards for AI infrastructure, we want you in the working group.

Email OMPI GitHub