TMX: The open standard AI agent memory has been waiting for

Truvem founder Dieng Amine has released TMX v0.1, an open standard JSON format for AI agent memory that enables portability across platforms, frameworks, and providers. The specification aims to solve the problem of proprietary memory formats locking in agent data, similar to how SMTP standardized email. The reference implementation, Truvem, is available on GitHub and supports export/import of agent memories.

The problem no one talks about: your agent's memories are prisoners. If you build an AI agent today using Mem0, your memories are locked in Mem0. Switch to Zep? You lose everything. Move to a new framework? Start from zero. This is exactly the problem email had in 1970. Every system had its own format. You couldn't send an email from one system to another. Then SMTP was invented. And email became universal. Today I'm publishing TMX v0.1 — the SMTP of AI agent memory. TMX Truvem Memory eXchange is an open, model-agnostic JSON format for storing, exporting, and importing AI agent memories across any platform, framework, or provider. It looks like this: { "tmx version": "0.1", "exported at": "2026-06-26T20:00:00Z", "source": "truvem", "agent id": "my-agent", "memories": { "id": "550e8400-e29b-41d4-a716-446655440000", "content": "User prefers dark mode and concise responses", "created at": "2026-06-01T08:30:00Z", "updated at": "2026-06-01T08:30:00Z", "expires at": null, "tags": "preference", "ui" , "source model": "gpt-4o", "metadata": {} } } That's it. Plain JSON. Human-readable. Portable. Right now, the AI agent ecosystem is exploding. Every week there's a new memory provider, a new framework, a new cloud service. But every one of them uses a proprietary format. This means: This is the biggest hidden tax in the agentic AI stack. TMX fixes it with a single open spec that anyone can implement — for free, with no approval needed. 1. Open — No license required. Implement TMX in any product, commercial or otherwise. 2. Model-agnostic — Works with GPT-4, Claude, Gemini, Mistral, Llama, or any future model. 3. Framework-agnostic — LangChain, CrewAI, Mastra, AutoGen — doesn't matter. 4. Human-readable — Plain JSON. No binary formats. Inspectable by any tool. 5. Minimal — The entire spec fits in one page. Complexity is optional. Truvem https://truvem.github.io/truvem is the reference implementation of TMX. You can start using it right now: Sign in with GitHub or Google at truvem.github.io/truvem/login.html https://truvem.github.io/truvem/login.html pip install truvem python from truvem import Truvem client = Truvem api key="your key" Write a memory client.remember agent id="my-agent", content="User prefers dark mode" Read memories — from any session, any model memories = client.recall "my-agent" print memories {"status": "ok", "memories": ... } curl -X GET https://truvem.onrender.com/v1/memory/export?agent id=my-agent \ -H "x-api-key: your key" You get back a valid .tmx.json file you can import anywhere. If you're building: You should implement TMX. Your users will thank you. The requirements to be TMX-compatible are simple: No fee. No approval. No committee. Just implement it. | Version | Features | |---|---| 0.1 today | Core format, basic fields, export/import | 0.2 | Migration scripts Mem0→TMX, Zep→TMX , CLI tool | 0.3 | Memory relationships, temporal invalidation | 1.0 | Stable standard, TMX Foundation, community governance | In 10 years, there will be more AI agents running than humans on Earth. Every one of them will need persistent memory. The question is: who controls that memory? If every provider keeps a proprietary format, agent memories become the new walled gardens — like email before SMTP, like the web before HTTP. TMX is a bet that open standards win. They always have. The full TMX v0.1 specification is published on GitHub: 👉 github.com/truvem/truvem/blob/main/TMX.md https://github.com/truvem/truvem/blob/main/TMX.md Try Truvem the reference implementation : What do you think? Is an open standard for agent memory something the ecosystem needs? I'd love feedback on the spec — open a GitHub issue or reply below. Built by Dieng Amine — solo founder, Abidjan, Côte d'Ivoire. Twitter: @gettruvem