# Mm · Memory Layer — element 16 of 58

> Agents that remember Tuesday. Turns stateless calls into continuity.

- **Group:** 4 · Knowledge & Memory
- **Necessity:** Optional
- **Price band:** $ · under $30/mo
- **Maturity:** Experimental
- **Edition:** v2026.Q3 · verified 2026-09-13

## Leading tools (v2026.Q3)

- **Mem0** — the default memory api
- **Zep** — enterprise temporal graph memory
- **Letta** — memory-first agent harness
- **Supermemory** — fast cheap context cloud
- **Cognee** — open-source graph memory

## Our take

Nascent and worth watching. The first element where 'my agent knows my business' becomes literal.

## Combines with

Ag, Vd


## The top 5 — deep dossier (verified 2026-09-13)

Mem0, for most builders — the biggest ecosystem (61.7k GitHub stars, 90k+ developers, exclusive memory provider for AWS's Agent SDK), the cheapest real entry ($19/mo), and the fastest shipping cadence (background consolidation 'Dream' landed Aug 4, 2026). Zep wins when you're an enterprise that needs temporal knowledge graphs over business data with provenance, ABAC, and SOC 2/HIPAA. Letta wins when the self-improving agent IS the product, not a feature. Supermemory wins on ingestion volume per dollar and cross-tool personal memory; Cognee when you want to own the whole pipeline open-source. The looming threat is bundling: Claude and ChatGPT now remember natively, Anthropic's developer memory tool is GA, and AWS/Google/Redis sell memory as a metered primitive — a standalone layer must earn its keep across models and apps, or it's a feature.

1. **Mem0** (Mem0 (YC S24)) — Hobby free (10k adds/mo) · Starter $19/mo · Pro $249/mo · Enterprise custom (on-prem, SSO). Best for: Adding 'remembers the user' to an existing app in an afternoon — a hosted extraction-and-retrieval API that works with any model and framework. Why: The category's center of gravity: 61.7k GitHub stars, 90k+ registered developers, 13M+ package downloads, and API calls that grew 35M (Q1 2025) to 186M (Q3 2025). Raised $24M (seed + Series A led by Basis Set, Oct 2025) and became the exclusive memory provider for AWS's Agent SDK. Still shipping fast: Dream, its background memory-consolidation engine, launched Aug 4, 2026. Watch: Its 'SOTA' LoCoMo claims are disputed — Zep published a rebuttal showing a corrected implementation beat Mem0's setup, and Mem0's own paper had a full-context baseline outperforming it. Retrieval quotas bite: 1k retrievals/mo free and 5k on the $19 tier push retrieval-heavy apps to $249 quickly. [https://mem0.ai](https://mem0.ai)
2. **Zep** (Zep AI) — Free 10k credits/mo · Flex $1,250/yr · Flex Plus $3,750/yr · Emerging Cos $13k/first year (SOC 2, HIPAA BAA) · Enterprise custom. Best for: Enterprises whose agents must remember evolving business facts — temporal knowledge graphs over chat plus CRM/app data, with provenance tracking and access control. Why: The engineering-serious enterprise pick: temporal context graphs (open-sourced as Graphiti, 29k stars) with sub-200ms retrieval at 100M graphs, provenance lineage for synthesized facts (Jul 2026), attribute-based access control (Jul 2026), and SSO-gated memory over MCP (Jun 2026). Customers include Zscaler, Samsung, and HoneyBook; S&P Global called it a likely 'de facto partner in this layer of the enterprise agent stack.' Watch: No cheap paid tier — the jump from free to $1,250/yr excludes hobbyists, and the self-hosted Community Edition was deprecated (code moved to legacy/), so the real product is cloud-only. Its 94.7% LoCoMo / 90.2% LongMemEval numbers are vendor-run, like everyone else's. [https://www.getzep.com](https://www.getzep.com)
3. **Letta** (Letta (ex-MemGPT, UC Berkeley)) — Free · Pro $20/mo (20 stateful agents) · Developer $0.10/active agent/mo + $0.00015/sec tool exec · Enterprise custom. Best for: Building agents whose memory and self-improvement are the product — stateful agents that learn across sessions, from the researchers who invented the pattern. Why: The intellectual origin of the category: MemGPT (Oct 2023) invented LLM virtual context management, and Letta commercialized it with a $10M Felicis-led seed at $70M (Sep 2024). Its March 2026 pivot doubled down on what worked — Letta Code, a model-agnostic harness with git-backed memory files ('you own the memory, you choose the model'), plus research on sleep-time compute and continual learning that the rest of the field imitates. Watch: Strategic churn is real: the Mar 16, 2026 'next phase' deprecated large chunks of the platform (Filesystem, server-side templates, MCP integrations, sleep-time agents, tool rules), and the original server repo is now labeled legacy. Smallest disclosed war chest of the leaders. [https://www.letta.com](https://www.letta.com)
4. **Supermemory** (Supermemory) — Free (~$5 usage) · Pro $19/mo · Max $100/mo · Scale $399/mo · Enterprise custom (self-host). Best for: High-volume, cost-sensitive context: memory + RAG + connectors (Slack, Gmail, Drive, GitHub) in one API, plus a personal memory app that follows you across AI tools. Why: The fastest riser: 1.5B+ memories stored, sub-300ms recall claims, and a shipping pace that produced a POSIX-compatible semantic filesystem (SMFS, May 28, 2026 — claimed 55% cheaper agentic retrieval), Context Cloud (May 18, 2026), and default 'dynamic dreaming' consolidation (May 25, 2026) — all on a $3M pre-seed (Susa Ventures, Oct 6, 2025). Vendor cites internal deployments at Google and Nissan. Watch: Tiny funding versus rivals and a split focus (consumer app + infra API). Benchmark leadership claims (LongMemEval, LoCoMo, ConvoMem) and the Google/Nissan logos are vendor-sourced with no independent verification. [https://supermemory.ai](https://supermemory.ai)
5. **Cognee** (Topoteretes) — OSS free (Apache-2.0) · Cloud: Free 1M tokens · Standard $2.50/1M tokens + $5/workspace · Enterprise custom (BYO cloud). Best for: Teams who want to own the memory pipeline — an open-source ECL (extract-cognify-load) engine that builds combined knowledge-graph + vector memory over your own databases. Why: The credible open-source alternative to hosted memory APIs: 29.8k stars, 5M+ SDK runs monthly, v1 shipped, and real production proof (Bayer runs agentic research memory on it; Knowunity POC'd 40,000 students in 2 days). Deploys self-hosted, Docker, on-prem, or cloud, and plugs into Claude Code, Cursor, LangGraph, and MCP. Watch: The smallest commercial operation in the top 5 — funding undisclosed (Pebblebed and others, amounts unannounced) — and the ECL pipeline demands data-engineering appetite that Mem0's two-line SDK doesn't. [https://www.cognee.ai](https://www.cognee.ai)

### How to choose
- If You have a working app and just need it to remember users across sessions, this week → Mem0 — free for 10k memory-adds a month, $19 after, two-line SDK, works with any model. Watch the retrieval quota, not the add quota.
- If You're an enterprise whose agents must track facts that change over time — accounts, policies, patient state — with audit and access control → Zep. Temporal graph with provenance and ABAC is the point; budget $1,250/yr minimum, $13k if you need SOC 2 II + HIPAA BAA as a startup.
- If The agent itself is the product and it must demonstrably learn and improve over weeks → Letta — the MemGPT lineage, sleep-time compute, and git-backed memory you can inspect and version. Accept the platform-pivot risk.
- If You're ingesting everything — email, Slack, docs, screenshots — and cost per token retrieved decides the architecture → Supermemory: connector-heavy, sub-300ms claims, and SMFS cut agentic retrieval costs 55% by the vendor's own math. Verify their benchmarks against your data.
- If One assistant, one user, one vendor — 'my chatbot should remember me' → Don't buy a layer. Claude and ChatGPT memory do this natively, and Anthropic's client-side memory tool is GA for developers. A standalone memory layer only earns its keep across models, apps, or agents.

### The field (19 more)

Graphiti, OpenMemory, LangMem, Claude memory + memory tool, ChatGPT memory, AgentCore Memory, Memory Bank, Redis Agent Memory Server / Iris, MemU, Honcho, Memobase, MIRIX, Hyperspell, Memary (fading), Papr (fading), MemGPT (renamed), Zep Community Edition (dead), Motorhead (dead), Rayrift (dead)

Full dossier data: https://elems.ai/e/mm.json

---
Source: [elems.ai](https://elems.ai/e/mm.html) — the periodic table of the AI-led startup. Data: https://elems.ai/elements.json (CC BY 4.0, cite elems.ai).