
Memory for Claude Code and coding agents: MCP, hooks and limits
How to give Claude Code persistent memory with MCP and hooks: step-by-step setup, what is sent to MemoryFirst, what each session recalls and the limits.

Notes on building MemoryFirst, the AI-native memory layer for businesses. Engineering, product, and the occasional founder rant.
20 articles

How to give Claude Code persistent memory with MCP and hooks: step-by-step setup, what is sent to MemoryFirst, what each session recalls and the limits.

Glean is an enterprise AI platform with 275+ connectors and contract-only pricing; MemoryFirst is cited memory over MCP for your agents. Facts as of 2026-11-14.

Letta is an open-source runtime for building stateful agents; MemoryFirst is cited memory for the agents you already use. Pricing and facts as of 2026-11-14.

An honest comparison of Mem0 and MemoryFirst: plans, verified pricing, MCP, graph, data residency and when each one fits. Data checked on 2026-11-14.

An honest Zep and Graphiti vs MemoryFirst comparison: verified pricing and credits, MCP, temporal graph, compliance and when each fits. Data of 2026-11-14.

Simulated scenario: a day for a founder juggling 11 projects if she and her agents shared one memory with citations. Before, after and limits.

Agent memory layers, assistant memory, enterprise search and DIY frameworks: public pricing checked on 2026-11-14 and which option fits which kind of team.

A simulated scenario: six people on Claude Code and Cursor, architecture decisions that get lost, and a shared memory over MCP, with illustrative numbers.

A simulated scenario: an agency with 12 clients, promises scattered across emails and calls, and what client separation MemoryFirst offers and what it does not.

A company brain is the memory your AI agents query, with citations you can verify. What it is, which sources it ingests today, who it suits and what it is not.

The short story of MemoryFirst: the problem we saw, why we built a memory layer with verifiable citations, and why we decided to build it ourselves, in Spain.

What it costs when an AI agent starts each session with no past: minutes, tokens and reopened decisions, with an illustrative sum and the market options.

Why what your company knows is split across chats, calls, documents and repos, what searching costs, and what it takes to bring it together with citations.

A good answer starts with good retrieval. Here's how we combine semantic, lexical and graph search, fuse them with RRF and rerank with a cross-encoder, and why each piece matters.

Mem0, Supermemory, Zep, MemoryFirst. They all promise 'memory for AI'. The differences that actually matter: where your data lives, whether you can audit answers, and which model reads your text.

An AI that asserts things it can't prove is a liability, not a feature. Here's how a memory layer with citations, retraction and EU data turns trust into something verifiable.

A memory layer is only useful if your tools can read it. That's why MemoryFirst offers two routes you already use: MCP and a plain JSON REST API. No proprietary SDK.

Karpathy framed LLMs as a new operating system: the model is the CPU, context is the RAM. But no serious computer ships without a disk. Persistent memory is the missing layer.

For many teams the question isn't only where data is stored, but who reads it when an answer is written. Here is what MemoryFirst does today, and what it doesn't yet.

Why we're building the memory layer for AI-native businesses, why now, and what's coming next.