Skip to content

Blog

Field notes on coordination memory

Category definitions, honest benchmarks, and build logs — written in the open.

Concepts Jul 11, 2026·6 min read

Agent memory: episodic, semantic, and coordination

“Agent memory” is one phrase doing three jobs. The split cognitive science drew — episodic and semantic — plus the type multi-agent systems actually need: coordination memory.

Read the article
Engineering Jul 11, 2026·6 min read

Per-agent access control for AI agents, compiled to SQL

When agents share memory, “who can read what” becomes a security boundary. Prompt-level rules are advisory; a policy compiled to a SQL predicate is enforced in the query plan.

Read the article
Engineering Jul 11, 2026·7 min read

Deterministic context packs and how prompt caching compounds

Multi-agent token bills balloon because every agent re-sends history. The underused lever is determinism: identical inputs → identical bytes → prompt-cache hits that compound across the fleet.

Read the article
Engineering Jul 11, 2026·6 min read

Claude Agent SDK: giving your agents shared memory

The Claude Agent SDK builds one capable agent fast — but its agents don’t share what they learn across runs and subagents. Point them at Lore’s MCP server and the whole fleet works from one reality.

Read the article
Engineering Jul 11, 2026·7 min read

Context engineering for multi-agent systems

Context engineering is the craft of deciding what goes in the window. For one agent it’s curation; for a team of agents it becomes a distributed-systems problem — and the tactics that work solo quietly break.

Read the article
Concepts Jul 11, 2026·6 min read

AI agents forget context — the fix isn’t a bigger model

It looks like forgetting, so teams reach for a bigger context window or a smarter model. But a multi-agent system that loses context has a coordination problem, not a capacity one — and scale doesn’t fix it.

Read the article
Research Jul 10, 2026·7 min read

Why multi-agent systems fail — reading the MAST taxonomy

A 1,600-trace study found most multi-agent failures aren’t reasoning errors — they’re coordination errors. The taxonomy, and what it says your stack is missing.

Read the article
Concepts Jul 9, 2026·8 min read

Multi-agent memory: why your agents live in parallel universes

Everyone says “agent memory,” but they don’t mean the same thing. A field guide to coordination memory — the category your multi-agent system is missing.

Read the article
Concepts Jul 8, 2026·6 min read

Read-your-writes for agents, explained

The oldest trick in distributed databases, applied to agent handoffs — the one consistency guarantee that makes them stop failing by luck.

Read the article
Comparisons Jul 6, 2026·8 min read

The agent-memory landscape in 2026: Mem0, Zep, and the gap

Three products say “agent memory” and solve three different problems. An honest map of Mem0, Zep, and the coordination axis they leave open.

Read the article
Research Jul 5, 2026·6 min read

AI agent memory benchmarks in 2026: the same-judge rule

One vendor reports 94.8; an independent run measures the same tool at 49.0. Why the numbers are nearly meaningless out of context — and the rule that fixes them.

Read the article
Engineering Jul 4, 2026·6 min read

Memory poisoning in AI agents — and how quarantine stops it

Shared memory is a shared attack surface. How trust tiers, quarantine, and access control keep a poisoned write out of every agent’s prompt — by construction.

Read the article
Concepts Jul 3, 2026·5 min read

What is coordination memory? A working definition

“Agent memory” is one phrase doing three jobs. A precise definition of the third one — coordination memory — and how it differs from just sharing a store.

Read the article
Engineering Jul 2, 2026·9 min read

Agent memory on Postgres: how we built the write path

A write path that never blocks on an LLM, guarantees read-your-writes with a sequence number, and resolves conflicts with a database constraint — all on Postgres.

Read the article

In the pipeline

  • What is agent memory? A 2026 field guide
  • Multi-agent state management without a message bus
  • Agent handoffs that don’t lose context

Everything falls into one shared reality.

Lore

Join the waitlist

Early access + design-partner slots. No spam — just the first ping when it opens.