Agentmemory Architecture

This is the architectural reference for agentmemory, the memory server for coding agents. You'll want this when you need to understand how observations flow from capture through hybrid retrieval (BM25 plus vectors plus graph expansion) or when you're extending the system with new functions. It's built entirely on iii engine primitives, no separate plugin layer, so everything is a registered function or HTTP trigger. The documentation covers the storage model, port allocation scheme starting at 3111, and the real-time viewer at 3113. Most useful when you're debugging why a memory isn't surfacing or when you need to reason about the end-to-end path from a coding session to a recalled context chunk.

skills.sh installs: 11.3K
GitHub stars: 30.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add rohitg00/agentmemory --skill agentmemory-architecture --agent claude-code

Installs into .claude/skills of the current project.

Files

agentmemory is a memory server for coding agents. It runs locally, captures observations, indexes them for hybrid retrieval, and serves them back over REST and MCP. Worker Compose runs the pinned iii engine with AgentMemory and the registry state and http workers. The state worker uses a file-backed KV store by default, with Redis available by configuration; it is not SQLite.

iii primitives

Everything is a function, a trigger, or worker state on the iii engine. There is no separate plugin system; the worker registers functions (mem::*) and HTTP triggers (api::*) and the engine routes calls. agentmemory does not bypass iii; new capability is a new function plus a trigger.