agentmemory-architecture

A technical guide to agentmemory, a local server that records coding-agent work and makes it searchable. It describes how data is stored, indexed, connected to concepts, and served through REST and MCP interfaces.

In plain words
What is it for?
Understanding agentmemory's storage model, search methods, lifecycle, internal engine, service ports, and local viewer.
Why use it?
It explains how information moves from capture to retrieval and what local services are involved. This helps developers extend the system or diagnose how memory searches work.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/rohitg00/agentmemory/agentmemory-architecture
Any agent
npx skills add rohitg00/agentmemory --skill agentmemory-architecture
Clone the repo
git clone --depth 1 https://github.com/rohitg00/agentmemory

Made for: Claude Code, Codex.

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00059 $0.00412
Opus 5 $0.00030 $0.00206
Sonnet 5 $0.00012 $0.00082
Haiku 4.5 $0.00006 $0.00041

Measured 3d ago against content hash e0ef13c123a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentmemory-architecture scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

plugin/skills/agentmemory-architecture/SKILL.md · 34 lines

What it actually says

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. It is built on the iii engine.

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.

Retrieval model

Recall is hybrid: BM25 keyword search plus vector similarity plus graph expansion over linked concepts. The default install needs no API key because embeddings run on-device and BM25 needs none. An LLM provider only adds richer summaries and auto-injection, both opt-in.

Storage and lifecycle

Memories carry content, concepts, files, importance, and timestamps, grouped into sessions and optionally linked to commits. A lifecycle of capture, compress, consolidate, and forget keeps the store useful over time rather than letting it grow unbounded.

Ports

REST is the anchor at 3111. Streams = N+1 (3112), viewer = N+2 (3113), engine = N+46023 (49134). --instance N shifts the whole block by N*100.

Viewer

A real-time web viewer at http://localhost:3113 shows memory building as sessions run. Useful for demos and for confirming capture is working.

See also

  • agentmemory-mcp-tools and agentmemory-rest-api for the surfaces.
  • agentmemory-hooks for automatic capture.
  • agentmemory-config for ports and feature flags.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 34 lines · 59 tokens per session scan A e0ef13c123a6

Subscribe to this mod's changes

agentmemory-architecture is a skill published in the GitHub repository rohitg00/agentmemory (27,906 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 412 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

impeccable

Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…

Fast-Editor/Lynkr · 189 tokens

circuit

Operate Circuit, the flow engine that runs coding work as structured, evidence-backed flows (Fix, Build, Explore, Review, Prototype). Use this skill at the START of any substantive coding task in a project where Circuit is installed: fixing a bug, building a feature, refactoring, reviewing a diff or PR, investigating…

petekp/claude-code-setup · 137 tokens

latent-potential

First-principles, team-of-experts assessment of a software project that surfaces latent potential; underexploited assets, a sharper north star, missing high-leverage capabilities, better framing and messaging. Produces a prioritized, evidence-grounded report with cheap probes, a reframe candidate, a stop-doing list…

petekp/claude-code-setup · 191 tokens

claude-code-audit

Forensic audit of the user's recent Claude Code sessions to surface step-change workflow improvements — not marginal ones. Use when the user asks to "audit my Claude Code sessions", "analyze how I use Claude Code", "find patterns in my usage", "improve my Claude Code workflow", "review my sessions", "find leverage in…

petekp/claude-code-setup · 174 tokens

deep-research

Conduct exhaustive, citation-rich research on any topic using all available tools: web search, browser automation, documentation APIs, and codebase exploration. Use when asked to "research X", "find out about Y", "investigate Z", "deep dive into...", "what's the current state of...", "compare options for..."…

petekp/claude-code-setup · 119 tokens

literate-guide

Create a narrative guide to a codebase or feature in the style of Knuth's Literate Programming — code and prose interwoven as a single essay, ordered for human understanding rather than compiler needs. Use when the user asks to 'explain this codebase as a story', 'write a literate guide', 'create a narrative…

petekp/claude-code-setup · 145 tokens