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.
npx agentmods add skills/m-t-d-n/agentmemory-codex-windows/agentmemory-architecturenpx skills add M-T-D-N/agentmemory-codex-windows --skill agentmemory-architecturegit clone --depth 1 https://github.com/M-T-D-N/agentmemory-codex-windowsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/m-t-d-n/agentmemory-codex-windows/agentmemory-architecture)<a href="https://agentmods.dev/skills/m-t-d-n/agentmemory-codex-windows/agentmemory-architecture"><img src="https://agentmods.dev/badge/skills/m-t-d-n/agentmemory-codex-windows/agentmemory-architecture.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.00412 |
| Opus 5 | $0.00030 | $0.00206 |
| Sonnet 5 | $0.00012 | $0.00082 |
| Haiku 4.5 | $0.00006 | $0.00041 |
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 5d 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.
This is a copy
100% identical to agentmemory-architecture — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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.
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.
- 5d ago First seen · 34 lines · 59 tokens per session scan A e0ef13c123a6
agentmemory-architecture is a skill published in the GitHub repository M-T-D-N/agentmemory-codex-windows (2 stars, last pushed 5d 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. It is 100% identical to agentmemory-architecture, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
engraphis-memory
Give the agent durable, scoped, explainable memory across sessions and repositories through the Engraphis MCP tools. Use when you learn a convention, decision, bug cause/fix, or user preference worth keeping; when prior context would help before you answer or act (to avoid re-asking or re-deriving); when asked "why is…
slm-recall
Search and retrieve facts, decisions, and past context from SuperLocalMemory. Use when the user asks to recall, find, search, or "what did we decide/say about X". Triggers multi-channel semantic retrieval with reranking; always call before storing anything new.
slm-remember
Capture durable facts, decisions, constraints, and gotchas into SuperLocalMemory. Use when the user says "remember that", "save this decision", "note this constraint", or when a session produces a conclusion worth persisting across sessions. Always recall first to avoid duplicates.
slm-session
Manage SuperLocalMemory session lifecycle — call sessioninit once at the start of every fresh session to load relevant project context and get a sessionid; call closesession when work is meaningfully complete to commit temporal summaries. Correct lifecycle hygiene is what makes SLM's learning loop work.
slm-compress
Compress large text, tool output, or transcripts to reduce context-window usage while keeping the full 1M window intact — call slmcompress(content, mode, reversible, ttlseconds) to shrink content; if the result is lossy a ccrid is returned so you can call slmretrieve(ccrid) later to recover the exact original; always…
slm-scope
Controls memory visibility across profiles — personal (private, default), shared (selected profiles), or global (all profiles on this machine). Default is always personal. Only change scope when the user explicitly asks to share a memory across workspaces. Works with both remember (write scope) and recall (read scope…