agentmemory-architecture
This skill details the architecture of agentmemory, including its iii engine primitives, storage model, ports, and viewer. It explains how memories are stored, retrieved, and managed, covering hybrid retrieval mechanisms and the memory lifecycle. Developers can leverage this skill to deeply understand agentmemory's internal workings, enabling better system extension, troubleshooting, or optimization of memory strategies, ensuring AI agents efficiently manage and utilize knowledge.
npx skills add https://github.com/rohitg00/agentmemory --skill agentmemory-architectureBefore / After Comparison
1 组Without this skill, developers would spend significant time manually sifting through code, fragmented documentation, or conducting trial-and-error to grasp agentmemory's complex internal mechanisms, leading to a steep learning curve and inefficient system extension or troubleshooting.
This skill provides a clear architectural overview and operational principles, enabling developers to quickly master how agentmemory stores, retrieves, and manages memories, significantly reducing learning time and accelerating development and diagnostic processes.
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.
User Reviews (0)
Write a Review
No reviews yet
Statistics
User Rating
Rate this Skill