Agent Memory
Persistent cross-session memory using vector and graph search that automatically records and compresses every session's work, injecting only the relevant context into the next session.
About this skill
name: agent-memory description: Use when Persistent cross-session memory using vector and graph search that automatically records and compresses every session's work, injecting only the relevant context into the next session.
Agent Memory
Goes beyond basic markdown session-log memory, which becomes unmanageable as it grows and can't capture everything. Agent Memory silently records everything that happens across every session with no manual logging required — just code normally. It automatically compresses activity into a local database, then on the next session injects only the context relevant to the current task using a combination of vector search and graph search, instead of dumping an entire file into context (which pulls in irrelevant noise). A web viewer lets you directly inspect what Claude currently remembers about your project.
What you get
- Fully automatic session recording with zero manual logging, vector + graph search retrieval instead of full-file context dumping, web viewer to inspect what's remembered, scales far better than markdown-based memory as history grows.
Customize your output
- Adjust retrieval sensitivity for vector vs. graph search and review/edit what's stored via the web viewer.
Example output
On session 12, Agent Memory automatically pulled in only the 3 relevant past decisions about the auth refactor, instead of the entire multi-week session history.
Best for
Developers on long-running projects who've hit the limits of markdown-based session logs and want smarter, automatic context retrieval.
Source: Korean Claude Code Creator · https://www.youtube.com/watch?v=UClLUoGaCxU Category: Development / Context Management · Priority: Standard
SKILL.md preview
---
name: agent-memory
description: Use when Persistent cross-session memory using vector and graph search that automatically records and compresses every session's work, injecting only the relevant context into the next session.
---
# Agent Memory
Goes beyond basic markdown session-log memory, which becomes unmanageable as it grows and can't capture everything. Agent Memory silently records everything that happens across every session with no manual logging required — just code normally. It automatically compresses activity into a local database, then on the next session injects only the context relevant to the current task using a combination of vector search and graph search, instead of dumping an entire file into context (which pulls in irrelevant noise). A web vi...