Menu

Individual skill

conversation-memory

0upvotes

Keep long conversations coherent — summarization checkpoints, entity tracking, topic stacks, and graceful context handoffs. Use when dialogues run long or span sessions and the agent keeps losing the thread.

skills/conversation-memory/SKILL.md

Read pinned source

Source commit faf37c0859ebf627bfcb5225e8057d088691e0ae

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Not checked yet
Last checked
Nov 8, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
54
Repository last updated
Oct 10, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Conversation Memory

A conversation is a stream of context that eventually overflows. Conversation memory is the 
practice of compressing, indexing, and resurfacing dialogue so long interactions stay coherent 
without drowning in tokens.

## Overview

The technique is checkpoints: at intervals, distill the conversation so far into a compact summary 
capturing decisions, open questions, entities, and tone. Between checkpoints, keep raw recent turns 
for fidelity. When the context fills, drop old raw turns but keep the summaries — the thread 
survives even as the details fade. Add entity tracking (who/what was mentioned and their status) 
and the agent can reference things from an hour ago as naturally as from a minute ago.
Back to top