CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-memory-mcp

A hybrid memory system that provides persistent, searchable knowledge management for AI agents (Architecture, Patterns, Decisions).

Install with Tessl CLI

npx tessl i github:duclm1x1/Dive-Ai --skill agent-memory-mcp
What are skills?

57

Does it follow best practices?

Validation for skill structure

SKILL.md
Review
Evals

Evaluation results

100%

68%

Automate Agent Memory System Bootstrap

Agent memory setup workflow

Criteria
Without context
With context

Correct clone destination

0%

100%

Correct source repo

0%

100%

npm install step

25%

100%

Compile step present

0%

100%

start-server command

0%

100%

Project ID argument

35%

100%

Absolute path argument

35%

100%

Node.js version requirement

100%

100%

Script parameterized

100%

100%

Without context: $0.2853 · 1m 21s · 18 turns · 20 in / 4,668 out tokens

With context: $0.3152 · 59s · 19 turns · 22 in / 3,661 out tokens

100%

100%

Build an Agent Memory Integration Cheat Sheet

MCP tool names and argument formats

Criteria
Without context
With context

memory_write tool name

0%

100%

memory_write key arg

0%

100%

memory_write type arg

0%

100%

memory_write content arg

0%

100%

memory_write tags arg

0%

100%

memory_search tool name

0%

100%

memory_search query arg

0%

100%

memory_search optional filters

0%

100%

memory_read tool name

0%

100%

memory_read key arg

0%

100%

memory_stats tool name

0%

100%

memory_stats no required args

0%

100%

Without context: $0.4395 · 1m 33s · 17 turns · 1,682 in / 4,893 out tokens

With context: $0.2017 · 57s · 11 turns · 268 in / 3,200 out tokens

100%

100%

Add Memory Monitoring to a Development Environment

Dashboard setup and complete workflow

Criteria
Without context
With context

Clone to correct path

0%

100%

npm install step

0%

100%

Compile step

0%

100%

start-server with project ID

0%

100%

start-server with absolute path

0%

100%

Dashboard start command

0%

100%

Dashboard receives absolute path

0%

100%

Dashboard URL correct

0%

100%

Node.js prerequisite

0%

100%

Source repo URL

0%

100%

Without context: $5.8680 · 17m 12s · 125 turns · 7,022 in / 32,655 out tokens

With context: $0.1724 · 35s · 12 turns · 13 in / 2,295 out tokens

Evaluated
Agent
Claude Code

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.