🧠
AI EngineeringJavaScript

Knowledge Agent

by thedotmack

Knowledge Agent is an AI Engineering skill for Claude Code, published by thedotmack in claude-mem.

90.6K stars7.9K forkson thedotmack/claude-memAdded 2026/08/13Repository updated 2026/08/13
aiai-agentsai-memoryanthropicartificial-intelligencechromadbclaudeclaude-agent-sdkclaude-agentsclaude-codeclaude-code-pluginclaude-skillsembeddingslong-term-memorymem0memory-engineopenmemoryragsqlitesupermemory
Install in seconds
Install Knowledge Agent
Copy Knowledge Agent into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/thedotmack/claude-mem/tree/main/plugin/skills/knowledge-agent ~/.claude/skills/knowledge-agent

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/thedotmack/claude-mem.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
plugin/skills/knowledge-agent/SKILL.md in thedotmack/claude-mem
Installs to
~/.claude/skills/knowledge-agent
Collection
One of 22 skills cataloged from this repository
Category
AI Engineering2451 skills

What Knowledge Agent does

Knowledge Agent builds and queries AI-powered knowledge bases from claude-mem observations. Use it to create focused 'brains' from observation history, ask questions about past work patterns, or compile expertise on specific topics.

Knowledge Agent is cataloged under AI Engineering on DirSkills. Knowledge Agent comes from a repository tagged ai, ai-agents, ai-memory, anthropic and artificial-intelligence.

Documentation

README

Knowledge Agent

Build and query AI-powered knowledge bases from claude-mem observations.

What Are Knowledge Agents?

Knowledge agents are filtered corpora of observations compiled into a conversational AI session. Build a corpus from your observation history, prime it (loads the knowledge into an AI session), then ask it questions conversationally.

Think of them as custom "brains": "everything about hooks", "all decisions from the last month", "all bugfixes for the worker service".

Workflow

Step 1: Build a corpus

build_corpus name="hooks-expertise" description="Everything about the hooks lifecycle" project="claude-mem" concepts="hooks" limit=500

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Knowledge Agent

  • What else does thedotmack publish alongside Knowledge Agent?

    Knowledge Agent is one of 22 skills that DirSkills catalogs from thedotmack/claude-mem, the repository it ships in. Its siblings there include Babysit PR, Cloud Sync and Design Is. Each one is a separate skill with its own page in this directory, installs the same way Knowledge Agent does, and is maintained by thedotmack in that same repository. The rest of the collection is listed on the thedotmack/claude-mem page.

  • How does Knowledge Agent compare to other AI Engineering skills?

    Knowledge Agent ranks #47 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Knowledge Agent against them. Open each page to compare what they document and how they install.

More from thedotmack/claude-mem

Knowledge Agent is one of 22 skills cataloged on DirSkills from thedotmack/claude-mem.

See all 22 skills
👀
3w ago

Babysit PR

Babysit PR monitors a pull request and its review cycle until it is ready to merge, checking review comments, unresolved threads, and CI status, and fixing actionable issues. Use when asked to babysit, monitor, or keep checking PRs until all actionable issues are resolved.
Quality
90.6K7.9K
☁️
3w ago

Cloud Sync

Cloud Sync sets up or checks claude-mem cloud sync with cmem.ai Pro, writing connection values and verifying SyncHub status. Use when the user wants memory database backed up or synced to a cmem.ai account.
DevOps
90.6K7.9K
🎨
3w ago

Design Is

Design Is audits a design against Dieter Rams' ten 'Good design is...' principles, scores each with evidence, and hands off a ready /make-plan prompt for new, refine, or redesign outcomes. Use it when the user asks for a design audit, design review, or critique that should lead to a plan.
Frontend
90.6K7.9K
🧠
3w ago

Do

Do gives Claude Code persistent long-term memory by storing and retrieving embeddings in SQLite and vector databases. Use it when you want the agent to remember context across sessions.
AI Engineering
90.6K7.9K
🤖
3w ago

Do Plan

Do Plan executes a phased implementation plan by deploying subagents for each phase, verification, anti-pattern checks, code review, and only committing after verification passes. Use it when asked to execute, run, or carry out a plan, especially one created by make-plan.
AI Engineering
90.6K7.9K
🧠
3w ago

How It Works

How It Works explains how claude-mem captures observations, when memory injection kicks in, and where data lives. Use when the user asks how claude-mem works or what it is doing.
AI Engineering
90.6K7.9K