knowledge-agent

Use it when:: You want to ask questions of one slice of your claude-mem history, such as everything about a subsystem or last month's decisions.
It does:: Collects matching observations into a named corpus, loads it into an AI session, and answers your questions from it.
You get:: A reusable knowledge base: prime it once, ask many questions, with follow-ups keeping context.
Filters by:: Project, observation type such as decision or bugfix, concept tags, files, a semantic query and dates, up to 500 observations by default.
Needs:: claude-mem and its MCP tools.

Needs claude-mem installed with its MCP server. Per claude-mem's docs, priming loads the whole corpus into a separate Claude session through the Agent SDK, so a large corpus costs tokens up front.

TL;DR

claude-mem records observations, notes on what happened in your agent sessions. This skill turns a filtered set of them, a corpus, into what it calls a knowledge agent, or a "brain". build_corpus collects the observations, prime_corpus loads them into an AI session, and query_corpus asks that session a question; list_corpora shows each corpus with its stats and whether it's primed. Its tips: focused corpora such as "hooks architecture" work better than everything at once; prime once and query many times; reprime to clear a conversation that drifted while keeping the corpus; and when new observations arrive, rebuild the corpus, then reprime.

Summarizes the skill at 31ebffb.

npx skills add https://github.com/thedotmack/claude-mem --skill knowledge-agent

skills.sh page Source on GitHub All skills from thedotmack/claude-mem

Total Downloads: 6,000 on skills.sh, Nov 9, 2026
Repo stars: 114,993 thedotmack/claude-mem
First seen: Apr 9, 2026 on skills.sh

Weekly Downloads

153

+51% over the 8 weeks to Nov 9

Weekly values

Week to	Installs
Sep 21	101
Sep 28	95
Oct 5	92
Oct 12	94
Oct 19	122
Oct 26	113
Nov 2	135
Nov 9	153

Category	category:agents category:software-engineering Build agents, orchestrate workers and give agents memory. Everything for building software: planning, coding, debugging, design, frameworks, cloud, agents and skills.
Type	type:tool Operates a CLI, API, app or bundled script to get something done.
Effect	effect:local Its own steps create or change files, git state or local tools.
Needs	needs:mcp Needs an MCP server connected.
Publisher	by:official A verified publisher on skills.sh, or the company or maintainer behind the product the skill operates.
Topics	memory
Stack	stack:claude-mem

SKILL.md

From thedotmack/claude-mem at 31ebffb. Checked daily, last changed Nov 6, 2026.

Frontmatter

name: knowledge-agent
description: Build and query AI-powered knowledge bases from claude-mem observations. Use when users want to create focused "brains" from their observation history, ask questions about past work patterns, or compile expertise on specific topics.

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

Filter options:

project — filter by project name
types — comma-separated: decision, bugfix, feature, refactor, discovery, change
concepts — comma-separated concept tags
files — comma-separated file paths (prefix match)
query — semantic search query
dateStart / dateEnd — ISO date range
limit — max observations (default 500)

Step 2: Prime the corpus

prime_corpus name="hooks-expertise"

This creates an AI session loaded with all the corpus knowledge. Takes a moment for large corpora.

Step 3: Query

query_corpus name="hooks-expertise" question="What are the 5 lifecycle hooks and when does each fire?"

The knowledge agent answers from its corpus. Follow-up questions maintain context.

Step 4: List corpora

list_corpora

Shows all corpora with stats and priming status.

Tips

Focused corpora work best — "hooks architecture" beats "everything ever"
Prime once, query many times — the session persists across queries
Reprime for fresh context — if the conversation drifts, reprime to reset
Rebuild to update — when new observations are added, rebuild then reprime

Maintenance

Rebuild a corpus (refresh with new observations)

rebuild_corpus name="hooks-expertise"

After rebuilding, reprime to load the updated knowledge:

Reprime (fresh session)

reprime_corpus name="hooks-expertise"

Clears prior Q&A context and reloads the corpus into a new session.