A connector for Waku Memory, a hosted store where several coding agents can share saved facts through MCP, a standard way for tools to communicate. It is separate from this app’s local memory.

Use it to connect this app to Waku Memory and export the related skills to other agents such as Claude Code, Codex, Grok Bot, or Hermes.

It lets information saved in one supported agent be recalled in another, instead of keeping each agent’s memory isolated.

waku-memory — Skill for Claude Code and Codex by ShenSeanChen

About the project

Waku Agent is a local-first personal AI assistant whose readable code implements the agent loop, memory, and evaluation system. It is for people who want an assistant they can run and understand on their own laptop, with memory stored in SQLite and built-in testing. The catalogue add-ons support its agent workflow.

ShenSeanChen/waku-agent · 2,030 stars · on GitHub

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add ShenSeanChen/waku-agent --skill waku-memory

Clone the repo

git clone --depth 1 https://github.com/ShenSeanChen/waku-agent

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/shenseanchen/waku-agent/waku-memory/github.svg)](https://agentmods.dev/skills/shenseanchen/waku-agent/waku-memory)

Your own site

<a href="https://agentmods.dev/skills/shenseanchen/waku-agent/waku-memory"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/waku-memory/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/shenseanchen/waku-agent/waku-memory"><img src="https://agentmods.dev/badge/skills/shenseanchen/waku-agent/waku-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 502 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00030	$0.00502
Opus 5.5	$0.00012	$0.00201
Sonnet 5.5	$0.00006	$0.00100
Haiku 4.5	$0.00003	$0.00050

Measured 15d ago against content hash 1767f316ed3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

waku-memory scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 15d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Subtle steeringmediumPrompt injection

Instructions that bias recommendations or shape behaviour without the user noticing.

never tell the user a fact is there unless a tool's output says so.

skills/waku-memory/SKILL.md · 45 lines

What it actually says

What Waku Memory is

This app's memory is local. It lives in ~/.waku/ on this machine. Waku also writes each fact to ~/.waku/memory/, one file per fact, so the Waku Memory importer can upload it. Waku Memory (waku.one) is a hosted memory that several agents share over MCP: a fact saved in Claude Code can be recalled in Codex, Grok Bot or this app. A fact reaches Waku Memory only when it is uploaded, so never tell the user a fact is there unless a tool's output says so.

Connecting this app

Connecting opens the user's browser, so you cannot do it for them. Tell them to type /connect waku-memory in the dashboard chat, or to run waku connect waku-memory in a terminal. It needs the MCP extra: pip install 'waku-agent[mcp]'. After it connects, a restart of Waku loads the waku_memory_* tools.

Connecting other agents

Claude Code, Codex, Hermes: point them to https://www.waku.one/docs.
Grok Bot: Settings → Plugins → add a custom connector with the URL https://api.waku.one/mcp and the header Authorization: Bearer <key>, using a key from waku.one → Account → Keys. Its connector form takes a URL and a header, not a browser sign-in, which is why it needs the key.
Muse Code or any other MCP client: add https://api.waku.one/mcp as a remote (streamable HTTP) server.

Tell the user to paste a key only into the other agent's own settings, never into this chat.

Carrying skills

waku skill export --to claude,codex copies Waku's skills into Claude Code's and Codex's skills folders. --project writes to ./.claude/skills, which Muse Code also reads. Saving skills into Waku Memory is not available yet.

What not to claim

Don't quote prices, plans or limits; point to https://www.waku.one/docs.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

15d ago Changed · +1 lines 1767f316ed3b
1mo ago First seen · 44 lines · 30 tokens per session scan B d1aa5216c101

Subscribe to this mod's changes

waku-memory is a skill published in the GitHub repository ShenSeanChen/waku-agent (2,030 stars, last pushed 5d ago), licensed MIT. It adds 30 tokens to every session and 502 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-15.

LLM Memory and context agent-framework ai-agent ai-assistant claude evals

data-sync

Sync and archive data from messaging platforms (WhatsApp, Discord, Slack, Twitter/X, Google) into Moltis memory as daily digest summaries. Orchestrates crawl tools and writes structured markdown to the memory system.

moltis-org/moltis · 46 tokens

agentlas-auto-activation

Use when adding or auditing local runtime behavior that turns a project folder into an Agentlas-aware workspace with .agentlas memory and sitemap files.

agentlas-ai/Agentlas-OS · 34 tokens

agentlas-one

Use when the user types /agentlas-one on|off, /agentlas one on|off, or asks to enable/disable the persistent personal agent mode.

agentlas-ai/Agentlas-OS · 37 tokens

memory-ticketing

Use when adding Memory Events, Memory Tickets, memory-map.json, vault-references.json, PM Soul memory ownership, or Memory Curator routing to an agent repo.