waku-agent is a local-first AI personal assistant with a readable ~95-line Python loop, SQLite memory, and built-in evaluation, designed as an educational blueprint for building transparent agent systems.

Stars

585

7-day growth

No data

Forks

123

Open issues

3

License

MIT

Last updated

2026-07-27

AI repository intelligence
FR-AI / ANALYSIS

Why it is worth attention

It demystifies agent architecture by providing a fully transparent, minimal codebase that demonstrates memory pillars, retrieval gates, and dual eval methods (deterministic and LLM-as-judge), all with a local dashboard.

Who it is for

  • AI developers and engineers learning agent architecture
  • Hobbyists wanting a local, private AI assistant
  • Educators teaching agent design and LLM operations
  • Developers needing a customizable, readable agent framework

Use cases

  • Personal scheduling and memory management (e.g., calendar events, preferences)
  • Local research assistant with web search and note-taking
  • Teaching tool for understanding agent loops, gates, and evals
  • Multi-channel assistant (CLI, browser dashboard, Telegram, voice)

Strengths

  • Readable ~95-line agent loop without heavy frameworks (LangGraph, etc.)
  • Local-first with SQLite memory and full data ownership; dashboard runs on localhost only
  • Built-in evaluation suite: deterministic tests and LLM-as-judge side by side
  • Comprehensive local dashboard for real-time monitoring of memory, tools, traces, and ops

Considerations

  • Not designed for high-scale production deployments (local, single-user focus)
  • Requires manual setup of API keys for various LLM providers
  • Some features (sub-agents, terminal, browser, cron) are experimental or skeleton-only

README quick start

waku-agent

Your own AI assistant. On your laptop. In code you can read in an afternoon.

Meet Waku — a local-first personal assistant that shows the four pillars behind every serious agent: Harness · Loop · Memory · Eval/LLM-Ops. No frameworks hiding the good parts. Built for Sean's AI Stories.

  • Local-first. Your memory is one SQLite file. Open it. Read it. It's yours.
  • Memory is the hero. Semantic + episodic + procedural — with a gate that decides whether to remember, and a pass that decides what to keep.
  • The loop is ~95 lines of plain Python. Step through it.
  • Watch it think. A local dashboard lights up every message as it flows through the harness.
  • Eval built in. Deterministic tests and LLM-as-judge, side by side, with a release gate.

The system-design whiteboard from the series. Every box maps to a file — see the whiteboard maps to the code.

Watch the 20-min code walkthrough — the loop, the memory pillars, the evals, the Telegram gateway and the "Waku Waku" wake word, live.

YouTube · X · LinkedIn · Instagram · TikTok · Discord · 哔哩哔哩 · 小红书 · 抖音

☕️ Buy me a coffee — it keeps this repo (and the videos) coming

Quickstart

git clone https://github.com/ShenSeanChen/waku-agent && cd waku-agent
uv venv && uv pip install -e .          # create the env + install the `waku` command
cp .env.example .env                    # pick a provider, paste ONE key
uv run waku                             # talk to your Waku in the terminal
uv run waku dashboard                   # …or the browser cockpit → localhost:7777

uv run waku … needs no venv activation. Three ways to run it:

CommandWhen
uv run waku dashboardquick s

Description

Waku Waku! Waku agent is your personal AI agent, on your own laptop, in code you can read in an afternoon — harness + loop + memory + eval

Related repositories

Similar projects matched by category, topics, and programming language.

lopopolo
Featured
lopopolo GitHub avatar

harness-engineering

Harness Engineering is a methodology for improving coding agent outputs by carefully crafting the environment around them—providing curated context, tools, and executable constraints that encode an organization’s nonfunctional requirements and cumulative lessons.

AI & Machine LearningAI Agents
2,390
slvDev
Featured
slvDev GitHub avatar

esp32-ai

A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.

AI & Machine LearningLarge Language Models
1,960
littledivy
Featured
littledivy GitHub avatar

mimic

mimic captures traffic from any iOS or web app and automatically generates a Python client library that lets you call the app's API like a regular library.

AI & Machine Learning
1,482