你自己的AI助手。在你的笔记本电脑上。用代码，你一个下午就能读懂。

认识一下Tini——一位以本地为先的私人助理，展示每个人背后的四大支柱 严肃代理：束缚 ·上下文 ·工具 ·循环 ·内存 ·评估/大型语言模型运算。没有框架隐藏优点。

• 本地优先。 你的内存是一个SQLite文件。打开它。读它。它是你的。
• 记忆是英雄。 语义 + 情节 + 程序化 — 带有一个决定是否 记住，以及决定“保留”什么的通行证。
• **循环是~95行纯Python。穿过去。
• 看它思考。 本地仪表盘会点亮通过线束流转的每条消息。
• **内置评估。**确定性测试和大型语言模型作为评判，并列使用释放门。

系列中的系统设计白板。 每个框都映射到一个文件——请参见白板映射到代码。

** ▶ 观看代码攻略 ** ——循环、记忆支柱、评估、Telegram网关和“Tini”唤醒词，实时运行。

快速开始

只是想说说：

它会告诉你第一次要设置哪个键。想读代码（ 这个仓库的重点）或贡献——克隆它：

Tini-agent

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

Meet Tini — a local-first personal assistant that shows the four pillars behind every serious agent: Harness · Context · Tools · Loop · Memory · Eval/LLM-Ops. No frameworks hiding the good parts.

• 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 code walkthrough — the loop, the memory pillars, the evals, the Telegram gateway and the “Tini” wake word, live.

Quickstart

Just want to run it:

pip install tini-agent
tini                                    # talk to your Tini in the terminal
tini dashboard                          # …or the browser cockpit → localhost:9000

It will tell you which key to set the first time. Want to read the code (the point of this repo) or contribute — clone it instead:

git clone https://github.com/tini-coder/tini-agent && cd tini-agent
uv venv && uv pip install -e .          # create the env + install the `tini` command
cp .env.example .env                    # pick a provider, paste ONE key
uv run tini                             # talk to your Tini in the terminal
uv run tini dashboard                   # …or the browser cockpit → localhost:9000

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

tini and tini dashboard are two doors into the same Tini. The dashboard is a tiny web server on your machine — chat in the browser, that process runs the turn. Nothing leaves your laptop. Set TELEGRAM_BOT_TOKEN and it starts your bot too. (make dashboard works as well.)

Now try it. “Remember that Alex prefers morning meetings.” Quit. Restart. “Book a catch-up with Alex on Friday.” → it remembers, and books 9am. Your memory is one file: .tini/state.db.