TC

tini-coder/tini-agent

Developer tools

Эта страница переведена автоматически. Технические детали смотрите в оригинале. Открыть оригинал

27 stars Качество 58 Тренд 19

Meet — a local-first personal assistant that shows the four pillars behind every serious agent: . No frameworks hiding the good parts.

Обзор

Meet — a local-first personal assistant that shows the four pillars behind every serious agent: . No frameworks hiding the good parts. - Your memory is one SQLite file. Open it. Read it. It's yours. - Semantic + episodic + procedural — with a gate that decides whether to remember, and a pass that decides what to keep. - of plain Python. Step through it. - A local dashboard lights up every message as it flows through the harness. - 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. — the loop, the memory pillars, the evals, the Telegram gateway and the "Tini" wake word, live. It will tell you which key to set the first time. Want to (the point of this repo) or contribute — clone it instead: uv run tini … needs . Three ways to run it: tini and tini dashboard are two doors into the Tini.

README

Показан фрагмент оригинального README. Открыть оригинал.

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:

Command When
uv run tini dashboard quick start, zero activation (recommended)
source .venv/bin/activate → tini dashboard activate once, bare tini all session
uv tool install . → tini dashboard install tini globally, forever

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.

Открыть полный README на GitHub

Рекомендуемые инструменты

Попробуйте другой запрос или уберите фильтр.

Установка

npx skillfish add tini-coder/tini-agent
Новичок в MCP? Начните с руководства на mcpskill.org →