Repolode
oratis

oratis/LISA

Open-source AI personal assistant for planning, writing and personal knowledge, runnable on a Mac or self-hosted with your own model keys.

Stars
175
Forks
2
Open issues
9
Last commit
4 days ago

What is it?

LISA is a personal AI assistant that helps with planning a day, drafting messages, and keeping a personal knowledge base. It can be used through a signed Mac app, a CLI with a self-hosted web workspace, or the hosted LISA Cloud service. Self-hosted setups support Anthropic, OpenAI, Gemini, OpenAI-compatible services and local models such as Ollama and LM Studio.

Beyond chat, LISA keeps file-backed identity, memories and journals within an instance, and can save links, ingest articles and video transcripts, and search a linked wiki. It can also observe supported coding agent sessions such as Claude Code, Codex, OpenCode and Aider. Optional read-only mail, MCP tools, and messaging channels including Telegram, Discord, Slack, Feishu and iMessage require explicit setup.

Autonomous features such as goals, routines and watchers are opt-in, and actions without an approval integration are denied. Local data is stored under ~/.lisa by default, while choosing a remote model sends relevant context to that provider.

Key features

  • 01Chat with streaming replies, tool activity, history and retry.
  • 02Persistent identity, memories and journals within a single instance.
  • 03Save links, ingest articles and video transcripts, and search a linked wiki.
  • 04Observe and coordinate Claude Code, Codex, OpenCode and Aider sessions.
  • 05Supports Anthropic, OpenAI, Gemini, OpenAI-compatible APIs and local models.
  • 06Opt-in Warden approval layer with scoped grants and audit records for web chat.

Use cases

  • Planning a day and drafting messages or writing from a personal assistant.
  • Building a searchable personal knowledge base from saved links and transcripts.
  • Monitoring and dispatching work across local coding agent sessions on a Mac.
  • Running a self-hosted assistant with a local model such as Ollama.

Quick start

  1. 1

    Install the CLI with Homebrew

    brew install oratis/tap/lisa
  2. 2

    Or install the CLI with npm

    npm install -g @oratis/lisa
  3. 3

    Add your model API key to ~/.lisa/config.env (create the folder first)

    mkdir -p ~/.lisa
  4. 4

    Start the web workspace at http://localhost:5757

    lisa serve --web

Things to know

  • Requires Node 22.19+ or a provider API key, or a local model, for the CLI and self-hosted setup.
  • Hosted LISA Cloud and your Mac instance keep separate histories, memories and credentials.
  • The iOS app is not yet publicly approved on the App Store.
  • Local tools only work while your Mac is running and reachable.

Topics

FAQ

What is LISA?
Open-source AI personal assistant for planning, writing and personal knowledge, runnable on a Mac or self-hosted with your own model keys. LISA is a personal AI assistant that helps with planning a day, drafting messages, and keeping a personal knowledge base. It can be used through a signed Mac app, a CLI with a self-hosted web workspace, or the hosted LISA Cloud service. Self-hosted setups support Anthropic, OpenAI, Gemini, OpenAI-compatible services and local models such as Ollama and LM Studio.
Is LISA free to use? What license does it have?
LISA is open source under the MIT license. Check the license terms before using it in commercial products.
Is LISA still maintained?
Actively maintained. The last commit to LISA was on Oct 19, 2026.
What can I use LISA for?
Planning a day and drafting messages or writing from a personal assistant. Building a searchable personal knowledge base from saved links and transcripts. Monitoring and dispatching work across local coding agent sessions on a Mac. Running a self-hosted assistant with a local model such as Ollama.
How do I install LISA?
Install the CLI with Homebrew: brew install oratis/tap/lisa Or install the CLI with npm: npm install -g @oratis/lisa Add your model API key to ~/.lisa/config.env (create the folder first): mkdir -p ~/.lisa Start the web workspace at http://localhost:5757: lisa serve --web
Where can I get LISA?
The source code and installation instructions are on GitHub: https://github.com/oratis/LISA

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects