amie — Anonymous Memory Intelligence
Your private memory intelligence. Captures thoughts from anywhere, organises them into your Obsidian vault, and reflects insights back to you — entirely on your own hardware. No cloud services, no subscriptions.
Install
Pick your platform:
- Linux / WSL2 → docs/install-linux.md
- Windows (native) → docs/install-windows.md
Quick path (Linux/WSL2):
# 1. Install uv and Ollama first (see docs/install-linux.md)
uv tool install amie
amie init
amie check health
Quick path (Windows, elevated PowerShell):
# 1. Install Python, uv, and Ollama first (see docs/install-windows.md)
uv tool install amie
amie init
amie check health
Dashboard
export AMIE_VAULT_PATH=/path/to/your/vault
amie dashboard serve --open
Opens a local web UI at http://127.0.0.1:8765. See docs/dashboard.md.
CLI overview
amie init first-time setup — vault, SSH, Syncthing
amie check health verify everything is ready
amie watch start start the background inbox watcher
amie digest weekly generate a weekly digest
amie dashboard serve launch the web dashboard
amie doctor detailed health report
amie --help full command reference
Requirements
| Requirement | Notes |
|---|---|
| Python 3.12+ | Ships with Ubuntu 24.04; winget on Windows |
| uv | Package manager — single binary install |
| Ollama | Local LLM runner — models stay on your device |
| Obsidian | Vault host — any existing vault works |
License
MIT. See LICENSE.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
amie-1.19.1-py3-none-any.whl
(190.3 kB
view details)
File details
Details for the file amie-1.19.1-py3-none-any.whl.
File metadata
- Download URL: amie-1.19.1-py3-none-any.whl
- Upload date:
- Size: 190.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via:
uv/0.12.3 {"installer":{"name":"uv","version":"0.12.3","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Debian GNU/Linux","version":"13","id":"trixie","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
3a267e0b706c7d6688a318070135daecbb0f6e4b67708889afdc0cd77c053967
|
|
| MD5 |
34f24787d51e591ab41deec20c9930a2
|
|
| BLAKE2b-256 |
5028c248488cfb28a98aedabcf35199b94f9a0884db7b165866842c3c612d68d
|