DEDUPED Hot AI repos, turned into use cases Get 5 a day

How to run a private companion that remembers your details with Apeireth

Install the desktop companion, add a provider key, and keep memories on your own machine.

Credentials. Your provider key is stored in the OS keyring when available, but the file backend is plaintext and the fallback backends do no zeroization, so check where your key is saved.

Who it is forA person who wants a personal assistant that remembers small everyday details and keeps them on their own computer.

The problemMost chat tools forget what you said earlier, and you have no clear view of what they keep about you.

The outcomeA running desktop companion that stores memories locally, which you can read, export, or wipe.

What you need first

  • A Windows PC for the installer path, or Windows, Linux, or macOS with the source build steps in INSTALL.md
  • An API key from one of the supported providers (OpenAI-compatible, MiniMax, or Anthropic)
  • For source builds: Git, rustup 1.97.1, and VS Build Tools 2022 as listed in INSTALL.md

Steps

  1. Download the Windows installer from the Releases page and check the attached SHA256 value.
  2. Double-click the installer and open the companion desktop icon.
  3. Pick a provider, enter your key, and say something to start a conversation.
  4. Open Settings and choose "Character & Memory" to review what it has kept.

Prompt for your agent

Using the Apeireth repo at <repo path>, confirm the companion starts on <target machine> and answers a test message. Expected output: a reply in the chat window. Verify that the memory section in Settings lists the test message.

Caveat. The care rule face is OFF by default and needs an explicit environment variable to turn on, so do not expect scheduled care messages out of the box.

Share: X LinkedIn Hacker News Email Copy link

Disclaimer

Deduped lists open-source repositories that belong to other people. We do not own, maintain, audit, or vouch for any of them, and a repo appearing here is not an endorsement or a safety check. The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong. Where a use case is marked "Seen in the wild", we link to public posts where someone described something similar, but we have not verified those posts and the use case itself is still our AI's own write-up. Use all of this at your own risk. Only run code, commands, or agents on systems and accounts you are authorized to use, and read the code and every command before you run it, especially anything that touches credentials, files, or the network. Nothing here is professional, security, legal, or financial advice. All trademarks and project names belong to their respective owners, and their use here does not imply affiliation. Content is provided as is, without warranties of any kind. Found a mistake, a safety problem, or something you want removed? Email [email protected] and we will look at it promptly. Full disclaimer page