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

How to build an assistant that remembers users across sessions with Octop Harness

Keep strong memory and a user profile that persist across sessions and can be saved on request.

Credentials. Memory captures eligible conversation content, so avoid saving secrets or private identifiers into MEMORY.md, USER.md, or chat.

Who it is forA team building a support or personal assistant that must recall user preferences and facts from earlier conversations.

The problemChat assistants lose context between sessions, so users repeat preferences and the agent cannot build on past work.

The outcomeAn agent that loads MEMORY.md and USER.md at session start, saves explicit remember requests with memory_save, and retrieves past history with memory_search.

What you need first

  • Python 3.12 or newer
  • An API key for at least one model provider (OpenAI, Anthropic, AWS Bedrock, or an OpenAI-compatible endpoint)

Steps

  1. Install Octop Harness and create a workspace with octop-harness init (inferred command). (inferred, check the README)
  2. Open MEMORY.md and USER.md in the workspace and add your own notes, since manual edits apply to new sessions.
  3. Start an interactive chat with the CLI (inferred: octop-harness chat). (inferred, check the README)
  4. Ask the agent to remember a preference, which it saves through memory_save.
  5. Start a new session and ask a question that depends on that preference, then check that the answer uses the saved fact.

Prompt for your agent

In the TencentCloud/octop-harness repo, set up a workspace at <workspace path> and add the user preference <preference> to USER.md. Start a new session and ask <question>. Verify the reply uses the saved preference.

Caveat. The README says agent file tools cannot edit MEMORY.md or USER.md, so changes to those files must be made by you or a host-provided editor.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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