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

How to give an existing repo a memory the agent keeps with Operator Memory

Set up Operator on a real project so each new agent session starts from an indexed codebase and written specs.

Who it is forA developer picking up an existing project with a coding agent, who is tired of the agent re-exploring the code at the start of every session.

The problemAgents forget everything when a session ends, so each new session wastes tokens re-learning the architecture and decisions.

The outcomeThe repo has an Operator brain with an index, and later sessions begin from that knowledge instead of from zero.

What you need first

  • Node.js with npm, or Bun, to install the Operator Helper
  • A supported harness installed, such as Claude Code or Codex
  • A local project repository you want the agent to document

Steps

  1. Install the Helper with npm install --global @aerovato/operator-helper.
  2. Install the adapter for your harness with operator-helper install claude-code or operator-helper install codex.
  3. In a new conversation, run /operator:user-init once to set up your global user partition.
  4. In your project, start a new conversation and run /operator:project-init to scaffold Operator and index the repo.
  5. Ask the agent to write the first specifications for the modules you work on, then start a new conversation for normal work.

Prompt for your agent

Use the Operator Memory repo at https://github.com/aerovato/operator-memory to set up Operator for the project at <project-path>. Run the install steps from its README, then ask the agent to write the first specifications for <module-name>. Verify that a .operator/ directory exists in the project and that it contains at least one specification file.

Caveat. The README says a cold project starts with a sparse brain, so the first sessions will need you to ask the agent for specs before the memory becomes useful.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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