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

How to keep a long task on track across fresh chats with Chat on Steroids

Use Goal, Loop and Compact & Resume to keep unfinished work moving and carry it into a new chat.

Who it is forA user running a multi-step task, such as a long refactor or research pass, that outgrows one chat session.

The problemLong tasks lose direction as chats grow, and restarting in a new chat normally drops the session and worker history.

The outcomeUnfinished work stays tracked toward the goal, and the session and worker history continue in a fresh chat.

What you need first

  • Windows 10/11, macOS 13 Ventura or newer, or a current desktop Linux with a Secret Service keyring
  • Chrome 125+, current Edge or Brave for the browser extension
  • A ChatGPT account or workspace that can create custom MCP apps
  • A tunnel and a restricted API key created at OpenAI for Core setup

Steps

  1. Complete the Get started steps in Settings → Setup.
  2. Write the task as a goal and start it so Goal follows unfinished work.
  3. Send a correction in the middle of the run if the direction changes.
  4. When the chat gets long, use Compact & Resume to carry the session and worker history into a fresh chat.
  5. In the new chat, check that the remaining work matches the original brief before continuing.

Prompt for your agent

Using the repo totec448-spec/chat-on-steroids, set the goal <goal-description> for the project at <project-path> and use Loop within the brief I give. When the chat is long, run Compact & Resume. Expected output: a summary of finished and unfinished items after the resume. Verify that the unfinished items match the original goal.

Caveat. These features organize work only and must not be used to evade rate limits, usage caps or account restrictions.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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