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

How to steer an agent mid-task with queued follow-ups with Waku

Send follow-up instructions while an agent is still working, without starting over.

Who it is forA developer who notices an agent heading the wrong way partway through a long task and wants to correct it without losing the session.

The problemMost agent terminals make you wait for a run to finish before you can redirect it.

The outcomeYour follow-up message is queued or used to steer the running agent, and the session continues in the same thread.

What you need first

  • A supported agent CLI installed and authenticated, such as Claude Code, Codex CLI, or Cursor CLI
  • macOS, Linux, or Windows (the README lists different install paths and feature availability per platform)
  • For the Linux script, a shell with curl and permission to write to ~/.local (no root needed)
  • For building from source: Rust 1.96 or newer, Bun, and the native prerequisites in CONTRIBUTING.md

Steps

  1. Install Waku and at least one authenticated agent CLI, as described in the install section of the README.
  2. Open a project and start a session with a task that will take a while.
  3. While the agent is working, type a follow-up message and choose to queue or steer it.
  4. Check the transcript to confirm the follow-up was applied in the same session.

Prompt for your agent

Using the waku app at <Waku install location>, start a session on the project at <project path> with the task <task description>, then send one follow-up message while the agent is running. Expected output: a transcript showing the queued or steered message inside the same session. Verify that the session ID did not change.

Caveat. The README describes queueing and steering but does not say which option each provider supports, so test with the agent you use.

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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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