Who it is forA developer or agent starting a task that may have been tackled in an earlier session, such as an error pattern or a design choice.
The problemEarlier attempts and decisions are scattered across many single-session chat histories that the harness does not search together.
The outcomeThe user or agent finds the matching sessions, with the user, device, harness, and session named for each hit, and reads the relevant passage.
What you need first
- macOS or Linux (arm64 or amd64) with a shell
- At least one supported harness CLI installed, such as Claude Code CLI, Codex CLI, Devin CLI, or opencode
- Docker with Compose, only for the team server use case
- A shared team server address and a way to send an invite string over a channel you trust, only for the team server use case
Steps
- Run
curl -fsSL https://flopwire.com/install.sh | shto install the Flopwire binary. - Run
flopwire setupto configure supported harnesses detected on PATH. - Run
flopwire agent runand keep it running to index this machine's transcripts. - Run
flopwire grep 'exit (code|status) [1-9]' --since 24hto find matching lines across every session, or replace the pattern with your own. - Run
flopwire search 'how did we handle rate limits?'for ranked keyword results, thenflopwire readon a hit to see the passage. (inferred, check the README)
Prompt for your agent
Use the flopwire/flopwire CLI to search all indexed sessions for <topic> with `flopwire search '<topic>'`. Report the top three hits with user, device, harness, and session for each, and confirm each hit by reading its passage with `flopwire read`.
Caveat. Search covers only transcripts from supported harnesses that the device agent indexes under your path rules, so sessions in excluded paths will not appear.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them freeShare: 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 The use cases, steps, and prompts are written by AI and may be incomplete, outdated, or just wrong.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