Find past discussions across existing screenpipe, Codex, Claude, Cursor, and Gemini CLI chats by title, workspace, or message text. With explicit authorization, send follow-up work to a specific supported chat; Gemini CLI supports search only.
Search what was said in existing screenpipe, Codex, Claude, Cursor, and Gemini CLI chats, then continue or steer one exact chat when the user explicitly asks. Use for requests about finding another agent conversation, recalling what an agent said, or sending work to one.
Review the instructions the agent will receive before you install.
screenpipe exposes search_chats and send_to_chat as agent tools. They use a
private core capability passed into the current chat process; do not scrape
transcript folders, guess runtime commands, or call a localhost app route.
search_chats with a short title, message, workspace, or exact id. The
query also matches the transcript, so a phrase said mid-conversation finds
the chat even when the title never mentions it. Omit the query to list recent
chats. Filter sources only when the user named a runtime.source and id as the address. Never derive an id from
a title or reuse a stale result after the target disappears.warnings array. Transcript reading is bounded to the most recent
chats per runtime, so report that older chats were not searched instead of
claiming a phrase was never said.Searching is read-only and does not require confirmation.
search_chats in the current turn.send_to_chat with the exact source, id, message, and
confirmed: true.mode: queue by default. Use mode: steer only when the user asked to
redirect a currently running screenpipe chat.Gemini CLI chats are search-only: Gemini has no non-interactive resume, so
send_to_chat rejects them instead of opening an interactive session. Say so
and offer to summarize what the chat already contains.
The tool refuses self-sends, guessed ids, dormant-chat steering, oversized messages, unsendable sources, and sends without confirmation. Cross-chat sending is disabled in unattended scheduled runs.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Develop and test Windows-specific Screenpipe changes on a disposable Azure virtual machine. The workflow verifies native behavior, preserves logs and desktop video, and handles branch and pull request delivery when authorized.
Prepare screenpipe component releases by updating versions and dependency lock files, running required build checks, and triggering GitHub Actions. Verify build results and release artifacts, then hand public app publication over to a person.
Create charts, dashboards, scorecards, and styled summaries as standalone HTML reports for the screenpipe viewer. Keep styles, scripts, and images inside the file so the report renders in a sandbox with no network access.
Use Screenpipe’s local REST API, an interface for programmatic requests, to search screen and meeting history, review app activity and active time, retrieve synced-device records, export recordings, and rerun audio transcription.
Search Screenpipe recordings, screen text, audio transcripts, and synced-device history through its local API. Use the evidence to review activity, find meeting details, and inspect saved workflows, including recorded steps that can inform automation.
Turn a recorded software failure into a draft bug report with timestamps, reproduction steps, expected and actual behavior, and relevant evidence. Separate visible symptoms from possible causes and remove sensitive details from shareable evidence.