Your agents ship diffs. Visr keeps trajectories.

Keep the Trajectory, Not Just the Outcome

visr shell starts a transcribed shell in your own terminal. Run Codex, Claude Code, Cursor, or plain commands inside it. Visr transcribes the whole trajectory: every command, output, retry, and fix. It hands you a transcript link when you're done. A goldmine for future agents: every dead end already ruled out, so they don't walk back in.

That's baseline memory for everything downstream: the raw material behind a CLAUDE.md, an AGENTS.md, an MCP server, a skill, evals.

From Trajectories to Knowledge Graph

A transcript is more than a log. The retries, the dead ends, the fix that finally worked: that's the tribal know-how a diff throws away. And because one visr shell can span many agent sessions, the transcripts connect: one session to the next, one fix to the next run, trajectories linking into a graph.

In v0.2.0, the transcript link shows up in your terminal status bar as soon as the session starts transcribing. When the shell exits, Visr prints a short summary and drops the transcript link on its own line, easy to copy, open, and share.

You run your agents, inspect output, fix bugs, retry a command, and exit with a transcript of the whole trajectory, not just the final outcome. From there it can seed a follow-up review, a skill, a runbook, an eval.

Your Next Agent's Trajectory

Try it on one real task. Run visr shell, work the way you normally would, and exit when you're done. Visr hands you the transcript link, and that transcript is the artifact worth carrying forward.

Share it with the next agent, the next teammate, the next workflow, so they don't have to guess what happened from the final diff alone. That's where this goes next, the same path the v0.1.0 changelog laid out: Agents run on terminal memories. Bottle yours.

Give it a try, and let us know what breaks. Thanks!

Previously

• v0.1.0 bottled terminal memories.