Recensa

Recensa

  See what your agents actually did.
  A self-hosted viewer for your Claude Code session transcripts — read, search,
  replay, and audit every session you have ever run. Your transcripts stay on your
  machine; nothing is uploaded anywhere.

  = 22">

  Quick start ·
  Tour ·
  Why ·
  Themes ·
  Security ·
  Architecture ·
  Contributing

Every Claude Code session you run is written to disk as raw JSONL under
~/.claude/projects/ — the full conversation, every tool call, the model's thinking,
every subagent it spawned. Then it just sits there, unreadable. Want to know how you
fixed that bug last month? What that 40-minute agent run actually changed? Which of
your prompts sent it down a dead end? Good luck grepping.

Recensa indexes those transcripts into a local SQLite database and serves a
three-pane reader at http://localhost:7788. Reading never modifies your
transcripts, and the index is a disposable cache you can rebuild at any time.

Quick start

You need Docker (Docker Desktop on Windows/macOS; Docker Engine with Compose v2 on
Linux) and a ~/.claude directory with some sessions in it. Rootless Docker and
Podman work too — uid alignment is automatic. Give the container ~1 GB of memory
headroom for the first big index.

Try it — run the prebuilt image straight from Docker Hub:

On Linux, ~/.claude/projects is created owner-only (700/600) by the host CLI, so the
container needs a matching uid/gid to read it — it detects this on its own from the
mount, no flags required (override with -e PUID=... -e PGID=... if the mount's owner
isn't the account you want). The trailing :z relabels the mount for SELinux-enforcing
hosts (RHEL/Fedora/CentOS, Podman); it's a no-op everywhere else, so it's safe to
always include.

Or with Compose, using the prebuilt image:

Or…