Persistent memory across every session

What gets captured

3-tier retention model

What to capture, where to store it, how long to keep it.

Layer 1 — User prompts

The Sprintra plugin hooks Claude Code's UserPromptSubmit event. Every message you send is captured to your private timeline, fire-and-forget — never blocks your prompt from reaching Claude. Per-user attribution by default.

Every next session's briefing surfaces a “Recent asks” line for the last 3 prompts in the past 24 hours. Older prompts are searchable through the dashboard and the agent's search tools.

Layer 2 — Session digests with pin flag

When a Claude Code session ends, the agent writes a structured digest before Stop fires: what was discussed, key decisions, open questions, user pushback, pending asks, links to artifacts created. Cost: zero LLM — the model is already running and writes its own summary as the final tool call. No background compression service, no extra round-trip.

By default, digests rotate after 30 days. Pin a digest to preserve a strategic discussion forever. The next session's briefing surfaces pinned digests preferentially under “Last conversation”.

Layer 3 — Local transcript search

Claude Code already writes the raw transcript for every session to disk. Sprintra doesn't copy those bytes — it indexes them in place. Full-text keyword search across every session you've ever had on this machine, returning results in well under 100 ms.

# One-time: scan your session history and build the index
sprintra transcript reindex

# List recent transcripts
sprintra transcript list --since 2026-04-01

# Keyword search across every session
sprintra transcript search "auth bug fix"

# Open the actual transcript file (no copy made)
sprintra transcript view <session-id>

# Disk usage / oldest / newest / retention
sprintra transcript status

# Manual prune (default cutoff: 90 days)
sprintra transcript prune --before 2026-01-01 --dry-run

Privacy and multi-user behavior

Three developers in the same repo, same Sprintra project. Each user's prompts and digests are private to them — the others cannot read them by default. Cross-user reads require admin or owner role (audit use case). The shared artifacts — features, decisions, notes, comments, work sessions — remain visible at the project level just like today.

Raw transcripts never sync to the cloud. They stay on the machine that produced them. Cross-device “what was I doing yesterday” works through the digest (a few KB) which IS in the cloud. Need a specific transcript on another device? Run sprintra transcript share <id> --to-cloud for an explicit, single-transcript opt-in upload.

Three opt-out flags in your Sprintra config:

# ~/.sprintra/config.json

{
  "capture_user_prompts":     false,   // disables prompt capture
  "capture_session_digests":  false,   // disables session digests
  "capture_transcript_index": false    // disables local indexing
}

To delete past data: purge cloud entries via the dashboard, or run sprintra transcript prune --before DATE for local.

Quickstart

# 1. Install the latest plugin
# Inside Claude Code:
/plugin marketplace add Sprintra-io/sprintra-mcp
/plugin install sprintra@sprintra

# 2. Install the CLI (with transcript subcommand)
npm install -g @sprintra/cli@latest

# 3. One-time backfill: index your existing transcripts
sprintra transcript reindex

# 4. Verify capture is live: open a fresh Claude Code session
# and check sprintra transcript status afterward.

Configuration reference