viberr 0.1.0

Lightweight local memory for vibe coding: prompts, edits, conflicts, decisions

Viberr

Lightweight local memory for vibe coding. Cursor hooks write prompts, edits, conflicts, and decisions to a single readable log. A small CLI helps you browse, search, and recap your sessions.

No server. No dashboard. No accounts.

What it solves

• Prompt amnesia — every prompt and response preview, timestamped
• File-change provenance — which prompt caused which edit (with diff)
• AI vs manual — edits you make yourself are tagged source: manual
• Conflicting AI edits — overlapping line ranges from different prompts
• Decision tracking — extracts "use X", "never Y" and flags contradictions
• Session recap — viberr recap → markdown summary of everything that happened
• Full-text search — viberr search "JWT" across prompts, diffs, and commands

Requirements

• Python 3.10+
• Git (a git repo is required — viberr init will tell you if one is missing)
• Cursor IDE with hooks enabled (Settings → Features → Hooks)
  • Minimum Cursor version: any build that ships hooks.json support (≥ 0.42)

Other editors (experimental): Adapter stubs for Claude Code, Aider, Cline, and Windsurf are included. Full support for these will be added in a future release.

Quick start

pip install viberr
cd your-git-repo
viberr init

Use Cursor in that workspace. Events append to .viberr/events.ndjson automatically.

What you'll see

viberr status

Events file: /your/project/.viberr/events.ndjson
Total events: 42
Active conversation: sess_a1b2c3
Latest work session: work_1 (3 conversation(s))
  [40] prompt evt_d4e5f6
  [41] edit evt_g7h8i9
  [42] shell evt_j0k1l2

viberr recap

# Viberr recap

**Scope:** work session `work_1` (3 conversations)

## Summary

- **Conversations:** 3
- **Prompts:** 12
- **Edits:** 28 (25 AI, 3 manual)
- **Shell commands:** 7
- **Files touched:** 9
- **Conflicts:** 1
- **Decisions:** 4
- **Decision contradictions:** 0

## Prompts

- `evt_abc` — refactor the auth module to use JWT
- `evt_def` — add refresh token support
...

## Decisions

- **use** JWT for authentication
- **prefer** httponly cookies for token storage

## Conflicts

- `src/auth.py`: prompt `evt_abc` overlaps `evt_def` at [[45, 60]]

Commands

Command	Description
viberr init	Git check, .viberr/, merge Cursor hooks, .gitignore
viberr status	Active session and recent events
viberr log	Print events (--session, --type, --tail, --since 1h)
viberr show <id>	Full event JSON
viberr search <query>	Search events (--regex, --type, --limit)
viberr recap	Markdown session summary
viberr conflicts	List conflict events
viberr decisions	List decision events
viberr tail	Follow the log live
viberr export	Export session (--format md|json|ndjson)
viberr doctor	Verify git, hooks, log file

How it works

flowchart LR
    Cursor[Cursor IDE] -->|hooks stdin/stdout| Hook[viberr.hook]
    Hook --> Log[".viberr/events.ndjson"]
    CLI[viberr CLI] --> Log
    Hook --> State[".viberr/state.json"]

See docs/schema.md for the full event format and docs/how-to-use.md for a complete walkthrough of every command.

Privacy

All data stays on your machine under .viberr/. viberr init adds .viberr/ to .gitignore.

Secret scrubbing is on by default. Common credential patterns (API keys, tokens, passwords) are redacted with [REDACTED] before reaching disk. Disable in .viberr/config.json:

{ "privacy": { "scrub_secrets": false } }

Even with scrubbing enabled, do not paste raw secrets into AI prompts — source-level caution is always better than automatic redaction.

Configuration

.viberr/config.json (created by viberr init):

{
  "decisions": {
    "enabled": true,
    "scan_responses": false
  },
  "work_session": {
    "idle_minutes": 30
  },
  "privacy": {
    "scrub_secrets": true
  }
}

Development

pip install -e ".[dev]"
pytest -q
ruff check viberr/ tests/

History

Earlier internal prototypes used a FastAPI daemon, SQLite, and a VS Code extension. v0.1 strips all of that back to a zero-dependency, hooks-only design that works with the single pip install viberr + viberr init workflow.

License

MIT