vardoger

A cross-platform plugin for AI coding assistants (Cursor, Claude Code, OpenAI Codex, OpenClaw, GitHub Copilot CLI, Windsurf, Cline) that reads your conversation history, extracts behavioral patterns, and generates personalized system prompt additions — making the assistant progressively better suited to how you work.

All processing happens locally. No data ever leaves your machine.

Prerequisites

Python 3.11+

pipx

Recommended for installing vardoger as an isolated CLI tool. Full instructions at pipx.pypa.io/stable/installation.

Quick Start

pipx install vardoger
vardoger setup cursor        # or claude-code, codex, openclaw, copilot, windsurf, cline

Then tell your assistant: "Personalize my assistant."

Looking for the in-app plugin listings? Track review status for each marketplace (PyPI, Cursor, Claude Code, Codex, Copilot CLI, Windsurf, Cline, ClawHub) in MARKETPLACE_STATUS.md. Vardoger is currently live on PyPI, the Cursor Marketplace, the Claude Code community catalog, self-hosted Codex and Copilot marketplaces, ClawHub, McpMux, and the Official MCP Registry.

Previous pre-releases. pipx install vardoger now resolves to the stable 0.3.2 release. The beta install paths below stay here for anyone still pinning an earlier release; new installs should not need them.

bash

Copy

# opt into future pre-releases (0.2.0bN, etc.):
pipx install --pip-args="--pre" vardoger
# or pin an older pre-release:
pipx install vardoger==0.1.0b3
# or run without installing:
uvx vardoger --help

CLI Commands

How It Works

1. Read — Parses conversation history already stored on disk by each platform
2. Analyze — The host AI model identifies patterns in your communication style, tech stack, workflow, and preferences
3. Generate — Produces a system prompt addition tailored to you
4. Deliver — Writes the addition to the platform's native config (.cursor/rules/, .claude/rules/, AGENTS.md, etc.)

First run vs. incremental runs. By default vardoger does not apply a time window — the first run reads your full local history (that is when the signal is richest and a windowed default would silently drop older sessions you never get a second chance to feed in). After that, a per-conversation checkpoint store at ~/.vardoger/state.json ensures every subsequent run only reprocesses new or changed conversations, so refreshes stay fast. If you have very large local history and want to cap the first-run cost, pass --since DAYS (e.g. vardoger prepare --platform cursor --since 90); use --full to force a full re-crawl that bypasses the checkpoint.

Supported Platforms

Development

Requires uv (Python package manager):

git clone https://github.com/dstrupl/vardoger.git
cd vardoger
uv sync
.venv/bin/vardoger --help

Project Layout

src/vardoger/          # shared core — history reading, analysis, prompt generation
.agents/plugins/       # repository-level Codex marketplace catalog
plugins/_shared/       # shared analysis/personalization skill authored once
plugins/cursor/        # Cursor MCP server config, install script
plugins/claude-code/   # Claude Code plugin manifest, skills
plugins/codex/         # Codex plugin manifest, skills
plugins/openclaw/      # OpenClaw skill
plugins/copilot/       # GitHub Copilot CLI plugin manifest, skills
plugins/windsurf/      # Windsurf install snippet and rules delivery
plugins/cline/         # Cline MCP-marketplace manifest + llms-install guide
tests/                 # all tests, mirroring src/ structure

• Platform-agnostic logic lives under src/vardoger/.
• Platform-specific integration (manifests, skills, install scripts) lives under plugins/<platform>/.
• Tests live in tests/, mirroring the source tree.

See AGENTS.md for full coding standards and quality checks.

Quality gates

CI enforces a combined quality bar on every push and pull request:

• ruff check / ruff format --check — lint (incl. complexity, pylint, return, pathlib, tryceratops rules) and formatting.
• mypy src/ — strict type checking.
• pytest --cov=vardoger --cov-fail-under=80 — tests across Python 3.11–3.13 with a combined 80% coverage floor.
• A parallel security job runs bandit -r src/ and pip-audit --skip-editable to catch common code smells and dependency CVEs.

Run the full bundle locally before pushing:

uv run ruff check . && uv run ruff format --check . && uv run mypy src/ && uv run pytest --cov=vardoger --cov-fail-under=80

Contributing

Contributions are welcome. Short version:

1. Fork dstrupl/vardoger on GitHub and clone your fork.
2. uv sync and create a topic branch.
3. Make your changes with tests and run the quality-gate one-liner above.
4. Push to your fork and open a PR against main.

CI (test on Python 3.11/3.12/3.13 plus a security job) will run automatically on the PR. First-time contributors may need a maintainer to click Approve and run before the first workflow execution.

See CONTRIBUTING.md for the full walkthrough and AGENTS.md for coding standards and commit-message conventions.

Releasing to PyPI

CI runs automatically on every push and PR (lint, type check, tests across Python 3.11–3.13). To publish a new version:

1. Bump the package, generated setup manifests, platform manifests, and registry metadata together; close the matching section in CHANGELOG.md.
2. Run the complete quality, security, plugin-validation, and build checks.
3. Commit and push to main, then wait for all required checks.
4. Create an annotated vX.Y.Z tag and publish the matching GitHub release.

The publish.yml workflow builds the package and uploads it to PyPI via trusted publishers (no API tokens needed). Once complete, pipx install vardoger will pull the new version.

Status

Public beta. Version 0.3.2 is published on PyPI and actively maintained. See MARKETPLACE_STATUS.md for live listings and the remaining official-directory submissions. See MANUAL_SUBMISSION_RUNBOOK.md for the owner-only submission, review, and publication steps. See PRD.md for the full product requirements document.

Privacy and security

• PRIVACY.md — what vardoger reads, writes, and (importantly) does not send anywhere.
• SECURITY.md — how to report a vulnerability privately.

License

Licensed under the Apache License, Version 2.0. See also the public Privacy Policy and Terms of Use.