93
/ 100
Polished and well engineered. Punching above its star count.
An AI Assistant that’s easy to setup, does your work 24/7, knows your preferences and gets better over time.
Top fixes
Highest-impact changes first, ranked by point weight
- 1Tests18pt
Wire your tests to a documented command (e.g. a test script in your build config) so the suite is reproducible.
- 2CI/CD14pt
Add `pull_request:` to the workflow `on:` triggers.
- 3CI/CD14pt
Upload coverage to Codecov, Coveralls, or report it with `--coverage` flags.
- 4Reproducibility6pt
Add .github/dependabot.yml with at least one package-ecosystem entry so dependencies are updated automatically.
Working through the fixes? Let every push regrade itself.
The free GitHub App rescans this repo on every push and posts the grade as a commit check, so the score climbs without coming back to rescan by hand.
Scorecard
Every check, grouped by category and sorted worst-first
Documentation
100
README is present.
README documents how to install the project.
Licensed under MIT.
Contributing guide is detailed and thorough.
Engineering
85
Test files detected (assistant/__tests__).
Lockfile present (assistant/bun.lock). Installs are reproducible.
CI is configured (.github/workflows/build-chrome-extension.yaml).
Linter or formatter configured (assistant/eslint.config.mjs).
Issue or PR templates present.
Project health
100
Dependency manifest found (assistant/examples/plugins/echo/package.json).
Repository has a description.
Actively maintained (pushed within the last month).
.gitignore present.
Repository health signals
Activity, community, and responsiveness at scan time
Activity
- 3659 / 12596Commits (30d / 90d)
- 113Forks
- 130Releaseslatest 5mo ago
Community
- 87% - GoodCommunity health
- 2 bus factorauthors own >50% of commits
- 772Watchers
Responsiveness
- <1hMedian issue response
- <1hMedian PR merge time
- 123Open issues
Repository files38 root entries
- .claude
- .cursor
- .githooks
- .githubGood: CI is configured (.github/workflows/build-chrome-extension.yaml).Good: Issue or PR templates present.
- .vscode
- assets
- assistantGood: Test files detected (assistant/__tests__).Good: Linter or formatter configured (assistant/eslint.config.mjs).Good: Lockfile present (assistant/bun.lock). Installs are reproducible.Good: Environment pinned via assistant/Dockerfile.Good: Dependency manifest found (assistant/examples/plugins/echo/package.json).
- benchmarking
- cli
- clients
- credential-executor
- docs
- evals
- gateway
- meta
- packages
- plugins
- scripts
- skills
- .dockerignore
- .env.example
- .git-blame-ignore-revs
- .gitignoreGood: .gitignore present.
- .nvmrc
- .tool-versions
- AGENTS.md
- ARCHITECTURE.md
- bunfig.toml
- CODE_OF_CONDUCT.mdGood: Code of conduct present.
- CONSTITUTION.md
- CONTRIBUTING.mdGood: Contributing guide is detailed and thorough.Good: Contributing guide includes setup/install instructions.Good: Contributing guide describes code style expectations.Good: Contributing guide explains how to run tests.Good: Contributing guide describes the PR/review workflow.Good: Contributing guide includes code examples.
- GLOSSARY.md
- LICENSEGood: Licensed under MIT.
- README.mdGood: README is present.Good: README is well structured with multiple sections.Good: README includes screenshots or visuals. Great for first impressions.Good: README has code examples.Good: README links to a live demo or deployed app.Good: README includes status badges.Good: README documents how to install the project.Good: README documents how to run the project.
- SECURITY.mdGood: Security policy present.
- setup.sh
- socket.yml
- test-preload.ts
Add this badge to your README
It updates automatically each time the repo is re-graded.
[](https://www.repo-grade.com/report/vellum-ai/vellum-assistant)