k-dense-byok vs paperjury

The two are close in size: 1.1k stars for k-dense-byok, 1.1k for paperjury. Over the days we have tracked them k-dense-byok moved +23.5% and paperjury +31%, so paperjury is growing faster right now.

They split the axes: k-dense-byok leads on privacy and model freedom and setup ease, paperjury on noise control.

Stars and commit dates come from our own daily tracking. The six axes are read off each project's documentation by our review pipeline, so they describe what a project says about itself, not what we measured in its code.

Where they stand today

A local-first, bring-your-own-keys AI research assistant that runs on your computer and bundles domain-specific scientific skills, workflows, and a living lab notebook.

Stars
1.1k
Tracked growth
+23.5%
Maturity
Last commit
13h ago
Language
TypeScript
License
MIT
Cost to run
Your API key (pay-per-use) or free local models

Bundles a bounded, audit-ready review→decide→patch→recheck loop with ledgered issues and edit-safety safeguards, exposed as a Claude Code skill.

Stars
1.1k
Tracked growth
+31%
Maturity
Last commit
22d ago
Language
JavaScript
License
MIT
Cost to run
Runs in your Claude session — model usage billed by the provider
0%+31%45 tracked days
K-Dense-AI/k-dense-byoku7079256/paperjury

Six axes, head to head

Each axis runs 0 to 5. The label under a score is what that project's own docs claim, not a category average.

Axisk-dense-byokpaperjury
Context depth
How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository.
Whole-project access
Whole-repo analysis
Noise control
How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only.
Clarifying prompts & review
Severity gating & dedup
Customization
How far it bends to your team: custom rules, prompts, style guides, per-path config.
Configurable skills & presets
Modes & personas
Privacy
Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only.
Fully local optional
Cloud LLM via session
Model freedom
Whether you can point it at any provider, or it is wired to one.
BYOK + local models
Claude-first (fixed)
Setup ease
What it takes to get a first useful run out of it.
Quick local start
Plugin install + session

Which one to pick

Pick k-dense-byok if…

Privacy-first — run a full scientific assistant locally or use your own OpenRouter key while keeping projects and data on your machine, with many prebuilt scientific skills and workflows.

  • Privacy: Fully local optional (5/5 against 3/5)
  • Model freedom: BYOK + local models (5/5 against 3/5)
  • Setup ease: Quick local start (5/5 against 3/5)
Runs in cli, web-app. Works with byok, local-ollama.

Pick paperjury if…

Audit-ready review loop — pick PaperJury when you want a pre-submission, multi-round reviewer simulation that produces minimal, author-confirmed LaTeX patches and deterministic compile/compliance checks.

  • Noise control: Severity gating & dedup (5/5 against 3/5)
Runs in coding-agent-plugin, cli. Works with anthropic.

What people want from each one

Questions people ask

Is k-dense-byok better than paperjury?

They split the axes: k-dense-byok leads on privacy and model freedom and setup ease, paperjury on noise control. k-dense-byok is worth picking when privacy-first — run a full scientific assistant locally or use your own OpenRouter key while keeping projects and data on your machine, with many prebuilt scientific skills and workflows.

Which of k-dense-byok and paperjury keeps my code private?

k-dense-byok: Fully local optional (5/5). paperjury: Cloud LLM via session (3/5).

What does each one cost to run?

k-dense-byok: Your API key (pay-per-use) or free local models. paperjury: Runs in your Claude session — model usage billed by the provider.

Full profiles: K-Dense-AI/k-dense-byok and u7079256/paperjury. Everything else in Research agents.