Deep-Research-skills vs ScienceClaw
Deep-Research-skills is much bigger: 2.4k stars against 1.0k. Over the days we have tracked them Deep-Research-skills moved +38.7% and ScienceClaw +16.9%, so Deep-Research-skills is growing faster right now.
They split the axes: Deep-Research-skills leads on model freedom, ScienceClaw on noise control and customization and privacy and setup ease.
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
Provides a structured two-phase (outline then deep investigation) human-in-the-loop research workflow packaged specifically as skills for Claude Code / OpenCode / Codex, including parallel web research modules and report generation.
- Stars
- 2.4k
- Tracked growth
- +38.7%
- Maturity
- ●●●●●
- Last commit
- 58d ago
- Language
- Python
- License
- MIT
- Cost to run
- Depends on model provider
Self-evolving scientific skills plus a hard research protocol (SCIENCE.md) that enforces evidence-only citations and long-running, persistent research memory.
- Stars
- 1.0k
- Tracked growth
- +16.9%
- Maturity
- ●●●●●
- Last commit
- 3d ago
- Language
- TypeScript
- License
- MIT
- Cost to run
- Free, self-host
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.
| Axis | Deep-Research-skills | ScienceClaw |
|---|---|---|
Context depth How much of your codebase it sees before it answers: the open diff, the diff plus related files, or the whole repository. | ●●●●● Web-only | ●●●●● Session-limited |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Human-in-the-loop | ●●●●● Protocol enforced |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Config file options | ●●●●● Extensive config & plugins |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Cloud APIs | ●●●●● Fully local |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Specific providers | ●●●●● Single fixed provider |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Manual install steps | ●●●●● One-click setup |
Which one to pick
Pick Deep-Research-skills if…
Claude/OpenCode/Codex integration — choose this when you run those agent clients and want an extensible, human-in-the-loop two-phase workflow (outline + deep web research) that outputs organized markdown reports.
- Model freedom: Specific providers (3/5 against 1/5)
Pick ScienceClaw if…
Zero-hallucination — pick ScienceClaw when you need a research assistant that enforces verified citations, supports long-duration sessions, and adapts to your field over time.
- Noise control: Protocol enforced (5/5 against 3/5)
- Customization: Extensive config & plugins (5/5 against 3/5)
- Privacy: Fully local (5/5 against 3/5)
- Setup ease: One-click setup (5/5 against 3/5)
What people want from each one
Weizhena/Deep-Research-skills
Questions people ask
Is Deep-Research-skills better than ScienceClaw?
They split the axes: Deep-Research-skills leads on model freedom, ScienceClaw on noise control and customization and privacy and setup ease. Deep-Research-skills is worth picking when claude/OpenCode/Codex integration — choose this when you run those agent clients and want an extensible, human-in-the-loop two-phase workflow (outline + deep web research) that outputs organized markdown reports.
Which of Deep-Research-skills and ScienceClaw keeps my code private?
Deep-Research-skills: Cloud APIs (3/5). ScienceClaw: Fully local (5/5).
What does each one cost to run?
Deep-Research-skills: Depends on model provider. ScienceClaw: Free, self-host.
Full profiles: Weizhena/Deep-Research-skills and beita6969/ScienceClaw. Everything else in Research agents.