llm-for-zotero vs MiroThinker
MiroThinker is much bigger: 8.4k stars against 3.0k. Over the days we have tracked them llm-for-zotero moved +51.8% and MiroThinker +1.3%, so llm-for-zotero is growing faster right now.
llm-for-zotero leads on context depth and customization and model freedom. MiroThinker does not take any axis by a clear margin.
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
Deep Zotero-native integration that provides grounded, citation-linked paper chat and library-wide agent actions (reads, writes, tagging, notes) not offered by generic agents.
- Stars
- 3.0k
- Tracked growth
- +51.8%
- Maturity
- ●●●●●
- Last commit
- 6h ago
- Language
- TypeScript
- License
- AGPL-3.0
- Cost to run
- Your API key or local models
Provides open-source deep research agents with extremely long (256K) context windows and very high tool-call budgets, enabling long‑horizon, verifiable multi-step research workflows.
- Stars
- 8.4k
- Tracked growth
- +1.3%
- Maturity
- ●●●●●
- Last commit
- 69d ago
- Language
- Python
- License
- Apache-2.0
- Cost to run
- Free; self-host models or use HuggingFace
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 | llm-for-zotero | MiroThinker |
|---|---|---|
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-library access | ●●●●● Diff only |
Noise control How it keeps output volume down — severity thresholds, deduplication, incremental runs over new commits only. | ●●●●● Citation gating & confirmations | ●●●●● Trace collection |
Customization How far it bends to your team: custom rules, prompts, style guides, per-path config. | ●●●●● Custom skills & settings | ●●●●● Configurable workflows |
Privacy Whether your code stays on your own infrastructure: fully local, self-hostable, or cloud API only. | ●●●●● Local model support | ●●●●● Fully local |
Model freedom Whether you can point it at any provider, or it is wired to one. | ●●●●● Bring-your-own model/key | ●●●●● HuggingFace weights |
Setup ease What it takes to get a first useful run out of it. | ●●●●● Easy install + API key | ●●●●● Online demo |
Which one to pick
Pick llm-for-zotero if…
Zotero-native — pick this when you want a research assistant tightly integrated with your local Zotero library for grounded citations, file-based notes, and library-wide agent workflows.
- Context depth: Whole-library access (5/5 against 1/5)
- Customization: Custom skills & settings (5/5 against 3/5)
- Model freedom: Bring-your-own model/key (5/5 against 3/5)
Pick MiroThinker if…
Long‑context research — choose MiroThinker when you need an open-source agent with 256K context and high tool‑call capacity for deep, verifiable multi‑step research tasks.
What people want from each one
yilewang/llm-for-zotero
Questions people ask
Is llm-for-zotero better than MiroThinker?
llm-for-zotero leads on context depth and customization and model freedom. MiroThinker does not take any axis by a clear margin. llm-for-zotero is worth picking when zotero-native — pick this when you want a research assistant tightly integrated with your local Zotero library for grounded citations, file-based notes, and library-wide agent workflows.
Which of llm-for-zotero and MiroThinker keeps my code private?
llm-for-zotero: Local model support (5/5). MiroThinker: Fully local (5/5).
What does each one cost to run?
llm-for-zotero: Your API key or local models. MiroThinker: Free; self-host models or use HuggingFace.
Full profiles: yilewang/llm-for-zotero and MiroMindAI/MiroThinker. Everything else in Research agents.