Releases: ZaneChen76/papyrus
Releases · ZaneChen76/papyrus
Release list
v0.2.1 — OpenClaw Platform Adapter
v0.2.1 — OpenClaw Platform Adapter
New
- OpenClaw platform adapter:
platforms/openclaw/papyrus-config.yaml- 9-step complete pipeline definition
- Triggers, dependencies, environment variables documented
- All design rules encoded for agent consumption
- OpenClaw is now a first-class platform alongside Claude Code, Codex, Hermes, and Open Code
All 5 Supported Platforms
| Platform | Adapter |
|---|---|
| OpenClaw | platforms/openclaw/papyrus-config.yaml |
| Claude Code | platforms/claude-code/papyrus-skill.md |
| OpenAI Codex | platforms/codex/papyrus-tool.yaml |
| Hermes | platforms/hermes/papyrus-tool.py |
| Google Open Code | platforms/open-code/papyrus-config.yaml |
github.com/ZaneChen76/papyrus
v0.2.0 — Multi-Platform Agent Support
v0.2.0 — Multi-Platform Agent Support
Cross-Platform Agent Adapters
Papyrus now works with Claude Code, OpenAI Codex, Hermes, and Google Open Code.
All four platforms use the same unified CLI with four commands: fetch, figures, formulas, pdf.
What is Papyrus
Turn arXiv papers into bilingual, deeply annotated, professionally typeset PDFs.
Original English + Chinese translation + web-researched expert commentary.
16 files | MIT License
github.com/ZaneChen76/papyrus
v0.1.1 — Vector PDF Figure Rasterization + NSA Paper Validation
v0.1.1 — Vector PDF Figure Rasterization
New
- render_figures.sh: PyMuPDF-based PDF figure → PNG conversion
- Auto-detects raster vs vector PDF figures
- Vector PDFs rasterized at 200 DPI (no external tools needed)
- Resizes oversized images to 1200px max width
Validated
- Successfully tested on NSA paper (ACL 2025 Best Paper, arXiv 2502.11089)
- Produced 16-page annotated deep-read with 8 figures + 8 formulas
- All 8 PDF figures correctly converted (4 were vector-only)
Documentation
- SOP.md: Phase 2.5 Figure Rasterization step added
- SKILL.md: render_figures.sh added to directory structure
- Known Limitations updated: vector PDF + PyMuPDF note
Commentary Note
- Current commentary depth is adequate but could be richer
- Future version will strengthen web-research integration for deeper insights