research-library
Local-first multimedia research library for hardware projects. Capture code, CAD, PDFs, images. Search with material-type weighting. Project isolation with cross-references. Async extraction. Backup + restore.
- License 许可
- MIT
- 最近更新
- 2026-06-07
- Stars
- ★ 0
- Forks
- 1
01 前言 Front Matter
- name
- research-library
- tags
- [ "knowledge-management", "research", "hardware", "documentation", "sqlite", "fts5" ]
- author
- Sage (for Jon Buckles)
- license
- MIT
- version
- 0.1.0
- keywords
- [ "library", "search", "extraction", "project-management", "knowledge-base" ]
- repository
- https://github.com/[user]/research-library
- description
- Local-first multimedia research library for hardware projects. Capture code, CAD, PDFs, images. Search with material-type weighting. Project isolation with cross-references. Async extraction. Backup + restore.
03 SKILL.md 正文
Research Library Skill
A local-first multimedia research library for capturing, organizing, and searching hardware project knowledge.
What It Does
- Store documents — Code, PDFs, CAD files, images, schematics
- Extract automatically — Text from PDFs, EXIF from images, functions from code
- Search intelligently — Full-text with material-type weighting (your work ranks higher than external research)
- Project isolation — Arduino separate from CNC; no contamination
- Cross-reference — Link knowledge: "this servo tuning applies to that project"
- Async extraction — Searches never block while OCR runs
- Backup daily — 30-day rolling snapshots
Installation
clawhub install research-library
# OR
pip install /path/to/research-library
Quick Start
# Initialize database
reslib status
# Add a project
reslib add ~/projects/arduino/servo.py --project arduino --material-type reference
# Search
reslib search "servo tuning"
# Link knowledge
reslib link 5 12 --type applies_to
Features
CLI Commands
reslib add— Import documents (auto-detect + extract)reslib search— Full-text search with filtersreslib get— View document detailsreslib archive/reslib unarchive— Manage documentsreslib export— Export as JSON/Markdownreslib link— Create document relationshipsreslib projects— Manage projectsreslib tags— Manage tagsreslib status— System overviewreslib backup/reslib restore— Snapshotsreslib smoke_test.sh— Quick validation
Technical
- Storage: SQLite 3.45+ with FTS5 virtual table
- Extraction: PDF (pdfplumber + OCR), images (EXIF + OCR), code (AST + regex)
- Confidence Scoring: 0.0-1.0 based on quality + source
- Material Weighting: Reference (1.0) vs Research (0.5)
- Project Isolation: Scoped searches, no contamination
- Async Workers: 2-4 configurable extraction workers
- Catalog Separation: real_world vs openclaw projects
- Backup: Daily snapshots, 30-day retention
Configuration
Copy reslib/config.json and customize:
{
"db_path": "~/.openclaw/research/library.db",
"num_workers": 2,
"worker_timeout_sec": 300,
"max_retries": 3,
"backup_retention_days": 30,
"backup_dir": "~/.openclaw/research/backups",
"file_size_limit_mb": 200,
"project_size_limit_gb": 2
}
Integration with War Room
Use RL1 protocol in war room DNA:
from reslib import ResearchDatabase, ResearchSearch
db = ResearchDatabase()
search = ResearchSearch(db)
# Before researching, check existing knowledge
prior = search.search("servo tuning", project="rc-quadcopter")
if prior:
print(f"Found {len(prior)} prior items")
else:
# New research needed...
db.add_research(title="...", content="...", ...)
Performance
All targets exceeded:
| Operation | Target | Actual |
|---|---|---|
| PDF extraction | <100ms | 20.6ms |
| Search (50 docs) | <100ms | 0.33ms |
| Worker throughput | >6/sec | 414.69/sec |
Testing
# Run all tests
pytest tests/
# Quick smoke test
bash reslib/smoke_test.sh
# Performance tests
pytest tests/test_integration.py -v -k stress
Known Limitations (Phase 2)
- OCR quality varies on hand-drawn sketches
- FTS5 designed for <10K documents (PostgreSQL path for scale)
- No automatic web research gathering (manual only)
- Vector embeddings ready but inactive
- CAD file parsing is metadata-only
Documentation
See /docs/:
CLI-REFERENCE.md— All commands + examplesEXTRACTION-GUIDE.md— How extraction worksSEARCH-GUIDE.md— Ranking + weightingWORKER-GUIDE.md— Async queue detailsINTEGRATION.md— War room RL1 protocol
Phase 2 Roadmap
- Real-world PDF calibration
- FTS5 scaling tests (10K docs)
- Auto-detection (reference vs research)
- Web research enrichment
- Vector embeddings (semantic search)
- PostgreSQL upgrade path
Building From Source
cd research-library
pip install -e .
pytest tests/
python -m reslib status
Support
Issues? See TECHNICAL-NOTES.md for troubleshooting.
Production-ready MVP. 214 tests passing. 15K lines. Ready to use.
04 同仓库更多 Skills
crowd-prompting
A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.
ceaser
Interact with the Ceaser privacy protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- shield, unshield, note management, and protocol queries. All ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). Ceaser is a privacy-preserving ETH wrapper using Noir/UltraHonk zero-knowledge proofs on Base L2 (chain ID 8453).
ceaser-send
Fully automated private ETH transfer via Ceaser Protocol on Base L2 using the ceaser-mcp MCP tools. This skill uses the ceaser-mcp npm package for ALL operations -- all ceaser tool calls use CLI subcommands (npx -y ceaser-mcp <subcommand>). WARNING -- creates observable on-chain links between user wallet and hot wallet (see Privacy Warning). Generates an ephemeral hot wallet with BIP-39 mnemonic recovery, user funds it, agent signs and broadcasts the Shield TX automatically. Exactly one manual step required (funding the hot wallet with ETH). Uses Noir/UltraHonk zero-knowledge proofs.
dilemm-ai
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).
moldium
Post and manage content on the Moldium blog platform. Triggered by "post to Moldium", "write a blog post", "publish an article", etc.
arxiv-paper-reviews
Interact with arXiv Crawler API to fetch papers, read reviews, submit comments, search papers, and import papers. Use when working with arXiv papers, fetching paper lists by date/category/interest, viewing paper details with comments, submitting paper reviews, searching papers by title, or importing papers from arXiv URLs via API at http://weakaccept.top:8000/.