AI-powered Research Workflow Management CLI
Project description
OpenSeed
AI-powered research CLI — discover, read, and analyze academic papers with Claude.
What it does
- Smart search — finds relevant papers via Claude WebSearch, ranks by real citation counts (Semantic Scholar)
- Analysis pipeline — search → pick papers → auto-summarize + auto-tag → save to library in one flow
- AI summarization — structured summaries: key contributions, methodology, limitations, relevance score
- Experiment code gen — generate runnable PyTorch/sklearn experiment code from a paper
- Library management — ArXiv import, tags, reading status, deduplication
Search
Papers are ranked by real citation counts fetched from Semantic Scholar — not keyword matching.
Install
pip install -e ".[dev]"
openseed doctor # check environment
openseed setup # configure auth
Auth — any of these work:
export ANTHROPIC_API_KEY=sk-ant-... # Anthropic API key
# or log in via Claude CLI
claude setup-token # OAuth (openseed setup will detect it)
Core Commands
# Search & discover
openseed paper search "diffusion models" --count 20
openseed agent search "multi-agent systems" # deeper search with trend summary
openseed agent pipeline "ViT image classification" # search → select → analyze → save
# Manage your library
openseed paper add https://arxiv.org/abs/1706.03762
openseed paper list
openseed paper show <id>
# Analyze papers
openseed agent summarize <id> # English summary
openseed agent summarize <id> --cn # Chinese summary
openseed agent review <id> # peer review
openseed agent ask "What is RLHF?" # research Q&A
openseed agent codegen <id> # generate experiment code
License
MIT
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
openseed-0.2.0.tar.gz
(552.5 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
openseed-0.2.0-py3-none-any.whl
(25.4 kB
view details)
File details
Details for the file openseed-0.2.0.tar.gz.
File metadata
- Download URL: openseed-0.2.0.tar.gz
- Upload date:
- Size: 552.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
678cc72a4ba2b9ecc5e3cc8313a911f161797f15250bde68b3472a864c81f418
|
|
| MD5 |
1b55a0318a0a437ec2345286b7858904
|
|
| BLAKE2b-256 |
3a8718c94330f15db8880c6eb5032d5bf55a10d27f4cbb9f7c442f020716a467
|
File details
Details for the file openseed-0.2.0-py3-none-any.whl.
File metadata
- Download URL: openseed-0.2.0-py3-none-any.whl
- Upload date:
- Size: 25.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.11.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
871f90a62662f59c4420dee7d100af41b689ee68843ad3897bbb1bf951c4300b
|
|
| MD5 |
d074c085ceb48ca5d0f8a5deb08377e1
|
|
| BLAKE2b-256 |
134a77a8c1e4941149d17761a17f43b90aa87ca3d0ee777af867db89929d11a2
|