-
Notifications
You must be signed in to change notification settings - Fork 11
feat: generated llms.txt for AI agents #226
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
Zethson
wants to merge
1
commit into
main
Choose a base branch
from
llms-txt
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+65
−3
Open
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,54 @@ | ||
| # scverse | ||
|
|
||
| > scverse is a consortium of foundational, interoperable open-source tools (mostly Python) for single-cell and spatial omics data analysis in the life sciences. | ||
|
|
||
| scverse packages share common data structures (AnnData, MuData, SpatialData) to guarantee interoperability across the ecosystem. | ||
| Most package documentation lives on dedicated external sites, linked below. | ||
| This site (scverse.org) hosts the package index, tutorials, project governance, events, and the blog. | ||
|
|
||
| ## Core packages | ||
|
|
||
| Foundational packages maintained by the scverse core team. | ||
| {{ range .Params.packages }} | ||
| - [{{ .name }}]({{ .url }}): {{ .description }} | ||
| {{- end }} | ||
|
|
||
| ## More packages | ||
|
|
||
| Other major packages developed within the scverse GitHub organization. | ||
|
|
||
| - [gget](https://scverse.org/gget/): Efficient querying of genomic reference databases. | ||
| - [PyDESeq2](https://pydeseq2.readthedocs.io/en/stable/): Python implementation of the DESeq2 pipeline for bulk RNA-seq differential expression analysis. | ||
| - [CellRank](https://cellrank.readthedocs.io/en/latest/): Cell fate and dynamics from multi-view single-cell data. | ||
| - [anndataR](https://anndataR.scverse.org): AnnData interoperability in R. | ||
| - [spatialdata-io](https://spatialdata.scverse.org/projects/io/en/latest/): Readers and converters for spatial omics formats into SpatialData. | ||
| - [napari-spatialdata](https://spatialdata.scverse.org/projects/napari/en/latest/): Interactive napari viewer for SpatialData. | ||
| - [spatialdata-plot](https://spatialdata.scverse.org/projects/plot/en/latest/): Static plotting for the SpatialData framework. | ||
| - [annbatch](https://annbatch.readthedocs.io): Minibatch loading for on-disk AnnData files, co-developed with Lamin Labs. | ||
| - [pytometry](https://pytometry.readthedocs.io/en/latest/): Flow and mass cytometry analytics. | ||
| - [rustar-aligner](https://scverse.org/rustar-aligner/): Rust implementation of the STAR RNA-seq aligner. | ||
| - [anndata-rs](https://scverse.org/anndata-rs/): Rust implementation of AnnData. | ||
|
|
||
| ## Learn | ||
| - [Tutorials]({{ absURL "learn/" }}): Getting-started tutorials for the core packages. | ||
| - [Package index]({{ absURL "packages/" }}): All core and ecosystem packages with links to docs, source, and distribution. | ||
| - [Single-cell best practices](https://www.sc-best-practices.org/): Community book on best practices for single-cell analysis. | ||
|
|
||
| ## About | ||
| - [Mission]({{ absURL "about/mission/" }}): What scverse is and why it exists. | ||
| - [Roles and governance]({{ absURL "about/roles/" }}): Core team, steering council, and how the project is run. | ||
| - [Code of conduct]({{ absURL "about/code_of_conduct/" }}): Community standards for participation. | ||
| - [AI policy]({{ absURL "about/ai_policy/" }}): Expectations for contributing AI-assisted code to scverse projects. | ||
|
|
||
| ## Community | ||
| - [GitHub](https://github.com/scverse): Source code for all scverse packages. | ||
| - [Discourse](https://discourse.scverse.org/): User forum for questions and discussion. | ||
| - [Zulip](https://scverse.zulipchat.com/): Developer chat. | ||
| - [Ecosystem packages](https://github.com/scverse/ecosystem-packages): Community packages built on scverse standards, and inclusion criteria. | ||
| - [cookiecutter-scverse](https://cookiecutter-scverse-instance.readthedocs.io/en/latest/): Project template for creating new scverse-compatible packages. | ||
|
|
||
| ## Optional | ||
| - [Blog]({{ absURL "blog/" }}): Announcements and release notes. | ||
| - [Events]({{ absURL "events/" }}): Conferences and hackathons. | ||
| - [People]({{ absURL "people/" }}): Contributors and core team. | ||
| - [YouTube](https://www.youtube.com/channel/UCpsvsIAW3R5OdftJKKuLNMA): Recorded talks and workshops. |
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Currently the core package list depends on code (I guess javascript of similar) execution to get rendered in the txt file. Do we know if an agent will see the rendered list at runtime, or just the:
This is important because if it does not render properly the agent will be quite lost.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hmm, I guess agents that look at the code will see this. Only if they access the rendered website, they'll see what we expect. So hardcoding this would be the right thing to do? Or will agents simply attempt to look at these parameters to figure out what should be there? Sure - less efficient but then we don't need to hardcode things.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
So I've seen that it depends a lot on the agent capability. High-end models (such as opus or fable) they will go through the trouble of jumping to other pages and following links if they are provided, while lower-end models (haiku, sonnet) they'll "speed-run" and not bother visiting other pages, so I would say it is safer to hardcode this just in case.