Skip to content

Enhancing llm.txt file#2142

Draft
sandijean90 wants to merge 3 commits intomainfrom
llm-txt-file
Draft

Enhancing llm.txt file#2142
sandijean90 wants to merge 3 commits intomainfrom
llm-txt-file

Conversation

@sandijean90
Copy link
Contributor

@sandijean90 sandijean90 commented Feb 24, 2026

Summary

ehances the llm.txt file by adding action oriented page definitions, adds missing pages, structures the file into sections

Linked Issues

closes #2101

Documentation

  • No Docs Needed:

If this PR adds new feature or changes existing. Make sure documentation is adjusted accordingly. If the docs is not needed, please explain why.

Mintlify

0 threads from 0 users in Mintlify

  • No unresolved comments

Open in Mintlify Editor

Signed-off-by: Sandi Besen <sandibesen@gmail.com>
@gemini-code-assist
Copy link
Contributor

Summary of Changes

Hello @sandijean90, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request significantly enhances the llm.txt file, which functions as a machine-readable index for the Agent Stack platform's documentation. The changes aim to improve the discoverability and usability of the documentation by organizing content into clear, thematic sections, adding new and previously unlisted pages, and providing concise, action-oriented descriptions for each resource. This update makes it easier for AI agents and developers to navigate and utilize Agent Stack's features.

Highlights

  • Documentation Structure: Structured the llm.txt file into logical sections such as 'Core Resources', 'Deploying Agents', and 'Agent Stack Services & Extensions' for improved navigation and clarity.
  • Action-Oriented Page Definitions: Added comprehensive, action-oriented descriptions for each documentation link, guiding users on specific functionalities and how to interact with Agent Stack.
  • Missing Pages Included: Incorporated previously missing documentation pages to provide a more complete and exhaustive resource index for the Agent Stack platform.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog
  • docs/llm.txt
    • Added a new documentation index file for the Agent Stack platform.
    • Organized documentation links into distinct sections including 'Core Resources', 'Deploying Agents to Agent Stack', 'Agent Stack Services & Extensions', 'Out of the box (Native) UI Extensions', 'Custom UI Development', 'Self-Hosting Agent Stack', and 'Community'.
    • Included action-oriented descriptions for each link to clearly define the purpose and content of the linked documentation page.
Activity
  • No human activity has occurred on this pull request yet.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request adds a new llm.txt file which serves as a machine-readable index for the Agent Stack documentation. The file is well-structured and provides a comprehensive list of resources. I've found a few areas for improvement regarding duplicate content and a minor typo. Please see my detailed comments. Also, there's a small typo in the pull request title ('Ehancing' should be 'Enhancing').

Signed-off-by: Sandi Besen <sandibesen@gmail.com>
@sandijean90 sandijean90 changed the title Ehancing llm.txt file Enhancing llm.txt file Feb 24, 2026
Signed-off-by: Sandi Besen <sandibesen@gmail.com>
@sandijean90
Copy link
Contributor Author

@tomkis please review but do not merge yet


## Deploying Agents to Agent Stack

- [Build New Agents](https://agentstack.beeai.dev/stable/deploy-agents/building-agents): Create a new agent using the official starter template, implement custom logic with the Agent Stack SDK, and register it with the platform for local execution.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please make sure all the references are to .md version.


> Agent Stack is open infrastructure for turning AI agents into running services.

This document provides a machine-readable index for the Agent Stack platform. AI agents and developers should utilize these links to discover how to make your agents Agent Stack ready, how to work with agent stack services, how to deploy your agent to a local or hosted version of Agent Stack, and how to self-host Agent Stack itself.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This section is not needed it won't tell agents much. Instead focus on giving a gist about what agenstack is

The idea is that this is root for the agent - it should give agent enough info to be able to navigate further.

for example

"Agentstack is a platform (server) that is running on your machine for purposes of development of AI agents. It is built on top of [agent ot agent a2A protocol](ink to google). It provide opinionated extended version of the A2A protocol that is defined in the SDK..."

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

But honestly if we do great job on describing each link it should be enough so maybe just skiping this entirely will do.

## Deploying Agents to Agent Stack

- [Build New Agents](https://agentstack.beeai.dev/stable/deploy-agents/building-agents): Create a new agent using the official starter template, implement custom logic with the Agent Stack SDK, and register it with the platform for local execution.
- [Wrap Existing Agents](https://agentstack.beeai.dev/stable/deploy-agents/wrap-existing-agents): Deploy agents built with any framework to Agent Stack by adding a server wrapper to gain instant access to the UI, observability, and deployment infrastructure.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I am not particualrly happy about Deploy -it may mislead the agent. It has nothing to do with deployment.

- [Build New Agents](https://agentstack.beeai.dev/stable/deploy-agents/building-agents): Create a new agent using the official starter template, implement custom logic with the Agent Stack SDK, and register it with the platform for local execution.
- [Wrap Existing Agents](https://agentstack.beeai.dev/stable/deploy-agents/wrap-existing-agents): Deploy agents built with any framework to Agent Stack by adding a server wrapper to gain instant access to the UI, observability, and deployment infrastructure.
- [Deploy Your Agents](https://agentstack.beeai.dev/stable/deploy-agents/deploy-your-agents): Containerize and deploy your agent to the platform as a managed service by connecting your GitHub repository, building Docker images, and verifying execution via the CLI or UI.
- [Connect A2A Agents](https://agentstack.beeai.dev/stable/deploy-agents/a2a-agents): Integrate existing A2A agents into Agent Stack by connecting Docker images or external URLs, and understand the requirements for agent card metadata and lifecycle management.
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Mention that these are plain A2A (not using Agentstack SDK)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

Status: PR in Review

Development

Successfully merging this pull request may close these issues.

Create Custom llm.txt file

2 participants