Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
| Date | Stars |
|---|---|
| 2026-07-31 | 252 |
| 2026-08-04 | 252 |
| 2026-08-06 | 252 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# LLMsTxt Architect
`llms.txt` is an emerging standard for communicating website contents to LLMs. It is a markdown file listing URLs within a site and their *descriptions*, giving LLMs a guide [to help fetch and read pages](https://github.com/langchain-ai/mcpdoc) in order to accomplish tasks. LLMsTxt Architect is a Python package that builds [LLMs.txt](https://llmstxt.org/) automatically, using LLMs to automate the process. It can start with a list of URLs or an existing `llms.txt` file, and a user can specify the LLM provider, model, prompt used to generate description along with other options.
## Quickstart
You can run this tool with many [LLM providers](https://python.langchain.com/api_reference/langchain/chat_models/langchain.chat_models.base.init_chat_model.html). For example, Anthropic (be sure `ANTHROPIC_API_KEY` is set):
```shell
$ curl -LsSf https://astral.sh/uv/install.sh | sh
$ uvx --from llmstxt-architect llmstxt-architect --urls https://langchain-ai.github.io/langgraph/concepts --max-depth 1 --llm-name claude-3-7-sonnet-latest --llm-provider anthropic --project-dir tmp
```
Local model via Ollama (be sure [Ollama is installed](https://ollama.com/download) and the model is pulled):
```shell
$ ollama pull llama3.2:latest
$ uvx --from llmstxt-architect llmstxt-architect --urls https://langchain-ai.github.io/langgraph/concepts --max-depth 1 --llm-name llama3.2:latest --llm-provider ollama --project-dir tmp
```
Both will use [RecursiveURLLoader](https://python.langchain.com/docs/integrations/document_loaders/recursive_url/) with `max-depth` 1 to only load the provided page. While running you will see:
The resulting `llms.txt` file for this example input page:
```shell
[Concepts](https://langchain-ai.github.io/langgraph/concepts): LLM should read this page when seeking to understand LangGraph framework concepts, exploring agent patterns, or learning about LangGraph Platform deployment options. The page covers key concepts including LangGraph basics, agentic patterns, multi-agent systems, memory, persistence, streaming, and various LangGraph Platform deployment options (Self-Hosted, Cloud SaaS, BYOC).
```
You can see some of the `llms.txt` files generated with this tool:
* https://langchain-ai.github.io/langgraph/llms.txt
* https://python.langchain.com/llms.txt
### Installation
You can also install the package with `pip`, and use the CLI:
```bash
$ python3 -m venv .venv
$ source .venv/bin/activate # On Windows: .venv\Scripts\activate
$ pip install llmstxt-architect
$ llmstxt-architect --urls https://langchain-ai.github.io/langgraph/concepts --max-depth 1 --llm-name claude-3-7-sonnet-latest --llm-provider anthropic --project-dir test
```
Use it in a notebook:
```python
import asyncio
from llmstxt_architect.main import generate_llms_txt
await generate_llms_txt(
urls=["https://langchain-ai.github.io/langgraph/concepts"],
max_depth=1,
llm_name="claude-3-7-sonnet-latest",
llm_provider="anthropic",
project_dir="test",
)
```
Use it in a script:
```python
import asyncio
from llmstxt_architect.main import generate_llms_txt
async def main():
await generate_llms_txt(
urls=["https://langchain-ai.github.io/langgraph/concepts"],
max_depth=1,
llm_name="claude-3-7-sonnet-latest",
llm_provider="anthropic",
project_dir="test_script",
)
if __name__ == "__main__":
asyncio.run(main())
```
## Configurations
The full list of configurations is available in the [CLI help](https://github.com/langchain-ai/llmstxt-architect/blob/main/llmstxt_architect/cli.py).
| Parameter | Type | Default | Description |
|-----------|------|---------|-------------|
| `--urls` | List[str] | (Required if not using `--existing-llms-file`Excerpt of 14,064 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:07c16edd480458a2, llm:Repository name 'llmstxt_architect' suggests tooling around LLMs/text architecture; language Python. No topics or README provided.
matched fp:07c16edd480458a2, llm:Repository name 'llmstxt_architect' suggests tooling around LLMs/text architecture; language Python. No topics or README provided.