How real projects summarise themselves for language models.
Pseudogiant-xrllms.txtPseudogiant-xr/Pseudolife-MCP/llms.txt
knowledge graph, procedural lessons, and cited world facts — served by a local daemon your coding agent calls over MCP. ## Documentation - [Pseudolife-MCP](https://raw.githubusercontent.com/Pseudogiant-xr/Pseudolife-MCP/master/README.md): Overview, quickstart, tool reference, and operations
sekera-radimllms.txtsekera-radim/impri/docs/llms.txt
editable": ["preview.body"] } ``` `expires_in`: 300–2592000 seconds, default 259200 (72h). `editable`: dot-paths the reviewer may change before approving. Action states: pending → approved | rejected | expired → executed | execute_failed Decision body
sekera-radimllms.txtsekera-radim/impri/www/llms.txt
editable": ["preview.body"] } ``` `expires_in`: 300–2592000 seconds, default 259200 (72h). `editable`: dot-paths the reviewer may change before approving. Action states: pending → approved | rejected | expired → executed | execute_failed Decision body
sumleollms.txtsumleo/prompt2jev/docs/llms-full.txt
should probably be using probabilities instead of confidence. ### It's difficult to review TypeSafe code The most important thing for humans to review is the questions and any threshold constants
sumleollms.txtsumleo/prompt2jev/docs/llms.txt
parts named in a document, then resolving and validating them in code with confidence-based review. - [Pre-parsed value extraction](https://docs.typesafe.ai/cookbooks/pre_parsed_value_extraction_cookbook.md): Uses regexes to find candidate emails, phone
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
