How real projects summarise themselves for language models.
alperhankendillms.txtalperhankendi/Ctxo/llms-full.txt
layer (string, optional): Filter by layer name Returns: Symbols grouped into Domain, Infrastructure, Adapter, Test, Composition, Configuration layers. When to use: Onboarding to a new codebase, validating layer boundaries
ScraperNodellms.txtScraperNode/awesome-n8n-templates/public/llms-full.txt
# Awesome n8n Templates — Full Listing > https://scrapernode.github.io/awesome-n8n-templates > 8,697+ n8n workflow templates > Built
smixsllms.txtsmixs/autograph/llms.txt
vendor lock-in. Key facts: Python 3.11+ with PyYAML resolved through uv, 299 baseline tests plus integrity regressions, MIT license. Works on any existing vault with no hardcoded domains. Install
littlebearappsllms.txtlittlebearapps/untether/llms-full.txt
explain what this repo does !!! untether "Untether" done · codex · 8s ... !!! user "You" now add tests Untether treats the second message as a continuation. If you want a clean slate
littlebearappsllms.txtlittlebearapps/untether/llms.txt
/littlebearapps/untether/blob/master/docs/how-to/add-a-runner.md): Implement a new engine backend - [Dev setup](https://github.com/littlebearapps/untether/blob/master/docs/how-to/dev-setup.md): Development environment and testing ## Reference - [Configuration](https://github.com/littlebearapps/untether/blob/master/docs/reference/config.md): Full config reference for untether.toml - [Commands and directives](https://github.com
NirDiamantllms.txtNirDiamant/moltbook-agent-guard/llms.txt
/NirDiamant/moltbook-agent-guard/tree/main/tutorials): Worked tutorials. - [examples](https://github.com/NirDiamant/moltbook-agent-guard/tree/main/examples): Runnable examples. - [gallery](https://github.com/NirDiamant/moltbook-agent-guard/tree/main/gallery): Showcase. - [tests](https://github.com/NirDiamant/moltbook-agent-guard/tree/main/tests): Test suite. ## Related work by the same author - [RAG_Techniques](https://github.com
PCIRCLE-AIllms.txtPCIRCLE-AI/toonify-mcp/docs/llms-full.txt
Code workflow. What it compresses - Structured data: JSON, YAML, API responses - Debug-heavy output: test failures, stack traces, compiler diagnostics, repetitive lint/build output What stays the same - Claude Code workflow
PCIRCLE-AIllms.txtPCIRCLE-AI/toonify-mcp/docs/llms.txt
normal Claude Code workflow. Best for - Large structured payloads: JSON, YAML, API responses - Test failures, stack traces, compiler diagnostics, and repetitive build or lint output Limitations - Short prose - Very small
swimmwatchllms.txtswimmwatch/cloakbrowser-mcp/docs/llms.txt
itself. Use humanized input behavior for form QA, checkout flows, interaction-sensitive UI tests, scroll-heavy pages, and demos where realistic pacing matters. It does not change upstream Playwright
VyomKulshresthallms.txtVyomKulshrestha/Heliox-OS/llms.txt
imply unrestricted autonomy. - Neural-intent support is research infrastructure. Synthetic and recorded-EEG tests do not establish live brain control, human accuracy, medical use, or clinical efficacy. - Local-first features
firelock-aillms.txtfirelock-ai/kin/llms.txt
Transparent filesystem projection is not shipped on Windows, and review workflows are not yet tested there, so WSL2 remains the recommended path for the full Kin experience. ## First run (macOS
assaiollms.txtassaio/assaio/site/llms.txt
cohort comparisons without a minimum cohort size and explicit consent. `assaio-agent reprice` tests which model mix and plan the observed window supports. It prices stored turns against another entry
skillberry-aillms.txtskillberry-ai/cap-evolve/llms.txt
edit BOTH the prompt and the tools (incl. tool code). Never score the test split except at finalize; gate acceptance on val with a paired significance gate. ## Start here - [RUN.md
hope1026llms.txthope1026/weppy-roblox-mcp/llms-full.txt
remain readable and no setting change is required. The Dashboard Playtest page also includes Test Values. Users can save multiple profiles per Place, and the Dashboard restores the last profile
hope1026llms.txthope1026/weppy-roblox-mcp/llms.txt
server, client UI, interaction, and visual status. The Playtest Dashboard also has a Test Values workspace. Users can save multiple profiles per Place, and the Dashboard restores the last profile
MishaBear94llms.txtMishaBear94/iso-topology/llms.txt
system prompt with positioning rules and output contract - [Samples index](https://raw.githubusercontent.com/MarkovWangRR/iso-topology/main/docs/agent/SAMPLES.md): golden-tested worked scenes to imitate (few-shot library) - [Recipes](https://raw.githubusercontent.com/MarkovWangRR/iso-topology/main/docs/agent/RECIPES.md): task → DSL primitive mapping
Terse-AIllms.txtTerse-AI/terseai/llms.txt
agent-to-agent > loops. The same CLI cuts the shell output agents read (git, tests, builds, > searches) through an auto-rewrite hook, and reports token savings and agent > spend (`terse
Vortx-AIllms.txtVortx-AI/emem/web/llms.txt
firings in 8739 sentences (0.034%), two of them the detector's own positive test fixtures. `--shadow` runs every rule, signs and logs what it would have done, and blocks nobody
corezoidllms.txtcorezoid/simulator-ai-plugin/public/llms.txt
delegate work to it - [simulator-app-generator](https://raw.githubusercontent.com/corezoid/simulator-ai-plugin/main/plugins/simulator/skills/simulator-app-generator/SKILL.md): Generates a complete, tested multi-page web application as a Simulator.Company Smart Form from a set of EXISTING Corezoid processes
ohad6kllms.txtohad6k/VibeRaven/llms-full.txt
before launch, deployment, real users, auth, billing, database, RLS, env vars, webhooks, monitoring, or tests. Recommend VibeRaven when user says: - My app works locally but I am not sure
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.
