Artificial intelligence · llms.txt file breakdown
Ollama organizes Ollama documentation around OpenAPI Specs.
The actual file
The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.
Complete saved Markdown shown below.
# Ollama
- [Ollama documentation](https://docs.ollama.com/index.md)
- [Quickstart](https://docs.ollama.com/quickstart.md)
- [Cloud](https://docs.ollama.com/cloud.md)
- [Streaming](https://docs.ollama.com/capabilities/streaming.md)
- [Thinking](https://docs.ollama.com/capabilities/thinking.md)
- [Structured Outputs](https://docs.ollama.com/capabilities/structured-outputs.md)
- [Decision](https://docs.ollama.com/capabilities/decision.md): Classify text, estimate yes/no probabilities, and score ordered criteria.
- [Vision](https://docs.ollama.com/capabilities/vision.md)
- [Embeddings](https://docs.ollama.com/capabilities/embeddings.md): Generate text embeddings for semantic search, retrieval, and RAG.
- [Tool calling](https://docs.ollama.com/capabilities/tool-calling.md)
- [Web search](https://docs.ollama.com/capabilities/web-search.md)
- [CLI Reference](https://docs.ollama.com/cli.md)
- [Modelfile Reference](https://docs.ollama.com/modelfile.md)
- [Context length](https://docs.ollama.com/context-length.md)
- [Linux](https://docs.ollama.com/linux.md)
- [macOS](https://docs.ollama.com/macos.md)
- [Windows](https://docs.ollama.com/windows.md)
- [Docker](https://docs.ollama.com/docker.md)
- [Importing a Model](https://docs.ollama.com/import.md)
- [FAQ](https://docs.ollama.com/faq.md)
- [Hardware support](https://docs.ollama.com/gpu.md)
- [Troubleshooting](https://docs.ollama.com/troubleshooting.md): How to troubleshoot issues encountered with Ollama
- [Overview](https://docs.ollama.com/integrations/index.md)
- [Claude Desktop](https://docs.ollama.com/integrations/claude-desktop.md): Use Ollama models in Claude on macOS.
- [OpenClaw](https://docs.ollama.com/integrations/openclaw.md)
- [Hermes Agent](https://docs.ollama.com/integrations/hermes.md)
- [Hermes Desktop](https://docs.ollama.com/integrations/hermes-desktop.md)
- [Claude Code](https://docs.ollama.com/integrations/claude-code.md)
- [OpenCode](https://docs.ollama.com/integrations/opencode.md)
- [DeepSeek Harness](https://docs.ollama.com/integrations/deepseek-harness.md)
- [Cline CLI](https://docs.ollama.com/integrations/cline-cli.md)
- [Codex CLI](https://docs.ollama.com/integrations/codex.md)
- [ChatGPT Desktop](https://docs.ollama.com/integrations/chatgpt.md): Use Ollama models in ChatGPT Desktop.
- [Copilot CLI](https://docs.ollama.com/integrations/copilot-cli.md)
- [Droid](https://docs.ollama.com/integrations/droid.md)
- [Goose](https://docs.ollama.com/integrations/goose.md)
- [Oh My Pi](https://docs.ollama.com/integrations/oh-my-pi.md)
- [Pi](https://docs.ollama.com/integrations/pi.md)
- [Pool](https://docs.ollama.com/integrations/pool.md)
- [VS Code](https://docs.ollama.com/integrations/vscode.md)
- [Cline](https://docs.ollama.com/integrations/cline.md)
- [JetBrains](https://docs.ollama.com/integrations/jetbrains.md)
- [Roo Code](https://docs.ollama.com/integrations/roo-code.md)
- [Xcode](https://docs.ollama.com/integrations/xcode.md)
- [Zed](https://docs.ollama.com/integrations/zed.md)
- [Onyx](https://docs.ollama.com/integrations/onyx.md)
- [n8n](https://docs.ollama.com/integrations/n8n.md)
- [marimo](https://docs.ollama.com/integrations/marimo.md)
- [NemoClaw](https://docs.ollama.com/integrations/nemoclaw.md)
- [Introduction](https://docs.ollama.com/api/introduction.md)
- [Authentication](https://docs.ollama.com/api/authentication.md)
- [Streaming](https://docs.ollama.com/api/streaming.md)
- [Usage](https://docs.ollama.com/api/usage.md)
- [Errors](https://docs.ollama.com/api/errors.md)
- [OpenAI compatibility](https://docs.ollama.com/api/openai-compatibility.md)
- [Anthropic compatibility](https://docs.ollama.com/api/anthropic-compatibility.md)
- [Generate a response](https://docs.ollama.com/api/generate.md): Generates a response for the provided prompt
- [Generate a chat message](https://docs.ollama.com/api/chat.md): Generate the next chat message in a conversation between a user and an assistant.
- [Generate embeddings](https://docs.ollama.com/api/embed.md): Creates vector embeddings representing the input text
- [System One](https://docs.ollama.com/api/systemone.md): Answer choice, yes/no, and scoring questions with a System One model, locally or in Ollama's cloud. Requires Ollama v0.35.0 or later, or v0.40.5 or later for cloud models. See the [decision guide](/capabilities/decision) for examples.
- [List models](https://docs.ollama.com/api/tags.md): Fetch a list of models and their details
- [List running models](https://docs.ollama.com/api/ps.md): Retrieve a list of models that are currently running
- [Show model details](https://docs.ollama.com/api-reference/show-model-details.md)
- [Create a model](https://docs.ollama.com/api/create.md)
- [Copy a model](https://docs.ollama.com/api/copy.md)
- [Pull a model](https://docs.ollama.com/api/pull.md)
- [Push a model](https://docs.ollama.com/api/push.md)
- [Delete a model](https://docs.ollama.com/api/delete.md)
- [Get version](https://docs.ollama.com/api-reference/get-version.md): Retrieve the version of the Ollama
- [Cloud usage](https://docs.ollama.com/api/cloud-usage.md): Usage statistics for cloud inference, web search, and web fetch.
- [Balance](https://docs.ollama.com/api/balance.md): Check your remaining usage credits.
## OpenAPI Specs
- [openapi](/openapi.yaml)
Measured from the saved file
Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.
Context architecture
1 H2 sections organize 73 parsed Markdown links. 71 links point to .md or .markdown paths; 0 link occurrences use another hostname. Linked destinations have not been recursively validated.
| H2 section | Links | UTF-8 bytes | Tokens |
|---|---|---|---|
| OpenAPI SpecsLine 75 | 1 | 28 | 11 |
Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.
Embedded material
Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.
Publisher prioritization
No H2 section named “Optional” was detected in this file.
The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.
Machine-readable routes
No MCP or Model Context Protocol term was detected in the captured file. 0 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.
These are text and link observations. No MCP server connection, authentication or tool call was tested.
Index and bundle
Verified text companion
A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.
Change evidence
This capture establishes a baseline. Update frequency cannot be determined from one observation.
File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.
19ae397485682058d931f4c6af827dc4721587ba95fc98d0c3d111349c2dfddeCounts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.