> ## Documentation Index > Fetch the complete documentation index at: https://rasa.com/docs/llms.txt > Use this file to discover all available pages before exploring further. # Project structure > Every file and folder a Mantle agent recognises, and which are required. A Mantle project is two config files and a `skills/` folder. Everything else is optional and added when a skill needs it. ## The minimum This is a complete, trainable agent: ``` my-agent/ ├── agent.yml # Identity, persona, rules, prompt tuning ├── integrations.yml # LLM provider and channels └── skills/ └── card_replace/ # The folder name is the skill id └── skill.md # Instructions, and any control declarations ``` ## Everything a project can hold Each optional file is added only when a skill needs it: ``` my-agent/ ├── agent.yml # Required. Identity, persona, rules, prompt tuning ├── integrations.yml # Required. LLM provider and channels ├── memory.yml # Optional. Project-wide memory, the project. namespace ├── responses.yml # Optional. Project-wide responses, overrides built-in wording ├── references/ # Optional. Agent-wide knowledge, every **/*.md is indexed ├── tools/ # Optional. Shared tools, declared with import_tools └── skills/ └── card_replace/ ├── skill.md # Required. The only required file in a skill ├── memory.yml # Optional. This skill's memory schema ├── responses.yml # Optional. Verbatim wording ├── tools.py # Optional. Auto-discovered, no declaration needed ├── tools/ # Optional. Or a folder of them, also auto-discovered └── references/ # Optional. Indexed into the same project-wide index ``` ## What makes it a Mantle project The engine is chosen by layout rather than by a config key. A project is Mantle when it has an `integrations.yml` **and** at least one `skills/*/skill.md`. That glob is one level deep, so a skill folder sits directly under `skills/`. ## Agent root | Path | Required | Purpose | | - | - | - | | `agent.yml` | **Yes** | [Identity, persona, rules, prompts, session settings](https://rasa.com/docs/mantle/reference/agent-yml.md) | | `integrations.yml` | **Yes** | [LLM provider, channels, optional MCP servers, model groups](https://rasa.com/docs/mantle/reference/integrations-yml.md) | | `memory.yml` | No | [Project-wide memory](https://rasa.com/docs/mantle/reference/memory-yml.md#project-memory-memoryyml-at-the-agent-root). A flat map, resolving to `session.project.` | | `responses.yml` | No | [Project-wide responses](https://rasa.com/docs/mantle/reference/responses-yml.md). Declaring a built-in name here replaces it | | `references/` | No | Markdown indexed at train time, reachable through `search_knowledge` | | `tools/` | No | Shared tools. A skill uses one by naming it in `import_tools` | ## A skill folder | Path | Required | Purpose | | - | - | - | | `skill.md` | **Yes** | [Frontmatter and prose body](https://rasa.com/docs/mantle/reference/skill-md.md) | | `memory.yml` | No | [This skill's schema](https://rasa.com/docs/mantle/reference/memory-yml.md), under `session..` | | `responses.yml` | No | [Verbatim wording](https://rasa.com/docs/mantle/reference/responses-yml.md) | | `tools.py` or `tools/*.py` | No | [Tools](https://rasa.com/docs/mantle/reference/tools.md), auto-discovered | | `references/` | No | Knowledge, indexed into the project-wide index | The **folder name is the skill id**. A skill in `skills/card_replace/` is `@skill.card_replace` in prose and `session.card_replace.` in memory, whatever its frontmatter `name:` says. ## Declared or discovered The difference decides whether a tool is usable without any config: * **A skill's own tools** are auto-discovered from `tools.py` and `tools/*.py` in that folder. Nothing to declare. Within one skill, a `tools/*.py` definition shadows a same-named one in `tools.py`. * **Shared tools** in the agent-root `tools/` folder must be named in the skill's `import_tools`. A shared tool that is not declared is not attached to the skill. * **MCP tools** use `mcp/:` in `import_tools`. Only listed tools are attached; see [Import MCP tools](https://rasa.com/docs/mantle/concepts/tools.md#mcp-tools). * On a name collision between skill-local and shared tools, the skill-local tool wins. An MCP bare name that collides with either fails `rasa train`. ## What ships in the trained model `rasa train` copies `agent.yml`, `integrations.yml`, `memory.yml`, `responses.yml`, and the `skills/`, `tools/`, and `references/` directories into the model archive. Two consequences worth knowing: * The reference index is built at train time, so adding or editing a file under any `references/` folder needs a retrain before the agent can answer from it. * `llm:`, `channels:`, and `mcp_servers:` are read from your project directory at runtime, so a provider, channel, or MCP connection change only needs a restart. ## Files the scaffold adds `rasa init --engine mantle` also writes `AGENTS.md`, context for your coding agent, and `.env`, holding your keys. Neither is read by the engine: `.env` supplies the environment variables that `api_key_env` and `${VAR}` resolve against, and `AGENTS.md` is for your IDE. ## See also * [Getting Started](https://rasa.com/docs/mantle/getting-started.md): scaffold a project and build the first skill * [skill.md](https://rasa.com/docs/mantle/reference/skill-md.md): the contract for the one required file ## Related topics - [Getting Started](https://rasa.com/docs/mantle/getting-started.md) - [Model Storage](https://rasa.com/docs/reference/integrations/model-storage.md) - [Custom Actions](https://rasa.com/docs/reference/primitives/custom-actions.md) - [Building a Conversational AI Team](https://rasa.com/docs/learn/best-practices/conversational-ai-teams.md) - [Overview](https://rasa.com/docs/reference/config/agents/overview-agents.md) This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.