> For the complete documentation index, see [llms.txt](https://docs.seda.xyz/home/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.seda.xyz/home/for-agents/agent-modules.md).

# Agent Modules

Index of agent-ready runbooks for SEDA. Use these pages as the source of truth for building, deploying, and executing Oracle Programs.

## Agent Modules

This page is the canonical index for SEDA’s agent-ready runbooks.

**Rule:** Do not guess steps or URLs. Always navigate from:

1. Getting Started
2. Agent Modules (this page)
3. The specific module page

***

### Module index

* **Accessing Data On SEDA:** [**https://docs.seda.xyz/home/for-agents/agent-modules/accessing-data-on-seda**](https://docs.seda.xyz/home/for-agents/agent-modules/accessing-data-on-seda)\
  Choose a data source type (supported feed, public API, private API, website-only).
* **HTTP FetchTimeouts:** [**https://docs.seda.xyz/home/for-agents/agent-modules/http-fetch-timeouts**](https://docs.seda.xyz/home/for-agents/agent-modules/http-fetch-timeouts)\
  Default timeout values and how to set per-request `timeout_ms`.
* **Deploying Data Proxies:** [**https://docs.seda.xyz/home/for-agents/agent-modules/deploying-data-proxies**](https://docs.seda.xyz/home/for-agents/agent-modules/deploying-data-proxies)\
  Set up Data Proxy routes for private/proprietary sources and enable Fast support if needed.
* **Build And Test Oracle Programs:** [**https://docs.seda.xyz/home/for-agents/agent-modules/build-and-test-oracle-programs**](https://docs.seda.xyz/home/for-agents/agent-modules/build-and-test-oracle-programs)\
  Build the starter kit OP to WASM and run local tests before deploying.\
  Keplr + faucet tokens (required for deploying Oracle Programs).
* **Execute On SEDA Fast**\
  Execute existing Oracle Programs via Fast API. <https://docs.seda.xyz/home/for-agents/modules/40-execute-fast>\
  **Important:** Fast does not deploy Oracle Programs.
* **Deploy Oracle Program (Upload to SEDA Network)** <https://docs.seda.xyz/home/for-agents/modules/50-execute-core>\
  Deploy/upload an Oracle Program to the SEDA Network and obtain an **Oracle Program ID**.
* **Prover Contract Deployments** <https://docs.seda.xyz/home/for-agents/modules/60-prover-deployments>\
  Verify a prover exists for your target chain and copy the correct address.
* **EVM Hardhat Integrations** <https://docs.seda.xyz/home/for-agents/modules/60-relay-evm-hardhat>\
  Consume SEDA Core results from an EVM contract via Hardhat.

***

### Recommended paths

#### Fast path (execute an existing OP)

Accessing Data On SEDA → Execute On SEDA Fast

#### Build + deploy + Fast execute (your own OP)

Accessing Data On SEDA → Build And Test → Wallets And Tokens → Deploy Oracle Program → Execute On SEDA Fast

#### Core path (onchain request lifecycle)

Accessing Data On SEDA → Build And Test → Wallets And Tokens → Deploy Oracle Program


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.seda.xyz/home/for-agents/agent-modules.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
