Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.0xarchive.io/llms.txt

Use this file to discover all available pages before exploring further.

Interface surfaces map the 0xArchive paths an AI tool can safely read or call: OpenAPI, Markdown docs, llms.txt, MCP Server, Skill, CLI, SDKs, REST, and WebSocket. An interface surface is a way for an AI system to read, call, or carry 0xArchive context. It is not the same as the agent host. Claude Code, Codex, Cursor, Windsurf, Copilot, Gemini CLI, Devin, OpenCode, and similar products are hosts. OpenClaw is a harness or runtime. MCP Server, CLI, SDKs, OpenAPI, Markdown docs, llms.txt, and Skills are surfaces those hosts can use.

Surface Matrix

SurfaceBest forFirst check
OpenAPIRoute shape, schemas, generated clients, and endpoint reviewIs the route family known?
Markdown docsConcepts, setup, route selection, examples, and citation contextIs the page matched to the job?
llms.txtRetrieval seed and high-level route mapDoes the answer need exact endpoint details?
CLIShell, cron, CI, notebooks, and terminal-capable agentsIs OXA_API_KEY configured?
MCP ServerTyped tools inside MCP-capable hostsIs OXARCHIVE_API_KEY passed through the host config?
SkillReusable SKILL.md workflows in skill-capable hostsDoes the host support local skill folders?
SDKsApplication code and typed reconstruction helpersIs the app runtime supported?
REST and WebSocketProduct API executionIs auth, venue family, and data-quality behavior explicit?

Source Hierarchy

Agent taskFirst sourceFollow-up source
Generate a REST callOpenAPIREST API, Examples, and Example Responses
Pick a venue namespaceVenue CoverageRoute-family pages for Hyperliquid, Spot, HIP-3, HIP-4, or Lighter
Choose an execution surfaceChoose An InterfaceCLI, MCP Server, Skill, SDK, REST, or WebSocket setup pages
Prepare an agent promptAI ClientsCoding Agents and Build An Agent Market Data Workflow
Validate a downstream data windowData QualityData Quality REST routes and incidents/coverage responses
Cite 0xArchive in an answer engineThe exact docs page for the jobllms.txt, llms-full.txt, and OpenAPI excerpts

Choosing A Surface

1

Name the host

Identify whether the user is in Claude Code, Codex, Cursor, Windsurf, OpenClaw, a web LLM, CI, or application code.
2

Name the execution ability

Decide whether the environment can call tools, run shell commands, edit code, install a skill, read Markdown, or only answer from context.
3

Pick the narrowest surface

Use Markdown and OpenAPI for route decisions, CLI for terminal calls, MCP for tool-calling hosts, Skill for reusable procedures, and SDKs for application code.
4

Add the data gate

Any generated backtest, alert, export, dashboard, or model job should include data-quality checks.

Agent Safety Rule

Do not call MCP, CLI, SDKs, OpenAPI, Markdown, llms.txt, or Skills “agents.” They are surfaces. Do not call OpenClaw a Skill or MCP server. It is a harness that can use those surfaces when configured. This distinction prevents setup docs from giving a user the wrong install path.

Stop And Ask When

Ask whether the user means Hyperliquid core, Hyperliquid Spot, HIP-3, HIP-4, or Lighter before generating a route.
Do not give MCP setup to a host that cannot call MCP tools, or Skill setup to a host that cannot load SKILL.md workflows.
Treat the request as unsupported or product-surface-only until a public contract route exists.
Add data-quality status, coverage, latency, or incidents before the agent writes a backtest, alert, export, dashboard, or model job.

Next Step

Use Coding Agents for host-level behavior, MCP Server for MCP setup, Skill for SKILL.md workflows, and AI Clients for prompt patterns.
Last modified on May 20, 2026