> For the complete documentation index, see [llms.txt](https://docs.noelclaw.fun/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.noelclaw.fun/install-by-client/aeon.md).

# Aeon

The noelclaw skill pack is live in the Aeon ecosystem (merged PR #253). Once added, all 121 Noelclaw tools are available in Hermes and the Aeon agent runtime.

***

## What Aeon Is

Aeon is an AI agent platform with its own skill registry. Skills are MCP-compatible tool bundles that agents can call during task execution. The noelclaw skill pack brings crypto intel, DeFi execution on Base, autonomous agents, vault memory, MiroShark simulation, and the Noel Framework into Aeon.

***

## Install

### Via Aeon Skill Registry (CLI)

```bash
aeon skill add noelclaw
```

This pulls the skill from the Aeon registry and registers `@noelclaw/mcp` as the underlying MCP server.

### Manual Config

If your Aeon version requires manual config, add to your Aeon config file:

```yaml
skills:
  noelclaw:
    mcp_server:
      command: npx
      args:
        - "-y"
        - "-p"
        - "@noelclaw/mcp@3.43.1"
        - "noelclaw-mcp"
    enabled: true
```

### Via Hermes in Aeon

If you use Hermes inside Aeon, follow the [Hermes install guide](/install-by-client/hermes-openclaw.md). Once the skill is registered in Hermes, Aeon agents can invoke it.

***

## Verify

In Hermes or any Aeon agent session:

```
/list-tools
```

You should see all 121 Noelclaw tools listed.

***

## Tools That Work Best in Aeon

Aeon agents are well-suited to longer autonomous tasks. These tool groups see the most usage in Aeon:

### Deep Research

Aeon agents can run multi-stage research that plans, searches, scrapes, and synthesizes - saving results to vault automatically:

```
deep_research topic: "analyze BTC market structure"
research_compare fromKey: "research/btc-q1" toKey: "research/btc-q2"
```

### Noel Vault

Vault is persistent across sessions - ideal for Aeon agents that need to store intermediate findings, plans, or outputs:

```
vault_save type: "execution" title: "Agent Output 001" content: "..." key: "agent-output-001"
vault_search query: "BTC analysis"
vault_history key: "agent-output-001"
```

### Noel Framework

Use playbooks to give Aeon agents structured, Sentinel-gated execution:

```
list_playbooks
run_playbook playbookId: "..."
get_noel_ledger
```

### MiroShark

Run social simulations as part of research or strategy workflows:

```
miroshark_simulate scenario: "How would a major exchange hack affect altcoin markets?"
miroshark_status simulation_id: "..."
```

### Market & Intel

Feed live data into agent reasoning:

```
get_market_data
get_token_data question: "PEPE, WIF, DOGE"
ask_noel question: "What narratives are gaining traction on Base?"
```

***

## Example: Aeon Agent Workflow

A typical Aeon agent task using noelclaw tools:

1. `ask_noel` - pull market analysis and current context
2. `deep_research` - run multi-stage research, auto-saves to vault
3. `agent_spawn` - create a persistent agent to track the topic
4. `vault_save` - store the analysis output
5. `create_automation` - set a recurring task based on the analysis
6. `agent_schedule` - schedule the agent to run daily

***

## Notes

* All 121 tools are available - no Aeon-specific limitations
* BYOK env vars (Grok, MiniMax) work the same way as in other clients
* See [Environment Variables](/reference/env-vars.md) for optional keys
* See [MCP Server Reference](/reference/mcp-server.md) for full tool parameter docs


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.noelclaw.fun/install-by-client/aeon.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.