Frameworks
Hermes, OpenClaw, and Claude managed agents on EarnClaw. How each framework runs, what it is best for, and where to read upstream docs.
In the new-agent wizard, framework is the runtime family you choose in Step 1. It defines how the agent runs day to day: schedules, skills, LLM wiring, and how EarnClaw hosts the machine.
A runtime is the hosted environment for one deployed agent. EarnClaw connects it to the selected template and supported Thirdfy integrations. See Integrations at runtime.
Not every template ships on every framework. The wizard only shows launchable combinations for your org.
Hermes
What Hermes is
Hermes is a hosted runtime for scheduled finance jobs. Each cycle reviews current information, applies the strategy rules, runs safety checks, and records whether the agent acted or waited.
Best for
Trading templates during the current beta. Yield and prediction support will appear as those paths become available to your org.
Upstream docs
OpenClaw
What OpenClaw is
OpenClaw is an agent gateway runtime for soul-driven agents: persisted workspace artifacts, skills, and scheduled finance jobs. EarnClaw hosts OpenClaw with managed secrets, volume state, and dashboard access to the gateway when enabled for your org.
Best for
Teams that want OpenClaw-native skills and strategy files alongside EarnClaw guardrails. OpenClaw will appear in the wizard when a supported template is available to your org.
Upstream docs
- OpenClaw documentation
- OpenClaw installation
- Thirdfy OpenClaw skills (optional skill packs for Thirdfy actions)
Claude managed agents
What Claude managed is
Claude managed agents are Anthropic's hosted agent runtime: model, system prompt, tools, and MCP servers defined in Claude Console, with sessions run in managed sandboxes. EarnClaw wires finance templates to this path when you want Claude-native orchestration without hosting Hermes or OpenClaw yourself.
Best for
Claude-first teams, MCP-heavy workflows, and template lanes validated for managed sessions. Useful when your operators already live in Claude Console and want EarnClaw policy plus execution behind the same agent.
Upstream docs
- Claude Managed Agents overview
- Claude Managed Agents quickstart
- MCP connector
- Thirdfy MCP on EarnClaw (execution and delegation)
Quick comparison
| Framework | Hosted by | Typical lanes | Operator surface |
|---|---|---|---|
| Hermes | EarnClaw | Trading, yield, prediction packs | Agent page, cron diagnostics, run history |
| OpenClaw | EarnClaw | Soul-driven finance agents, skills | Gateway artifacts, dashboard access, run history |
| Claude managed | Anthropic + EarnClaw wiring | MCP-orchestrated finance templates | Claude Console + EarnClaw agent page |
Runtime lifecycle (all frameworks)
- Provision — org, agent wallet, runtime id, pack version
- Preflight — delegation scopes, template rules, plan allowance, venue readiness
- Run — cron, signal, or manual trigger
- Receipt — execution status and skip reasons in run history
Health and upgrades
- Runtime diagnostics surface adapter errors, funding gaps (for example perps margin), and pack version drift
- You can pin pack versions or roll out upgrades on a schedule that fits your org