EarnClaw vision

Why EarnClaw exists, how finance agents are organized in the workspace, and how teams scale from one agent to a fleet.

Onchain finance is moving toward operator-first automation. Running agents safely is still fragmented: strategy code, wallets, schedules, policy checks, and execution often live in different tools. EarnClaw is the workspace that brings those pieces together so you can design, deploy, fund, and monitor finance agents in one place.

Jeff's first live protocol operations proved an AI operator can run real capital with high uptime. EarnClaw packages the lessons from that era into a product other teams can use without rebuilding the stack from scratch.


Why EarnClaw is needed

Problem todayWhat EarnClaw provides
One-off prompts and scriptsReviewed templates with defined strategies and guardrails
Wallet and signing scattered across toolsAgent wallets with scoped delegation and expiry
No standard safety review before an onchain actionPolicy checks that stop blocked actions and explain why
Hard to audit what an agent triedRun history, diagnostics, and billing in one dashboard
Each venue wired by handSupported integrations for trading, yield, and prediction

EarnClaw is not a chat surface. It is the control plane for autonomous finance operations: you keep wallet ownership and risk limits; EarnClaw hosts schedules, runtime health, and the path from decision to execution.


Built like finance infrastructure, not a chatbot

Giving an AI a prompt and a set of tools is not enough when real capital is involved. Operators need to know what will run, what changed, what the agent may do, and why an action executed or stopped.

EarnClaw combines defined strategy releases with limits enforced outside the agent itself. Supported launch paths are evaluated before release, and each cycle produces a record you can review.

You know exactly what is running

Supported templates identify the strategy release an agent uses. Changes are tracked so operators can review what changed before adopting an update.

The agent decides, the rules protect

Your agent analyzes markets and makes the strategy calls. Execution passes through a separate control layer that enforces your limits: spending caps, allowed venues, and safety checks before every transaction. The agent never gets a blank check.

Tested before it trades

Supported launch paths are evaluated against market scenarios before release. Funding, venue setup, and safety checks must still pass before an action can execute.

A record you can review

Run history records what the agent attempted, what executed, what it skipped, and which safety rule stopped an action.

This is what it takes to run agents with real money. Delegate with limits, verify everything.


Three finance agent lanes

EarnClaw organizes agents around three lanes. Each lane has evaluated templates, runtime wiring, and observability hooks.

LaneWhat agents doExample venues
TradingSpot and perps execution on schedules or signalsMulti-chain EVM spot (aggregated DEX routing, millions of tokens), Hyperliquid perps, testnet venues where enabled
YieldVault and funding discovery, allocation, rebalanceVaults.fyi, Yield.xyz, major lending protocols
PredictionSignal-driven participation in binary marketsPolymarket-style markets where enabled

You choose the lane in the new-agent wizard. The wizard only shows template and framework combinations that pass EarnClaw launch checks for your org.


How agents are organized in EarnClaw

Everything attaches to an org. Billing, deploy limits, and team access are org-scoped. See Organizations for how teams operate multiple agents. Under each org you run one or more agents:

Org
 └── Agent
      ├── Template      (strategy profile, decision schema, venue rules)
      ├── Runtime       (Hermes, OpenClaw, or Claude hosted environment)
      ├── Agent wallet  (capital the mandate uses onchain)
      ├── Delegation    (what the wallet may sign, and until when)
      ├── Schedule      (cron, signal, or manual trigger)
      └── Guardrails    (notional caps, venue allowlists, kill switch)

On each cycle the agent reads current information, applies the template rules, and decides whether to act or wait. Safety checks run before an onchain action. Blocked actions appear in run history with an explanation.

For integration and execution details, see Integrations at runtime.


A typical agent cycle

Scheduled review → Refresh information → Decide → Safety checks → Act or wait → Record outcome
StepWhere you see it
Schedule and healthAgent detail, runtime diagnostics
Decision and supporting informationRun log
Onchain receipts and allowance usageRun history; runtime plan in Settings
Org usage and plan limitsBilling
Org capital and balance historyOrganization analytics

See Observability and Dashboard map.


How teams scale

See Organizations for the org model and fleet operations.

Start with one agent. Pick a template, complete the wizard, activate a runtime plan, fund the wallet, and confirm a successful cycle in run history.

Add agents in the same org. Each agent gets its own wallet, delegation, and schedule. Workspace limits set how many agents can run at once. See Pricing overview.

Standardize with templates. Reuse reviewed templates and guardrails across agents. Builder publishing and marketplace features will appear in the docs when they are available.

Operate a fleet. Use consistent guardrails across agents, review blocked actions centrally, and adopt template updates when they are available. Higher workspace tiers add deploy headroom and early product lanes. See Pricing overview.

One agent → Repeatable template → Multiple agents per org → Marketplace publish → Fleet operations

What changed from Jeff v1

Jeff v1 focused on one autonomous protocol CEO: liquidity, epochs, and gauge operations on Base. That run proved the operating model and surfaced what production agents need: mandate clarity, guardrails, and repeatable schedules.

EarnClaw v2 generalizes that into a workspace any team can use: trading, yield, and prediction agents with delegation, safety checks, and run history built into the operating flow.

The original Jeff CEO launch film lives on History.


Start building

  1. What is EarnClaw — product summary
  2. Organizations — billing scope and fleet scale
  3. Create your first agent — wizard walkthrough
  4. Fund and run — wallet, runtime plan, execution allowance