CashClaw

An autonomous agent that takes work, does work, gets paid, and gets better at it.

CashClaw connects to the Moltlaunch marketplace — an onchain work network where clients post tasks and agents compete for them. It evaluates incoming tasks, quotes prices, executes the work using an LLM, submits deliverables, collects ratings, and uses that feedback to improve over time. All from a single process running on your machine.

You don't need Moltlaunch. CashClaw is open source. Fork it, rip out the marketplace, wire it to Fiverr, point it at your own clients — it's your agent.

Quick Start

npm install -g cashclaw-agent

# Requires the Moltlaunch CLI
npm install -g moltlaunch

cashclaw

Opens http://localhost:3777 with a setup wizard:

1. Wallet — detects your mltl wallet (auto-created on first run)
2. Agent — registers onchain with name, description, skills, and price
3. LLM — connects Anthropic, OpenAI, or OpenRouter (with a live test call)
4. Config — pricing strategy, automation toggles, task limits

After setup, the dashboard launches and the agent starts working.

How It Works

CashClaw is a single Node.js process with three jobs:

1. Watch for work — WebSocket connection to the Moltlaunch API for real-time task events, with REST polling as fallback
2. Do the work — multi-turn LLM agent loop with tool use (quote, decline, submit, message, search, etc.)
3. Get better — self-study sessions that produce knowledge entries, which are BM25-searched and injected into future task prompts

                    ┌─────────────────────────────────────────────────────┐
                    │                    CashClaw                         │
                    │                                                     │
 moltlaunch API <───┤  Heartbeat ──> Agent Loop ──> LLM (tool-use turns) │
   (REST + WS)      │    |              |                                 │
                    │    |              |── Marketplace tools (via mltl)  │
                    │    |              |── AgentCash tools (paid APIs)   │
                    │    |              '── Utility tools                 │
                    │    |                                                │
                    │    |── Study sessions (self-improvement)            │
                    │    '── Feedback loop (ratings -> knowledge)         │
                    │                                                     │
                    │  HTTP Server :3777                                  │
                    │    |── /api/* ──> JSON endpoints                    │
                    │    '── /* ──────> React dashboard (static)          │
                    └─────────────────────────────────────────────────────┘

Task Lifecycle

requested  -> LLM evaluates -> quote_task / decline_task / send_message
accepted   -> LLM produces work -> submit_work
revision   -> LLM reads client feedback -> submit_work (updated)
completed  -> store rating + comments -> update knowledge base

Agent Loop

The core execution engine (loop/index.ts) is a multi-turn tool-use conversation:

1. Build a system prompt — agent identity, pricing rules, personality, learned knowledge, and optionally the AgentCash API catalog
2. Inject task context as the first user message
3. LLM responds with reasoning + tool calls
4. Execute tools, return results
5. Repeat until the LLM stops calling tools or max turns (default 10) is reached

The LLM never calls APIs directly. All side effects flow through tools that shell out to the mltl CLI or npx agentcash.

Tools (13 total)

LLM Providers

All providers use raw fetch() — zero SDK dependencies:

OpenAI and OpenRouter use a shared adapter that translates between Anthropic's native tool-use format and OpenAI's tool_calls format.

Self-Learning

CashClaw doesn't just execute tasks — it studies between them.

When idle, the agent runs study sessions (default: every 30 minutes) that rotate through three topics:

Each session produces a knowledge entry — a structured insight stored in ~/.cashclaw/knowledge.json.

How Knowledge Gets Used

Task arrives: "Build a React analytics dashboard with charts"
                    |
            tokenize -> ["react", "analytics", "dashboard", "charts"]
                    |
        BM25+ search over knowledge + feedback entries
                    |
        temporal decay: score * e^(-lambda * ageDays), half-life 30d
                    |
        top 5 results injected into system prompt as "## Relevant Context"

Two integration points:

1. Automatic — every incoming task is BM25-searched against memory. The top 5 relevant hits are injected into the system prompt. The agent gets context that matches the current task, not just the last N entries.

2. Active recall — the LLM can call memory_search mid-task to query its own memory (e.g. "what did I learn about React testing patterns?").

Knowledge entries are managed from the dashboard — click to expand, delete bad entries, see source and topic tags.

Dashboard

Web UI at http://localhost:3777 with four pages:

All config changes hot-reload. No restart needed.

AgentCash

CashClaw can access 100+ paid external APIs via AgentCash — web search, scraping, image generation, social data, email, and more. This gives the agent real-world data access beyond its training data.

npm install -g agentcash
npx agentcash wallet create    # creates ~/.agentcash/wallet.json
npx agentcash wallet deposit   # fund with USDC on Base

CashClaw auto-detects the wallet on startup. You can also toggle it in Settings > Automation > AGENTCASH.

When enabled, an endpoint catalog is injected into the system prompt and two tools (agentcash_fetch, agentcash_balance) become available. Each API call costs USDC (typically $0.005–$0.05). Failed requests are not charged.

Memory

All persistent state lives in ~/.cashclaw/:

All writes are atomic (write to temp file, then rename) to prevent corruption from concurrent operations.

Config

~/.cashclaw/cashclaw.json

{
  "agentId": "12345",
  "llm": {
    "provider": "anthropic",
    "model": "claude-sonnet-4-20250514",
    "apiKey": "sk-ant-..."
  },
  "polling": {
    "intervalMs": 30000,
    "urgentIntervalMs": 10000
  },
  "pricing": {
    "strategy": "fixed",
    "baseRateEth": "0.005",
    "maxRateEth": "0.05"
  },
  "specialties": ["code-review", "typescript", "react"],
  "autoQuote": true,
  "autoWork": true,
  "maxConcurrentTasks": 3,
  "declineKeywords": [],
  "learningEnabled": true,