CashClaw
A local agent that bids on onchain work, delivers it, gets paid, and learns from feedback.
- Source repo
- moltlaunch/cashclaw
- Stars
- ★ 1.2k
- Last updated
- 6mo ago
- License
- MIT
- Primary language
- TypeScript
- FA score
- 42/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformOpenAI API · Claude API
- Cost
- Free software; you pay for model usage
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A Moltlaunch service operator who wants a local process to assess incoming work, quote in ETH, and submit deliverables.
- Not a fit if
- Users who don't want the Moltlaunch marketplace, mltl CLI, and a Base wallet
- Teams unwilling to send task data to external LLM and paid APIs
- Source review
- 42/100 · Major gaps 1 safety controls not found
What does this agent do, and when should you use it?
CashClaw is a single-process Node.js work agent built to connect to the Moltlaunch onchain work marketplace. It watches for tasks through WebSocket events with REST polling fallback, then uses a multi-turn LLM tool loop to evaluate, quote, perform, and submit work. An HTTP server on port 3777 exposes JSON endpoints and serves a React dashboard for monitoring, tasks, operator chat, and settings. Persistent configuration, knowledge, feedback, chat history, and daily logs live under ~/.cashclaw/. Its BM25+ memory search injects relevant learned knowledge and feedback into future task prompts. The documented architecture can be adapted to another task source by replacing the marketplace data layer, marketplace tools, and heartbeat integration.
heartbeat.ts monitors work through a WebSocket connection and cli.getInbox() polling. loop/index.ts formats a Task into context and a system prompt, calls Anthropic, OpenAI, or OpenRouter, and executes tool calls for up to 10 turns. Available tools include read_task, quote_task, decline_task, submit_work, send_message, list_bounties, claim_bounty, check_wallet_balance, and memory_search; marketplace actions go through the mltl CLI in src/moltlaunch/cli.ts. When AgentCash is enabled, agentcash_fetch and agentcash_balance are also available. Completed-task ratings and comments are stored, while idle study sessions in loop/study.ts create feedback-analysis, specialty-research, or task-simulation knowledge entries. The local HTTP server serves /api/* JSON endpoints plus the React dashboard.
- A Moltlaunch service operator who wants a local process to assess incoming work, quote in ETH, and submit deliverables.
- A provider handling React, TypeScript, or code-review work who wants customer ratings turned into searchable context for later tasks.
- A team with its own task API that is willing to modify src/moltlaunch/cli.ts, src/tools/marketplace.ts, and src/heartbeat.ts while retaining the LLM loop and dashboard.
- A solo operator who needs a local dashboard for active tasks, ratings, wallet balances, event logs, and learned knowledge.
- An operator with an AgentCash wallet who wants the agent to make paid search, scraping, image-generation, or other external API calls while performing work.
How do you install or deploy this agent?
Install the global package with npm install -g cashclaw-agent, then install the required Moltlaunch CLI with npm install -g moltlaunch. Run cashclaw and open http://localhost:3777. Complete the wallet, onchain agent, LLM, and configuration wizard; the LLM step requires credentials for Anthropic, OpenAI, or OpenRouter and performs a live test call.
How do you use this agent?
Use the wizard to set the agent name, description, skills, and pricing, then choose an LLM provider and model. Configure autoQuote, autoWork, maxConcurrentTasks, polling intervals, learning, and pricing strategy; the dashboard launches and task monitoring begins. For requested work, the agent can quote, decline, or message; for accepted or revision work, it produces a deliverable and calls submit_work. To use AgentCash, run npm install -g agentcash, npx agentcash wallet create, and npx agentcash wallet deposit, then enable it in Settings > Automation > AGENTCASH.
What are this agent's strengths and limitations?
- Combines task monitoring, LLM tool execution, quoting and delivery, ratings feedback, and scheduled learning in one local Node.js process.
- Supports Anthropic, OpenAI, and OpenRouter through raw fetch-based adapters rather than provider SDK dependencies.
- Uses BM25+ retrieval with temporal decay to inject the five most relevant knowledge or feedback entries for a task, rather than merely recent entries.
- Includes a hot-reloading local dashboard for tasks, events, memory, feedback, balances, and direct operator chat.
- The default workflow depends on Moltlaunch, the mltl CLI, a Base wallet, and Moltlaunch's task model; other platforms require edits in three documented integration areas.
- The agent can invoke tools with external effects, including quoting, submitting work, messaging, and claiming bounties, so automation and pricing settings need careful control.
- AgentCash is optional but paid: its external API calls consume USDC, with documented typical calls ranging from $0.005 to $0.05.
- The task loop defaults to a maximum of 10 tool-use turns, and the documentation does not describe an automatic recovery or retry strategy beyond that limit.
How does this agent compare with similar options?
Moltlaunch is CashClaw's default task frontend. Marketplace coupling is concentrated in src/moltlaunch/cli.ts, src/tools/marketplace.ts, and src/heartbeat.ts. The documentation names Fiverr, Upwork, a custom API, database queries, and a local folder watcher as possible replacements, but each requires integration code.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| CashClaw This agent | 42 · Major gaps | CLIFree + model costs | ★ 1.2k | 6mo ago | TypeScript | OpenAI API · Claude API |
| Bubble Lab | 58 · Major gaps | Web appFreemium | ★ 1.1k | 5mo ago | TypeScript | — |
| Clawd Cursor | 74 · Some gaps | MCP serverFree + model costs | ★ 402 | today | TypeScript | Codex · Claude Code |
| Atomic Agent | 56 · Major gaps | CLIFree + model costs | ★ 2.5k | 1d ago | TypeScript | — |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence shows: tools execute external operations via CLI, but least privilege is not explicitly addressed; auto-quote and auto-work toggles exist but default on, lacking user confirmation; data flow is described in README but sensitive data handling is not detailed; dependencies are few but no security audit; external effects include submitting quotes and work, but rollback is not addressed; source attribution is via README and package.json author, but publisher unverified. Deductions: lack of explicit least privilege, user confirmation, sensitive data protection details, dependency security audit, rollback, and source verification.
Evidence shows: README and code structure are consistent; tests cover core loop, but external CLI and API dependencies are not verified for availability; failure messages are present in tests but actual error handling is not detailed. Deductions: external dependencies without availability guarantees; incomplete failure message handling.
Evidence shows: README describes multiple use cases including custom task sources; capability boundaries are defined via tool list and configuration; trigger precision is controlled by task status and polling intervals; environment fit is described via Node.js and CLI dependencies. Deductions: trigger precision relies on external events, not detailed; environment fit lacks detailed system requirements.
Evidence shows: README provides detailed information architecture and install notes; naming is stable but version is only 0.1.0; examples and FAQ are sparse; known limitations not explicit; license is MIT; no changelog; maintenance responsibility unclear. Deductions: missing changelog, known limitations, FAQ; maintenance responsibility unclear.
Evidence shows: output is usable work products submitted via tools; marginal value lies in automating work flow; cost-benefit not analyzed in detail but pricing strategy provided. Deductions: insufficient cost-benefit analysis, no actual run data.
Evidence shows: README claims align with code structure, but no external verification; tests cover core functionality but not independently verified; facts and inferences not clearly separated. Deductions: lack of external verification and fact/inference separation.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Auto-quote and auto-work are enabled by default, which may execute external actions without user confirmation; configure carefully.
- Relies on external CLIs (mltl, agentcash) and APIs whose availability and security are unverified.
- Sensitive data (e.g., API keys) stored in config file without encryption or protection.
- No rollback mechanism; once work or quotes are submitted, they may not be reversible.