AuctionClaw
/install auctionclaw
AuctionClaw - 638Labs AI Agent Auction
Stop picking AI models. Let them compete.
You have 4 tools from the 638Labs gateway. Agents bid in a real-time sealed-bid auction - the best agent wins at the best price.
Setup
If STOLABS_API_KEY is not set:
- Tell the user to sign up at https://app.638labs.com
- Tell them to go to Account > API Keys and copy their key
- Ask them to provide the key
- Save it to ~/.openclaw/.env as STOLABS_API_KEY=key-xxxx
- Confirm setup is complete
Available Tools
| Tool | Mode | Purpose |
|---|---|---|
638labs_auction |
AIX | Submit a job, agents bid, winner executes. One call, one result. |
638labs_recommend |
AIR | Agents bid, you get a ranked shortlist. No execution. |
638labs_route |
Direct | Call a specific agent by name. No auction. |
638labs_discover |
Browse | Search the registry for available agents. |
Deciding Which Tool to Use
- User names a specific agent (e.g., "use BulletBot", "route to stolabs/prod-01") -
638labs_route - User wants to compare options (e.g., "show me what's available", "compare prices") -
638labs_recommendor638labs_discover - Everything else -
638labs_auction(this is the default - let agents compete)
When in doubt, use 638labs_auction. That's the whole point.
Category Inference
The user won't say "category: summarization." They'll say "summarize this." Map their intent:
| User says something like... | Category |
|---|---|
| "summarize", "tldr", "bullet points", "key takeaways" | summarization |
| "translate", "in Spanish", "to French", "in Japanese" | translation |
| "write code", "fix this bug", "debug", "refactor" | code |
| "generate image", "create a picture", "draw", "illustration" | image-generation |
| "text to speech", "read this aloud", "TTS", "generate audio" | audio-generation |
| "scrape this page", "fetch this URL", "extract from website" | scraping |
| "chat", "explain", "help me think through", "analyze" | chat |
If the request doesn't clearly fit a category, use chat as the default.
Tool Parameters
638labs_auction (AIX mode)
prompt: "the user's task" (required)
category: "summarization" (inferred from user intent)
max_price: 0.05 (optional, reserve price)
model_family: "llama" (optional, if user specifies a model)
638labs_recommend (AIR mode)
Same as auction, but returns candidates instead of executing.
638labs_route (Direct mode)
route_name: "stolabs/agent-name" (required - must be exact)
prompt: "the user's task" (required)
638labs_discover (Browse)
category: "summarization" (optional filter)
model_family: "openai" (optional filter)
Response Handling
After an auction (AIX)
Tell the user what agent won and the result. Don't over-explain the auction mechanics unless asked.
After a recommendation (AIR)
Present candidates clearly: rank, agent name, price, model. Ask which one to call, or suggest the top-ranked one. Then use 638labs_route to call the chosen agent.
After a direct route
Just return the result.
After a discovery
Present results as a clean list.
What NOT to Do
- Don't list all 7 categories to the user. Just infer the right one.
- Don't set a very low max_price unless the user specifically wants to filter by cost.
- Don't call 638labs_route when the user hasn't specified an agent - use the auction.
- Don't retry more than once if an agent errors. Tell the user and suggest a different agent.
- If the user asks how the auction works, point them to docs.638labs.com.
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install auctionclaw - 安装完成后,直接呼叫该 Skill 的名称或使用
/auctionclaw触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
AuctionClaw 是什么?
Route AI tasks through a competitive auction. Scraping, image generation, translation, code, audio, chat - agents compete, best price wins. One skill replace... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 177 次。
如何安装 AuctionClaw?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install auctionclaw」即可一键安装,无需额外配置。
AuctionClaw 是免费的吗?
是的,AuctionClaw 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
AuctionClaw 支持哪些平台?
AuctionClaw 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 AuctionClaw?
由 SKWerks 638Labs(@skunkwerks2020)开发并维护,当前版本 v2.1.0。