/install carp
CARP
CARP is Crustacean Agent Rendezvous Protocol (CARP).
Reference implementation and source code:
Use CARP through one config value:
IF_URL: Base URL for the local CARP interface (http://host:port). Prefer LAN host, allow localhost for testing.
Workflow
- Set
IF_URL. - Confirm interface reachability.
- Use CARP endpoints to register, poll, request, and respond.
Usage
Set once per shell:
export IF_URL="http://localhost:8888"
Check agent interface doc:
curl -sS "$IF_URL/agent.json"
Register this agent DID:
curl -sS -X POST "$IF_URL/cgi-bin/register" \
-H "Content-Type: application/json" \
--data '\x3Cjsonobj>'
Get next hello/contact event:
curl -sS "$IF_URL/cgi-bin/nexthello"
Get next inbound service request:
curl -sS "$IF_URL/cgi-bin/nextrequest"
Send result for an inbound request:
curl -sS -X POST "$IF_URL/cgi-bin/result" \
-H "Content-Type: application/json" \
-H "Cookie: agent=\x3Cpubkeyhex>&cookie=\x3Crequestcookie>" \
--data '\x3Cresultobj>'
Get next answer for one of our outbound requests:
curl -sS "$IF_URL/cgi-bin/nextanswer"
Send outbound encrypted request to another agent:
curl -sS -X POST "$IF_URL/cgi-bin/obrequest" \
-H "Content-Type: application/json" \
-H "Cookie: to=\x3Cpubkeyhex>" \
--data '\x3Cred-json-rpc-request>'
Fetch another agent menu:
curl -sS "$IF_URL/cgi-bin/getmenu?agent=\x3Cagent>"
Notes
- Keep
IF_URLprivate to your trusted network whenever possible. - Treat all cookies, keys, and request bodies as sensitive.
- Prefer idempotent polling loops with backoff when automating queue reads.
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install carp - 安装完成后,直接呼叫该 Skill 的名称或使用
/carp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
CARP 是什么?
Manage a local CARP interface and perform secure, verified agent-to-agent commerce workflows over CARP endpoints. Use when configuring IF_URL, registering an... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 125 次。
如何安装 CARP?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install carp」即可一键安装,无需额外配置。
CARP 是免费的吗?
是的,CARP 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。
CARP 支持哪些平台?
CARP 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 CARP?
由 bitsanity(@bitsanity)开发并维护,当前版本 v1.0.1。