synnada-ai/recurse-agents
v0.4.0Apache-2.0
Build reusable agentic workloads. Explore alternatives and check results with serverless execution on Recurse. Expose as MCP or run to completion.
plugin.json
- name
- recurse-agents
- version
- 0.4.0
- description
- Build reusable agentic workloads. Explore alternatives and check results with serverless execution on Recurse. Expose as MCP or run to completion.
- author
- Synnada
- license
- Apache-2.0
- homepage
- https://recurse.run
- extensions
- com.openai
plugin.json
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "recurse-agents",
"version": "0.4.0",
"description": "Build reusable agentic workloads. Explore alternatives and check results with serverless execution on Recurse. Expose as MCP or run to completion.",
"author": {
"name": "Synnada"
},
"homepage": "https://recurse.run",
"license": "Apache-2.0",
"extensions": {
"com.openai": {
"interface": {
"displayName": "Recurse Agents",
"shortDescription": "Build reusable agents",
"longDescription": "Your coding agent uses Recurse to define Python tools and checks around a task. An LLM calls those tools to explore alternatives and refine results. Execution is serverless: expose the workload as an MCP server for use in agentic workflows, or run it to completion. Requires the Recurse SDK and a Recurse account.",
"developerName": "Synnada",
"category": "Productivity",
"capabilities": [],
"defaultPrompt": [
"Design a Python workload that tests code changes against a benchmark.",
"Plan a Recurse workload that generates puzzle levels and checks solvability.",
"Help me expose a tested Recurse workload through MCP."
],
"websiteURL": "https://recurse.run",
"brandColor": "#5c3df5",
"composerIcon": "./assets/recurse-icon.png",
"logo": "./assets/recurse-logo.png"
}
}
}
}
What else this package ships
These files come with the package and this site does not publish them. They are listed so you know what is there before you install it.
- LICENSE
Client extensions
Data this package carries for particular clients. The directory lists the clients named and never reads what is addressed to them.
- com.openai