Recurse
Serverless agentic workloads.
@Recurse Help me experiment with different agent configurations, evaluate them on my task, and find the best-performing setup.@Recurse Build a serverless workload that tries different code optimizations, benchmarks them, and returns the best result.@Recurse Help me turn my Python functions into tools and expose them through MCP.
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.
Įgūdis
Informacija
- Galimybės
- Python, Serverless, Tool development, MCP deployment, Self-Improvement, Agent deployment
- Kūrėjas
- Synnada
- Kategorija
- Productivity
- Versija
- 0.2.2