#benchmark — Claude Updates

Claude Skill 14

A benchmarking harness for coding agents.

Python MIT Updated 2w ago

swival 0 0

MCP Server 6

An Agent Infra Benchmark Suite for Agentic Tool Serving (AgentCore, Lambda, GCP, AgentRun, E2b etc.)

Python Apache-2.0 Updated 3w ago

tanksys 0 0

MCP Server 119

An MCP server that lets LLM agents play Civilization VI.

Python MIT Updated 4w ago

lmwilki 0 0

MCP Server 1.6k

Quickly find bottlenecks in Rust - one profiler for CPU, time, memory, SQL and async code.

Rust MIT Updated 1w ago

pawurb 0 0

MCP Server 443

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

Python Apache-2.0 Updated 1mo ago

eval-sys 0 0

MCP Server 312

Standardized environment infrastructure for Agentic AI development.

Python Apache-2.0 Updated 1w ago

inclusionai 0 0