MCP servers and skills: search, filter by where they run, and compare.
Nothing matches every word exactly, so these are the closest matches.
SWE-bench repository patch localizer and regression verifier (Devin SWE style)
SkillLink only★ 8
Automated benchmark patch verification harness & fail-to-pass matrix (SWE-bench)
SkillLink only★ 8
MCP connector for BenchFleet: let AI agents use your real Android phones safely, with permissions, approvals and an audit log.
MCPLink onlyFew stars
Microsoft Build AI 2026 National 1st Place. Local codebase memory for AI coding agents: 63.8% Coverage@5, 75.2% Coverage@10, 60-65x lower context.
MCPLink only★ 16
AST code fault localization & regression test patch synthesizer (SWE-Bench)
SkillLink only★ 8
High-performance AI-native shell, process executor, snapshot engine, and MCP server in Rust.
MCPLink onlyFew stars
An Investigation Across Two MCP Servers, Two Frontier Models, and 20 Controlled Benchmark Runs
MCPLink onlyFew stars
Real-time LLM inference throughput profiler & benchmark (Inferock Bench style)
SkillLink only★ 8
Agent-Computer Interface SWE patch synthesizer & automated bug fixer (SWE-agent style)
SkillLink only★ 8
Public MemQ benchmark repository for reproducible memory, retrieval, and coordination proof.
SkillLink only★ 7
Benchmark comparing MCP server implementations in Python, Rust, Go, TypeScript, and C# — proxy vs compute patterns over Streamable HTTP
MCPLink only★ 1Few stars
Transport-cost micro-benchmark: in-process vs MCP-shaped stdio JSON-RPC (companion to the tools/MCP/skills essay)
MCPLink onlyFew stars
Real-world AI task evaluation & custom benchmark runner (oqoqo style)
SkillLink only★ 8
Mobile gaming & app cohort ROAS, retention & payback benchmarker
SkillLink only★ 9
Autonomous software engineering SWE agent and repo refactor debugger (Cognition Devin style)
SkillLink only★ 8
Constitutional AI harmlessness benchmark and RLAIF safety evaluator (Anthropic style)
SkillLink only★ 8
Distributed model serving platform & Elo benchmark arena (FastChat style)
SkillLink only★ 8
Comprehensive prompt evaluation and LLM output benchmarking suite
SkillLink only★ 9
A Model Context Protocol (MCP) plugin for analyzing and comparing CPU benchmark ratings.
MCPLink onlyFew stars
Real-world agent task evaluation & benchmark harness synthesizer (oqoqo style)
SkillLink only★ 8
Mode VC Startup Distribution Moat & Pre-Seed Valuation Benchmarks MCP Server + 3,650+ VC Investor Atlas
MCPLink onlyFew stars
Measure any code repository, at any commit, through any retrieval engine — with the sample sizes attached.
MCPLink only★ 1Few stars
Public reference implementation and benchmark suite for evaluating Robbie’s Razor™ compliance, recursive stability, compression efficiency, and constrained AI reasoning systems.
MCPLink onlyFew stars
LLM outputs validation factuality checker
SkillLink only★ 9
Who stands behind it
