Results for “benchmarking”

The best-benchmarked open-source memory system for AI coding assistants

BGI tries to group code based on what the code actually does (its behavior), not just which file imports what.

Durable hybrid memory for AI agents: vector + BM25 + temporal + graph recall, exposed through MCP, HTTP, and Python.

MCP server for Claude Code and Codex. One tool call replaces ~42 minutes of agent exploration

Bilig WorkPaper: headless spreadsheet formula engine and MCP server for Node agents: complete spreadsheet work autonomou

Turn any web page into traceable, citable evidence for AI agents.

Fast Python web crawler for RAG and AI ingestion. Extracts clean Markdown from any site for LLMs and vector stores.

Graph-based tool retrieval for LLM agents — 248 tools → 82% accuracy, 79% fewer tokens. Zero dependencies. OpenAPI / MCP

AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL o

Diagnose, secure, and benchmark your MCP servers. Zero-config CLI for Claude Code, Cursor, VS Code, and Windsurf.

Universal LLM router for AI coding tools. Works with Claude Code, Cursor, Codex, Gemini CLI, Copilot and more.

OpenCode skill for creating, testing, and optimizing other OpenCode skills. Adapted from Anthropic's skill-creator for C

NEXO Brain — Shared brain for AI agents. Persistent memory, semantic RAG, natural forgetting, metacognitive guard, trust

GPT Image 2 prompt gallery, image prompt library, agentic skill, and CLI for OpenAI image generation/editing

Open-source runtime security and governance for AI agents, MCP tools, robotics, industrial automation, and physical AI.

Python SDK for WaveGuard physics-based anomaly detection API. One call. Any data.

The MCP server that turns Claude into the only coding agent hitting 100% on a real benchmark. -77% active tokens, -76% w

Computer Experience Layer — MCP server for native computer use on macOS. Structured perception, reliable actions, contin

Screen-reader navigation cost analyzer — models the real effort to discover, reach, and operate interactive web content

AI-powered code generator for Arbitrum Stylus, SDK bridging, dApps & Orbit chains — 19 MCP tools with RAG

Python SQL Parser and Transpiler

Universal MCP Gateway - Single-port multiplexing with Meta-MCP for ~95% context token savings

MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollam

SWI-Prolog as a logic calculator for LLMs — MCP server and Python library

LLM readiness linter for websites. Audits robots.txt, llms.txt, Schema.org, and content density on a 0-100 scale. Includ

cosmergon-agent

Privacy-first developer intelligence — surfaces what matters from the noise

Live context engine for AI assistants — resolve-before-context, session waypoints, and tool-selection intelligence for H

Persistent memory for AI agents. Agents forget. CI remembers.

memstate-mcp

A Model Context Protocol (MCP) server that provides access to remote job listings and company information from Himalayas

Agent governance for ThumbGate: 👍/👎 become Pre-Action Checks that block repeat mistakes before code, money, or custome

Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demoted. pip i

Claude Code skill for YouTube creators — channel audits, video SEO, retention scripts, thumbnails, content strategy, Sho

Spanish dialect localization MCP server and CLI. Translate across 25 regional variants with register control, structure

PDF extraction that checks its own work. #2 reading order accuracy — zero AI, zero GPU, zero cost.

Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistak

CogmemAi — Cognitive Memory for Any Ai System. Autonomous robots, self-driving vehicles, defense systems, coding assista

Open-source Claude Code skills, agents, and slash commands for AI-powered penetration testing, bug bounty hunting, and s

ArcadeDB Multi-Model Database, one DBMS that supports SQL, Cypher, Gremlin, HTTP/JSON, MongoDB and Redis. ArcadeDB is a

Alcove is an MCP server that gives AI coding agents on-demand access to your private project docs — BM25 + vector hybrid

MCP server for the Ejentum API. 8 cognitive operations across 4 harnesses (reasoning, code, anti-deception, memory) in d

An LLM-first SEO analysis skill for Antigravity, Codex, Claude with 16 specialized sub-skills, 10 specialist agents, and

A memory engine for conversational AI agents, inspired by neuroscience and Buddhist psychology