Results for “judges”

Regression testing for AI agents. Snapshot behavior,diff tool calls,catch regressions in CI. Works with LangGraph, CrewA

Academic Research Skills for Claude Code: research → write → review → revise → finalize

Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.

Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contrad

@erezweinstein5

A Claude Code skill that adds a rubric-based eval layer to any agent project. Framework-agnostic — generates rubric, tes

Production-grade Playwright + TypeScript QA framework with AI-powered testing, LLM-as-Judge evaluation, MCP server, 7 CL

Autoresearch ALL THE THINGS. RLVR for the masses.

Build Claude Code–style deep agents in Python: tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints

Bioinformatic MCP server that wraps the most useful functions of the gget library

World-class product planning AI skill for Claude Code — 22 PM frameworks, 6 modes, 6 languages. From idea to dev handoff

Four reusable dynamic-workflow templates for Claude Code (multi-dimension review, exhaustive audit, budget-scaled bug hu

clarifyprompt-mcp

Open-source Claude Code alternative. Provider-agnostic, MIT licensed. Native Claude Code hook/plugin compatibility.

Reproducible evaluation for AI coding agents. Multi-turn scenarios against Claude Code, Codex, Copilot, Cursor, Gemini C

一个生产级的深度研究 Agent 系统，从零构建多智能体编排、Red-Blue 对抗降噪、 语义级上下文压缩、跨 Agent 共享记忆四大核心能力，配套 165 次独立实验 + Bootstrap 统计显著性检验的完整评测体系。

An AI co-worker with its own computer. Self-evolving, persistent memory, MCP server, secure credential collection, email

MCP prompt template server: hot-reload, thinking frameworks, quality gates

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

Evidence-first multi-agent debate skill: get a second opinion by pitting Codex × Claude Code (or GLM/DeepSeek/Qwen) to i

AI-operable research workspace for Zotero, Obsidian, and NotebookLM. Use any two, or all three, through CLI, MCP, REST,

Self-growing multi-agent system: Gemma Orchestrator + Qwen Executor + Claude Escalation + Skill Factory

Multi-agent code review mesh — orchestrates AI agents from multiple providers to review code in parallel, cross-review e

Most AI agents forget you the moment the tab closes. Constellation Engine gives them a hippocampus — a living star map w

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and e

LLM-as-judge evaluation framework for assessing AI agent output quality

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Con

LLM Council works together to answer your hardest questions

Claude Code skill: Run decisions, code, and plans through a council of 5 AI advisors with anonymous peer review. Based o

Lightweight Long-Term Memory for LLM Agents.

🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous wor

Metatron is a self-hosted system that captures a codebase's real implementation decisions — preferred patterns, rejected

A Claude Code plugin that gives Claude persistent memory across sessions — stores lessons and decisions as markdown in y

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over

Universal long-term project memory for AI coding agents — Claude Code, Cursor, Windsurf, Cline + 4 more. TDD rules, code

Monitor the Model Context Protocol (MCP) Registry for new, updated, and removed servers. Get real-time notifications via

Convert GitHub repositories to MCP servers automatically. Extract tools from OpenAPI, GraphQL & REST APIs for Claude Des

Persistent memory for Claude Code & Codex CLI. Auto-extracted knowledge graph, multi-representation embeddings, 3D WebGL

Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.

Samurai-inspired multi-agent system for Claude Code. Orchestrate parallel AI tasks via tmux with shogun → karo → ashigar

Cut your Claude / OpenAI / Gemini bill 70–95% on AI coding. Local proxy that compresses context, keeps provider caches h

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

Agentic QA boilerplate built on Playwright + KATA + TypeScript. Multi-agent skills following the agentskills.io spec, or

Remote-control Unity Editor from any AI IDE — 62 tools including AI-powered profiling & light probes. File-based IPC, ze

AI powered automation toolkit which acts as an agent that discovers MCP servers for you. Point it at GitHub/npm/configur

总结Prompt&LLM论文，开源数据&模型，AIGC应用