Search

Testing and evaluation platform for LLM agents — hybrid metrics, multi-agent simulation, and iterative prompt improvement.

AI model: jbishop914/ue5-agent-qwen3b-merged

AI model: AgentAnon/gemma-4-26B-A4B-it-uncensored

AI model: SawinuCP/bus_booking_voice_agent_merged

The Open Authorization Standard for AI Agents. Framework-agnostic tool permissions, identity verification, scoped access control, and audit logging for any AI agent.

Build, deploy, and connect AI agents to SAP Joule via the A2A protocol on BTP Cloud Foundry — directly from Claude Code. Supports TypeScript (Express or CAP) and Python agents with LangGraph and SAP GenAI Hub.

Visual drag-and-drop editor for your real codebase. Click, drag, resize, edit text in the browser. Claude writes the code. Works with any framework.

🦜 The AI agent framework that actually works. 15 platforms, 14 providers, 200+ models. Ultra-fast, ultra-cheap.

Browse and manage Bilibili videos, users, and favorites directly from the command line with a fast, lightweight CLI tool.

Package manager for AI coding assistants — manage skills, agents & MCPs across Claude Code, Codex, Copilot, and Cursor

The context-engineering OS for multi-agent Claude Code projects. Template + discipline that runs PA·co (22 agents, production SaaS) distilled for your team.

A zero-dependency Claude Code PreToolUse guard that blocks destructive shell commands before they run.

自进化量化选股系统 — Kronos K线预测模型 + Hermes Agent 自进化闭环 + A股三池漏斗选股

Agentic LLM system for binary exploitation using MCP tools and pwntools

OpenAPI-style breaking-change detection for LLM tool contracts.

Persistent decision memory for any project. Karpathy's LLM Wiki, productized.

Automatic repair for failing Python code, powered by any LLM.

CLI for Orbit — the skill & persona registry for AI agents

Ezent platform CLI for human developers and AI agents. No disk persistence — credentials come from CLI flags or env vars only.

72 Solana, EVM, Deep42, and perp-risk endpoints for AI agents