SuperAPI AI Directory
Partner with us中文AI newsFavorites

AI agents

2,963 results · Page 31 of 83

Agent-Wiz

AI agents

Agent-Wiz is a Python command-line tool for extracting agent workflows from mainstream AI frameworks such as LangGraph, AutoGen, and CrewAI, visualizing them, and automatically performing security threat assessments based on threat modeling methodologies such as MAESTRO. It is aimed at developers, researchers, and security teams, helping to clarify the relationships among agents, tools, and data flows in complex LLM orchestration, identify potential vulnerabilities, and generate security reports. Agent-Wiz requires an OpenAI API key to be configured in order to run analysis commands. Related framework parsers, standardized graph representations, security report generation, analysis for additional threat models such as STRIDE/PASTA/LINDDUN, and agent simulation-based threat exploration are still planned or under development.

Read more

Agent37

AI agents

Agent37 is an infrastructure platform that provides isolated sandbox hosting for AI agents. Each customer gets an independent sandbox, supports running any agent framework, is billed by the minute, and costs as little as 95% less than most sandbox providers. The platform offers persistent disks, a real Linux environment, browser and desktop access, state sleep and wake, automatic backups, usage monitoring, and spending limits, and ensures security through gVisor kernel isolation, an egress firewall, and encryption at rest. It is suitable for development teams and startups that need to build agent products for multiple tenants.

Read more

Agent4Rec

AI agents

Agent4Rec is a recommender system simulator implemented based on the paper "On Generative Agents in Recommendation" (SIGIR 2024 perspective). It contains 1,000 LLM-powered generative agents initialized from the MovieLens-1M dataset, with diverse social characteristics and preferences. Each agent interacts with personalized movie recommendations in a page-by-page manner and performs actions such as watching, rating, reviewing, exiting, and being interviewed. The simulator aims to explore the potential of LLM-empowered generative agents to simulate realistic, independent human behavior in recommendation environments, and supports multiple recommender systems (such as Random, Pop, MF, MultVAE, LightGCN) and different simulation configurations.

Read more

AgentForge

AI agents

AgentForge is a low-code framework for rapidly developing, testing, and iterating AI-driven autonomous agents and cognitive architectures. Its core concepts include flexible Agents, declarative Cogs, and optional Memory, supporting everything from simple first runs to complex multi-agent orchestration. It is compatible with a variety of LLM models, including OpenAI, Google Gemini, Anthropic Claude, as well as local models running via Ollama or LMStudio, and allows different models to be run for different agents.

Read more

agentify

AI agents

Agentify is an open-source command-line tool developed by MonadWorks for compiling OpenAPI/Swagger specifications into multiple interface files for AI agents. Starting from a single OpenAPI specification, it can generate up to 9 output formats, including MCP server, CLAUDE.md, AGENTS.md, .cursorrules, Skills, llms.txt, GEMINI.md, A2A, and CLI. The tool parses the specification into an intermediate representation, AgentifyIR, then generates artifacts in each format through pluggable emitters, and performs security scanning (input sanitization, prompt injection pattern detection, generated code scanning) before writing to disk. It is suitable for developers who want their APIs to be callable by AI agents, supports Swagger 2.0 and OpenAPI 3.x, and can handle APIs ranging from small (13 endpoints) to very large (1000+ endpoints).

Read more

AgentK

AI agents

AgentK is a self-evolving, modular autonomous agent AGI system, in which multiple agents collaborate and new agents can be built on demand to complete tasks. In its name, "K" stands for kernel, and the goal is to bootstrap itself with only the minimum agents and tools, then gradually grow its own "mind." AgentK's mind consists of two parts: the agents that collaborate to solve problems, and the tools used by the agents to interact with the external world. Both are developed as ordinary Python files (located in the agents and tools directories), making it easy to track progress and contribute. The system contains four core agents: Hermes is responsible for interacting with humans to understand goals, managing task creation and assignment, and coordinating other agents; AgentSmith is the architect, responsible for creating and maintaining other agents, ensuring they are equipped with the necessary tools and testing their functionality; ToolMaker is the tool developer, creating and optimizing the tools needed by agents to perform tasks; WebResearcher is the knowledge collector, conducting in-depth online research to provide the latest information and help agents make informed decisions. AgentK is built on the LangGraph and LangChain frameworks and runs in an isolated Docker container, requiring the latest version of Docker to be installed. To use it, copy .env.template to .env and set the environment variables.

Read more