AgentFlocks/flocks

Flocks is an agentic SecOps platform.

What it solves

Flocks is an AI-native SecOps platform designed to automate and assist with security operations tasks. It provides a structured environment where multiple AI agents can collaborate to plan and execute security-related workflows, reducing the manual effort required for complex SecOps processes.

How it works

The platform utilizes a multi-agent system consisting of specialized agents (such as build, plan, and general agents) that collaborate to solve tasks. It integrates a wide array of tools, including bash execution, file operations, code search, and Language Server Protocol (LSP) support. The system is powered by a FastAPI-based HTTP API server and supports various LLMs from providers like Anthropic, OpenAI, and Google. Users can interact with the platform via a browser-based WebUI or a modern terminal user interface (TUI).

Who it’s for

It is built for security operations (SecOps) professionals who want to leverage AI agents to automate technical security tasks and manage them through a centralized platform.

Highlights

  • Multi-Agent Collaboration: Uses a coordinated system of agents to handle planning and execution.
  • Extensive Tooling: Includes built-in support for bash, file system operations, and the Model Context Protocol (MCP).
  • Flexible Interface: Offers both a WebUI and a TUI for different user preferences.
  • Broad Model Support: Compatible with multiple leading AI model providers.
  • Enterprise-Ready Deployment: Supports local installation, Docker deployment, and includes robust session and authentication management.

Related

  • Project
    Kritt-ai/open-kritt

    An open-source security research platform that orchestrates AI agents to find, validate, and rank vulnerabilities in code through focused, parallelized workflows.

  • Project
    bgdnvk/clanker

    An AI-powered DevOps CLI that allows users to manage, query, and deploy cloud infrastructure and Kubernetes clusters using natural language agents.

  • Project
    Simpleyyt/ai-manus

    A general-purpose AI agent system that executes tasks in a secure Docker sandbox, supporting real-time browser and code execution.

  • Project
    kgoedecke/doop

    Doop is an open‑source, real‑time design canvas where humans and AI agents (via Claude Code or a built‑in Doop Agent) edit HTML frames together. It offers live multiplayer features, AI‑driven design tasks, private sharing, and can be self‑hosted with a single Docker command or `bun run dev`. The AI backend works with Anthropic (free tier) or user‑provided OpenAI/ChatGPT keys.

  • Project
    opensandbox-group/OpenSandbox

    OpenSandbox is an open‑source sandbox platform for AI agents and other code‑execution workloads. It offers multi‑language SDKs, a CLI, and a server that can run sandboxes on Docker locally or on Kubernetes at scale, with strong isolation (gVisor, Kata, Firecracker), network policies, and a credential vault. Use cases include coding agents, browser/desktop automation, RL training, and secure code‑execution services.