AI Agents Made Simple.
Just YAML. No Code.

Build and run AI agents with a single config file. Supports multi-agent orchestration, RAG, and the A2A protocol.

hector-server — -zsh — 80x24

Your Agents. Your Infrastructure. Your Privacy.

Built on open standards. Deployed on your terms.

Open & Auditable MIT licensed. No hidden telemetry. Audit every line.
Deploy Anywhere On-premise, air-gapped, or cloud. No lock-in.
Built-in Security Guardrails, JWT auth, PII redaction, and tool sandboxing.

Integrate with your SSO via JWT, enable prompt injection detection and PII redaction with declarative guardrails, and sandbox command execution—all without writing code.

A2A-Native Federation

Hector is built on the Agent-to-Agent (A2A) protocol. Unlike traditional systems with central orchestrators, Hector enables true peer-to-peer federation.

Agents communicate directly, forming federated networks where each agent maintains autonomy while collaborating seamlessly. Hector is proudly listed as an A2A Compatible Framework.

RAG Ready

Hector comes RAG-ready out of the box. Connect SQL databases, APIs, and document stores to build comprehensive knowledge bases.

Choose from Ollama, OpenAI, or Cohere embedders to convert your data into vectors, automatically indexed into vector databases like Qdrant. Agents retrieve relevant context using semantic search, augmenting their responses with accurate, context-aware answers.

Meet Hector Studio

Hector Studio is your visual command center to design, try, and deploy agents with confidence. Whether connecting to a remote production mesh or managing local workspaces, it provides a powerful X-ray view into your system, allowing you to debug message flows, inspect tool executions, and orchestrate complex workflows in real-time.

Download Studio Read the Docs

Programmatic API

Need full control? Hector's programmatic API allows you to build agents, define tools, and orchestrate complex workflows entirely in Go.

Seamlessly mix configuration and code. Embed Hector directly into your applications with a clean, fluent interface.

Read the Guide API Reference

import "github.com/verikod/hector/pkg/builder"

func main() {
    // 1. Build LLM
    llm := builder.NewLLM("openai").
        APIKey(os.Getenv("OPENAI_API_KEY")).
        MustBuild()

    // 2. Build Agent
    agent, _ := builder.NewAgent("assistant").
        WithLLM(llm).
        WithInstruction("You are a helpful assistant.").
        Build()

    // 3. Run
    runner, _ := builder.NewRunner("app").WithAgent(agent).Build()
    runner.Run(ctx, "user", "session", input, ...)
}

Features

Zero-Code Configuration

Pure YAML agent definition. No Python/Go required—define sophisticated agents declaratively.
Metrics & Tracing

Built-in Prometheus metrics and OpenTelemetry tracing. Monitor latency, token usage, and errors.
Guardrails & Security

Prompt injection detection, PII redaction, tool authorization, JWT auth, and command sandboxing.
Hot Reload

Update configurations instantly. Changes are detected and applied with zero downtime for rapid iteration.
Studio Mode

Built-in visual dashboard to interact with tools, debug agents, and visualize message flows in real-time.
Workflow Agents

Design complex, multi-step agent behaviors with loops, conditionals, and sub-agent orchestration.
A2A Protocol Native

Standards-compliant agent communication and federation for distributed, interoperable deployments.
Lightweight

Single 30MB binary with fast startup. No runtime dependencies.
Scalable RAG

Turn any folder or database into a knowledge base with automated chunking, embedding, and vector search.

AI Agents Made Simple. Just YAML. No Code.