convez.ai
MCP ServerDevOps & InfraestruturaAvançado
agentbreeder

AgentBreeder

agentbreeder/agentbreeder

Um YAML, qualquer framework, qualquer cloud — governança automática para agentes IA

Ver no GitHub
InicialPluginScore · de 0 a 100

Plataforma agnóstica de frameworks para construir, deployar e governar agentes IA em escala corporativa. Define uma vez em YAML e implante em qualquer cloud (AWS, GCP, Azure, K8s) com RBAC automático, rastreamento de custos e auditoria integrada.

Instalação

$npx convez-ai agentbreeder/agentbreeder

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
4
Forks
10
Acompanhando
1
Saúde
87%
Último commit
há 1 dia
Versão
v2.7.3
Issues abertas
67
Contribuidores
5

Casos de uso

  • Implantar agentes com LangGraph, CrewAI, Claude SDK ou OpenAI Agents de forma unificada
  • Implementar RBAC, rastreamento de custos e auditoria sem configuração manual
  • Evitar duplicação de agentes com registro organizacional de descoberta

Veredito

Solução madura e bem-arquitetada para quem precisa escalar agentes IA em ambiente corporativo. Elimina overhead de governança com estrutura de pipeline, não configuração — excelente para times com múltiplos agentes e requisitos de compliance.

README

A tradução para o português deste README ainda está na fila.

AgentBreeder™ — v2.0

The only agent platform that doesn't pick a winner.

Build with anyone's framework. Deploy to anyone's cloud. Govern automatically. One YAML, one command — Apache 2.0, no vendor lock-in.

PyPI PyPI Downloads npm Python License CI Coverage PRs Welcome

LangGraph OpenAI Agents Claude SDK CrewAI Google ADK MCP

Quick Start · Install · Docs · Contributing


Your company has 47 AI agents. Nobody knows what they cost, who approved them, or which ones are still running. Three teams built the same summarizer. The security team hasn't audited any of them.

AgentBreeder fixes this.

Write one agent.yaml. Run agentbreeder deploy. Your agent is live — with RBAC, cost tracking, audit trail, and org-wide discoverability. Automatic. Not optional.


The Problem

AI coding tools make it easy to build agents. Nobody has made it easy to ship them responsibly.

What happens todayWhat happens with AgentBreeder
Every framework has its own deploy storyOne YAML, any framework, any cloud
No RBAC — anyone deploys anythingRBAC validated before the first container builds
No cost tracking — $40k surprise cloud billsCost attributed per team, per agent, per model
No audit trail — "who deployed that?"Every deploy logged with who, what, when, where
No discoverability — duplicate agents everywhereOrg-wide registry — search before you build
Governance is bolted on after the factGovernance is a structural side effect of deploying

Governance is not configuration. It is a side effect of the pipeline. There is no way to skip it.


How It Works

Eight atomic steps run in sequence:

parse → RBAC check → *(approval gate if required)* → resolve deps → build container → provision infra → deploy → health check → register. If any step fails, the entire deploy rolls back.

Three Ways to Build

All three tiers compile to the same internal format. Same deploy pipeline. Same governance. No lock-in.

TierWhoHowEject to
No CodePMs, analysts, citizen buildersVisual drag-and-drop canvas — pick model, tools, prompts from the registryLow Code
Low CodeML engineers, DevOpsWrite agent.yaml in any IDEFull Code (agentbreeder eject)
Full CodeSenior engineers, researchersPython/TS SDK with full programmatic control—

Use with Claude Code

Install the /agent-build architect as a Claude Code plugin:

claude plugin marketplace add agentbreeder/agentbreeder
claude plugin install agent-build@agentbreeder

Then run /agent-build in Claude Code to scaffold an agent (it recommends framework, model, memory, RAG, and deploy target, then generates agent.yaml + code).


Documentation

User docs (guides, references, examples) — agentbreeder.io/docs

How-To guidesInstall, deploy, orchestrate, evaluate
QuickstartFull local platform in one command
Self-hostingRun the platform on your own Kubernetes via Helm (deploy/helm/agentbreeder)
CLI referenceAll commands and flags
SDK referencePython + TypeScript full-code SDK

For contributors — internal engineering references in this repo:

ContributingHow to contribute — setup, standards, PR process
ArchitecturePlatform architecture — deploy pipeline, abstractions, data model
DesignFeature design docs — RBAC, LiteLLM gateway, polyglot agents

Changelog · Roadmap · Issues · Discussions · Discord · Apache 2.0 · Trademark · Code of conduct · CLA · Security · Governance

Ver o original no GitHub

Bom para

Relacionados