Parte de Plug-and-Play
Vanilla Agents
Composable libraries and a scaffold project that ship the 60–70% of agent code that is pure infrastructure, so your team writes business logic on day one.
$1,200 USDA set of independent libraries plus a scaffold project for building production-ready AI agents — fast. Roughly 60–70% of any agent codebase is infrastructure plumbing: structured logging, OpenTelemetry, LLM clients, FastAPI middleware, session management, MCP tool integration, streaming lifecycle. Vanilla Agents ships that plumbing as composable libraries so your team writes business logic on day one, not week six.
Comes with an SDK-agnostic runtime interface — you start with the Claude Agent SDK, but you can swap in OpenAI Agents, Bedrock, or another runtime without rewriting your service layer.
What you get
- 3 standalone infrastructure libraries — structured logging (with data sanitization + session aggregation), OpenTelemetry (settings, exporters, decorators), LLM clients (OpenAI-compatible factory)
- 1 agent toolkit library — settings, middleware, request/response models, session bridge, generic runtime interface, SDK-agnostic MCP tool system, skills system, base agent service
- 1 scaffold project — assembles everything into a runnable agent with FastAPI app, health checks,
/invocationsendpoint, example MCP tools, example skill, Dockerfile, docker-compose, CI/CD workflows - AWS Bedrock AgentCore deployment templates included
Tools / stack
- Python + Pydantic + FastAPI — service layer
- structlog + OpenTelemetry — logging and observability
- httpx (OpenAI-compatible) — LLM client
- Claude Agent SDK — default runtime (swappable via
AgentRuntimeinterface) - AWS SSM Parameter Store — config in deployed environments
- AWS Bedrock AgentCore — deployment target
Why “vanilla”
You get the plumbing, not opinions about your business logic. Each agent extends 6 abstract methods (get_runtime, get_system_prompt, get_mcp_servers, get_allowed_tools, get_skills, _model_name) and the toolkit handles the rest — aggregator setup, streaming, interaction capture, SSE formatting, session persistence, error handling, cleanup. Same pattern proven in production agents.
See it built live
Add a Workshop (+$500) — your engineers watch me install it live, learning the patterns alongside the product. 4 hours, real work.
Llamada de descubrimiento gratuita de 30 minutos. Vemos si encaja con tu equipo.
Agenda una llamada →