Skip to content
Idun Agent Platform

Idun Agent Platform

From AI prototypes to governed agent fleets on your own infrastructure.

Idun Agent Platform is an open source control plane for generative AI agents. It turns LangGraph, ADK or Haystack agents into production-ready services with unified deployment, observability, memory, guardrails and access control.

Who is this for
GenAI developers who want to ship agents without rebuilding infra each time.
AI and data platform teams who need governance, auditability and sovereignty.

Quickstart in 5 minutes Join the Discord

Start here

Platform workflow

LangGraph Agent Development Kit Langfuse MCP A2A Postgres Phoenix LangSmith Google Cloud Okta Guardrails AI LangChain Haystack AG-UI LangGraph Agent Development Kit Langfuse MCP A2A Postgres Phoenix LangSmith Google Cloud Okta Guardrails AI LangChain Haystack AG-UI

Should you use Idun Agent Platform

You probably should if:

  • You have or plan multiple agents built with LangGraph, ADK, Haystack or similar
  • You care about observability, guardrails, security, and AI regulation
  • You want to self host or run on your own cloud, not depend on a vendor black box

You probably should not if:

  • You are just experimenting with a single toy chatbot
  • You do not need observability, governance or multi environment setups yet

For GenAI developers

You want to spend time on agent logic, not boilerplate infra.

With Idun you can:

  • Wrap your LangGraph, ADK or Haystack agent as a FastAPI service in minutes
  • Get tracing, feedback and metrics without rewriting your code
  • Run the same agent locally, on staging and in production with the same config
  • Plug tools and memory through configuration instead of hard coding everything

Start building: Quickstart guide.

For AI and data platform teams

You want to standardize how agents run in production and stay compliant.

With Idun you can:

  • Maintain a catalog of approved agents with clear ownership and environments
  • Enforce SSO, RBAC and per tenant isolation, integrated with your IdP
  • Control which models, tools and data sources each agent can use with MCP
  • Enforce guardrails for safety and compliance, with full audit and monitoring

Learn more: SSO & RBAC · Guardrails.

Why Idun exists

Today, each agent framework comes with its own way to deploy, observe and govern agents. The result is a zoo of one off POCs, custom servers and ad hoc dashboards.

Idun Agent Platform gives you:

  • One configuration model: define agent configurations in one central hub that works across frameworks
  • Production features by default: memory, observability, guardrails, MCP, SSO access
  • Flexible deployment: run locally, self host on your own cloud or integrate it into your platform
  • Centralized control: manage agents, environments and access from one dashboard or CLI

For a deeper architecture overview, see the Technical whitepaper.

Key capabilities at a glance

  • Observability Plug Langfuse, Phoenix, LangSmith or GCP, get tracing and metrics for every call. → Observability overview

  • Guardrails Add content safety, PII detection and prompt injection protection in front of any agent. → Guardrails overview

  • MCP integration Extend agents with Model Context Protocol servers; Idun manages server lifecycle and tool registration. → MCP configuration

  • Memory and session persistence Persist conversations and state across calls with backends like SQLite or Postgres. → Memory overview

High level architecture

Idun Agent Platform is structured in four layers:

  • Web dashboard UI to create, configure and monitor agents.

  • Manager API Control plane that stores configurations, handles auth, observability and guardrails settings.

  • Engine runtime Executes agents via adapters for LangGraph, ADK, Haystack and others, exposes AG-UI compatible FastAPI endpoints.

  • Data layer PostgreSQL for checkpointing and configuration, MCP servers for external tools and data.

For more, see Architecture and Deployment options.

Quickstart

You need Python 3.12, Docker and Git.

  1. Clone the repo
git clone https://github.com/Idun-Group/idun-agent-platform.git
cd idun-agent-platform
  1. Start the platform locally
cp .env.example .env

docker compose -f docker-compose.dev.yml up --build
  1. Open the dashboard at http://localhost:3000 and create your first agent.

Then follow the Quickstart guide for a full step-by-step tutorial, including ADK example code.

Project status and roadmap

The platform is under active development and already used in production in real projects.

  • ✅ Core runtime on PyPI as idun-agent-engine, with adapters for LangGraph and ADK
  • ✅ Local and self-hosted deployment with Docker
  • ✅ AG-UI compatible CopilotKit endpoint, MCP server support, Guardrails AI, observability (Langfuse, LangSmith, Phoenix, GCP Trace), SSO access to Manager UI
  • 🚧 More agent frameworks and MCP integrations, environment management (DEV/STG/PRD), and expanded observability & evaluation
  • 🚧 Deployment templates (Terraform, Helm/Kubernetes), ready-to-use agents & MCP tools, and Idun Cloud managed offering

See the detailed Roadmap for up-to-date status.

Community and support

For commercial support, contact contact@idun-group.com.