🟪 Open-source runtime that ships any LangGraph or Google ADK agent as a production-ready FastAPI service. Bundled , AG-UI copilotkit API, chat UI, 15+ guardrails, MCP, OpenTelemetry, OIDC. One pip install. Self-hosted, no vendor lock-in.
From the author’s README · Quick Start · not verified by Flowy
$ mkdir my-agent && cd my-agent$ pip install idun-agent-engine langgraph langchain-google-genai
Repo: Idun-Group/idun-agent-platform
What's inside
Self-hosted. Open source. No vendor lock-in.
Cloud · Try the demos · Quickstart · Docs · Discord · Book a demo
⭐ If you find this useful, please star the repo. It helps others discover the project.
Why Idun? Teams building agents face a tradeoff: build the production wrapper yourself (FastAPI + traces + guardrails + admin UI — slow), or adopt a SaaS like LangGraph Cloud or LangSmith (sovereignty trade-off). Idun is the third path: pip install a self-sufficient FastAPI process that bundles your agent with chat UI, admin, traces, and guardrails — all open source, all on your infrastructure.
Prerequisites: Python 3.12 or 3.13.
Create a new directory and install the engine:
mkdir my-agent && cd my-agent
pip install idun-agent-engine langgraph langchain-google-genai
Save the three files below inside my-agent/.
my-agent/agent.py
from typing import Annotated, TypedDict
from idun_agent_engine.mcp import get_langchain_tools_sync
from langchain_google_genai import ChatGoogleGenerativeAI
from langgraph.graph import StateGraph, START
from langgraph.graph.message import add_messages
from langgraph.prebuilt import ToolNode, tools_condition
class State(TypedDict):
messages: Annotated[list, add_messages]
tools = get_langchain_tools_sync()
llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash").bind_tools(tools)
def chatbot(state: State):
return {"messages": [llm.invoke(state["messages"])]}
graph = StateGraph(State)
graph.add_node("chatbot", chatbot)
graph.add_node("tools", ToolNode(tools))
graph.add_edge(START, "chatbot")
graph.add_conditional_edges("chatbot", tools_condition)
graph.add_edge("tools", "chatbot")
my-agent/config.yaml
server:
api:
port: 8000
agent:
type: LANGGRAPH
config:
name: "my-agent"
graph_definition: "./agent.py:graph"
checkpointer:
type: sqlite
db_url: "sqlite:///conversations.db"
mcp_servers:
- name: idun-docs
transport: streamable_http
url: https://docs.idun-group.com/mcp
my-agent/.env — get a Gemini key at aistudio.google.com/apikey:
GEMINI_API_KEY=your-key-here
From inside my-agent/, run:
idun init
graph_definition: "./agent.py:graph"is resolved against the directory where you runidun init. Stay insidemy-agent/when you launch it, or use an absolute path.
A browser opens at http://localhost:8000 for the chat UI. The agent already has tools from the Idun docs MCP wired in. Visit /admin to configure more MCP servers, managed prompts, guardrails, observability, messaging integrations, and SSO. Visit /admin/traces for the trace store.
What
pip install idun-agent-enginedeliversA single wheel that bundles three Python packages:
idun_agent_engine— the engine SDK (FastAPI app factory, MCP registry, observability, guardrails).idun_agent_standalone— theidunCLI, the admin REST API, and the chat / admin / traces UIs.idun_agent_schema— the Pydantic config schemas.The
iduncommand on your$PATH(setup,serve,init,hash-password,agent serve) is provided by the bundled standalone — it is not a separately published package. You won't seeidun-agent-standalonein the engine's declared PyPI dependencies because it ships co-installed inside the wheel, not as a transitive dep.See docs.idun-group.com/architecture for the full layering.
Langfuse · Arize Phoenix · LangSmith · GCP Trace · GCP Logging
Trace every agent run. Connect multiple providers at the same time through config.
PII detection · Toxic language · Ban lists · Topic restriction · Bias checks · NSFW · 9 more
Apply policies per agent on input, output, or both. Powered by Guardrails AI.
Register MCP servers and control which tools each agent can access. Supports stdio, SSE, streamable HTTP, and WebSocket.
PostgreSQL · SQLite · In-memory · Vertex AI · ADK Database
Conversations persist across restarts. Pick a backend per agent.
Versioned templates with Jinja2 variables. Assign prompts to agents from the UI or API.
[!NOTE] AG-UI streaming — Every agent gets a standards-based streaming API, compatible with CopilotKit clients. Built-in chat playground for testing.
Idun ships as one process: idun-agent-standalone. It bundles the engine SDK, a Next.js chat UI, an admin panel, and a traces viewer — your agent runs inside this process, configured from a YAML file and re-loaded live from the admin REST.
flowchart LR
subgraph Idun["idun-agent-standalone (one process)"]
direction TB
UI["Chat UI / Admin / Traces"] --> ENG["Engine SDK"]
ENG --> DB[(Postgres / SQLite)]
end
Users --> UI
Admin --> UI
ENG --> Agent["Your LangGraph / ADK agent"]
Agent --> LLM["LLMs / MCP / tools"]
[!NOTE] Framework support — LangGraph and Google ADK are first-class today, with full adapters in the engine. LangChain is supported via the LangGraph adapter; broader native LangChain compatibility is on the roadmap.
| Idun Engine | LangGraph Cloud | LangSmith | DIY (FastAPI + glue) | |
|---|---|---|---|---|
| Self-hosted / on-prem | ✅ | ❌ | ❌ | ✅ |
| Multi-framework (LangGraph + ADK) | ✅ | LangGraph only | ❌ obs only | Manual |
| Guardrails (15+ built-in) | ✅ | ❌ | ❌ | Build yourself |
| MCP tool governance | ✅ per-agent | ❌ | ❌ | Build yourself |
| Observability (multi-provider) | ✅ Langfuse, Phoenix, LangSmith, GCP | ❌ LangSmith only | ✅ LangSmith only | Manual |
| Memory / checkpointing | ✅ Postgres, SQLite, in-memory | ✅ | ❌ | Build yourself |
| AG-UI / CopilotKit streaming | ✅ | ✅ | ❌ | Manual |
| Open source (GPLv3) | ✅ | ❌ | ❌ | — |
[!NOTE] Idun is not a replacement for LangSmith (observability) or LangGraph Cloud (hosting). It is the layer between your agent code and production that handles governance, security, and operations, regardless of which observability or hosting you choose.
After pip install idun-agent-engine, your $PATH and site-packages contain:
| Module | Distributed via | Purpose |
|---|---|---|
idun_agent_engine | declared in requires_dist | FastAPI app factory, MCP registry, observability, guardrails wiring |
idun_agent_schema | declared in requires_dist | Pydantic config models for config.yaml |
idun_agent_standalone | co-bundled in the engine wheel | idun CLI, admin REST under /admin/api/v1/, chat / admin / traces UIs at /, /admin/, /admin/traces/ |
idun (console script) | [project.scripts] idun = "idun_agent_standalone.cli:main" | Subcommands: setup, serve, init, hash-password, agent serve |
The bundled-install model means you do not need to pip install idun-agent-standalone separately — it isn't published. To verify your install carries everything:
python -c "import idun_agent_engine, idun_agent_standalone, idun_agent_schema; print('all 3 modules importable')"
idun --help
Both checks are smoke-tested in the release pipeline before any wheel is published.
View @idun-group’s profileDrive Google's Antigravity CLI (agy, powered by Gemini 3.5) without leaving Claude Code. A Claude Code plugin that hands work to agy — Google's Antigravity CLI — and brings the result back into your session.
@idun-groupFAQ
idun-agent-platform is a Claude Code plugin with hand-picked skills for deployment work, indexed on Flowy. Install it with the command on its page. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it