MCPcopy Index your code
hub / github.com/eidolon-ai/eidolon

github.com/eidolon-ai/eidolon @v0.1.17

Chat with this repo
repository ↗ · DeepWiki ↗ · release v0.1.17 ↗ · + Follow
1,348 symbols 5,532 edges 221 files 171 documented · 13%

Browse by type

Functions 977 Types & classes 363 Endpoints 8
What it actually does AI analysis from the code graph — generated when you open this
loading…
README

Welcome to Eidolon - an Open Source Agent Services Framework

img_1

The Eidolon framework represents a sophisticated architecture for designing and operating agent-based systems. It is purpose-built to support the agile development of software agents—modular components designed to perform specific tasks autonomously within a distributed computing environment. At its core, the eidolon system facilitates an extensive range of functionalities, enabling developers to construct, customize, and scale agent operations effectively.

Demo

Deploy a Chatbot: Help Swifties learn about Kelce

Getting Started

Step 0: Prerequisites

Step 1: Install Eidolon SDK

First, you need to install the Eidolon SDK. Open your terminal and run the following command:

pip install eidolon-ai-sdk

Step 2: Create an Agent

Now it is time to create your first AgentProgram. Create a directory and add a yaml file to describe your resource.

mkdir hello_world
vim hello_world/hello_world_agent.yaml
apiVersion: eidolon/v1
kind: Agent
metadata:
  name: hello_world
spec:
  description: "This is an example of a generic agent which greets people by name."
  system_prompt: "You are a friendly greeter who greets people by name while using emojis"
  actions:
    - user_prompt: "Hi, my name is {{name}}"

Step 3: Run Eidolon Server

Finally, open a new terminal window and run your machine using eidolon-server.

eidolon-server -m local_dev hello_world

🚨 Getting command not found: eidolon-server? Open a new terminal window and try the command again.

⚠️ The -m local_dev option specifies using the local_dev builtin Machine resource. This machine uses in-memory symbolic memory rather than mongo, so state will disappear between server restarts.

Step 4: Try it out!

First create a process for your conversation.

curl -X POST http://0.0.0.0:8080/agents/hello_world/processes; echo
````

The result should be a json object with a process id. For example:

```json
{"process_id":"hello_world-1"}

Now let's try to make a request to your server from another terminal window.

curl -X POST http://0.0.0.0:8080/agents/hello_world/processes/{process_id}/actions/converse -H 'Content-Type: application/json' -d '{"name": "World"}'; echo

Replace {process_id} with the process id you received from the previous command.

You should now see something like Hello, World! 🌍👋

And that's it! You have successfully set up and used a basic project using the Eidolon SDK. To see more endpoints on your agent machine, visit the swagger ui.

Further Reading

For full documentation, visit www.eidolonai.com.

Extension points exported contracts — how you extend this code

Core symbols most depended-on inside this repo

Shape

Method 682
Class 332
Function 295
Interface 31
Route 8

Languages

Python92%
TypeScript8%

Modules by API surface

sdk/eidolon_ai_sdk/agent/doc_manager/transformer/text_splitters.py57 symbols
sdk/tests/system/test_code_agents.py44 symbols
sdk/tests/system/test_reference_model.py33 symbols
sdk/tests/conftest.py29 symbols
sdk/eidolon_ai_sdk/system/agent_controller.py25 symbols
client/python/eidolon_ai_client/events.py25 symbols
client/python/eidolon_ai_client/client.py24 symbols
sdk/tests/test_simple_agent.py22 symbols
examples/eidolon_examples/group_conversation/base_conversation_coordinator.py21 symbols
examples/eidolon_examples/lib/base_conversation_coordinator.py19 symbols
sdk/eidolon_ai_sdk/cpu/agents_logic_unit.py18 symbols
examples/eidolon_examples/swifties/validating_cpu.py18 symbols

For agents

$ claude mcp add eidolon \
  -- python -m otcore.mcp_server <graph>

⬇ download graph artifact

Ask about this repo answers extend the page