PromptPanel
Accelerating your AI agent adoption
Documentation | DockerHub | GitHub

To get started running your first PromptPanel instance:

docker run --name promptpanel -p 4000:4000 -v PROMPT_DB:/app/database -v PROMPT_MEDIA:/app/media --pull=always promptpanel/promptpanel:latest

After running, your environment will be available at: http://localhost:4000

Read more on running PromptPanel.

To run Ollama for local / offline inference with the following Docker Compose file:

curl -sSL https://promptpanel.com/content/media/manifest/docker-compose.yml | docker compose -f - up

which will run:

services:
  promptpanel:
    image: promptpanel/promptpanel:latest
    container_name: promptpanel
    restart: always
    volumes:
      - PROMPT_DB:/app/database
      - PROMPT_MEDIA:/app/media
    ports:
      - 4000:4000
    environment:
      PROMPT_OLLAMA_HOST: http://ollama:11434
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: always
volumes:
  PROMPT_DB:
  PROMPT_MEDIA:

Your models, conversations, and logic are locked in walled-gardens.

Let's free your AI interface.

• Run any large language model, across any inference provider, any way you want. From commercial models like OpenAI, Anthropic, Gemini, or Cohere - to open source models, either hosted or running locally via Ollama.
• Access controls to assign users to agents without revealing your API tokens or credentials. Enable user sign-up and login with OpenID Connect (OIDC) single sign-on.
• Bring your own data and store it locally on your instance. Use it safely by pairing it with any language model, whether online or offline.
• Create custom agent plugins using Python, to customize your AI agent capabilities, and retrieval augmented generation (RAG) pipelines.

Get started developing using a one-click cloud development environment using GitPod:

This ./plugins directory contains the community plugin agents found in PromptPanel as well as a sample agent as a template for you to get started with your own development.

• The ./hello_agent directory gives you some scaffolding for a sample agent.
• The other community plugin agents give you references to sample from.
• The docker-compose-agent-dev.yml file gives you a sample with the various mounts and environment variables we recommend for development.

To get more information about how to build your first plugin we recommend giving a read to:

• Building Plugin Agents
• Data Model

Running DEV_PORT=4000 docker compose up -f docker-compose-agent-dev.yml from this directory with a development port set will bring up a development environment you can use to start developing your agent plugin.

Command:

DEV_PORT=4000 docker compose up -f docker-compose-agent-dev.yml

With these settings, your development environment will be available at: http://localhost:4000

Feel free to get in contact with us at:
[email protected]