Skip to main content

Declarative AI agent framework - build agent applications in YAML

Project description

Digitorn

Declarative AI agent framework. Build agent applications in YAML, run them locally or in the cloud, plug into any LLM (Anthropic, OpenAI, DeepSeek, Groq, Ollama, GitHub Copilot, ...) and any MCP server.

app:
  app_id: hello
  name: Hello

agents:
  - id: main
    role: assistant
    brain:
      provider: anthropic
      model: claude-sonnet-4-5
      backend: anthropic
      config:
        api_key: "claude-code"
    system_prompt: "Reply with one short sentence."
digitorn dev deploy hello.yaml
digitorn dev chat hello -m "ping"
# pong

The same YAML runs identically on a laptop, a server, a CI runner, or behind a reverse proxy. The daemon ships every primitive an agent needs: filesystem, shell, web, RAG, vector, database, LSP, MCP, channels (webhook / cron / email / slack / ...), hooks, behavior engine, sandbox, multi-agent orchestration, credentials vault, real-time event stream.

Install

Windows

Open PowerShell and run:

irm https://digitorn.ai/install.ps1 | iex

macOS / Linux

curl -fsSL https://digitorn.ai/install.sh | sh

The installer fetches Python 3.12 via uv, installs the digitorn CLI, registers a background service (Windows Service / launchd / systemd), and starts the daemon on http://127.0.0.1:8000.

Already have Python 3.12? pip install digitorn (or uv tool install digitorn) works too. Then:

digitorn service install
digitorn service start

First steps

digitorn doctor                       # check the environment
digitorn init my-app && cd my-app     # scaffold a project
digitorn dev deploy app.yaml          # push it to the local daemon
digitorn dev chat my-app              # interactive chat

Documentation: docs.digitorn.ai.

Requirements

  • Windows 10+, macOS 12+, or a recent Linux distro
  • Python 3.12 (the installer fetches it via uv if missing)
  • 2 GB free disk space for the model cache (embeddings, ONNX runtimes)
  • Outbound HTTPS for LLM providers and MCP servers you choose to use

Operating the daemon

digitorn service status               # is it running?
digitorn service logs                 # last 50 lines
digitorn service stop                 # stop until next boot
digitorn service start                # start again
digitorn service uninstall            # remove the service

Logs live under:

  • Windows: Event Viewer (Applications and Services Logs > DigitornDaemon)
  • macOS: ~/Library/Logs/digitorn/
  • Linux: journalctl --user -u digitorn

The daemon also writes its own structured logs to ~/.digitorn/logs/.

Development

This repository is the source for the daemon and the language. To work on it directly:

git clone https://github.com/mbathe/digitorn-bridge
cd digitorn-bridge
uv sync                               # or: poetry install
uv run digitorn start                 # foreground, with the venv's deps

Documentation is built with Docusaurus under docs-site/ (cd docs-site && npm install && npm start). The web client lives in a separate repository.

License

Apache 2.0. See LICENSE.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

digitorn-1.0.0.tar.gz (3.1 MB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

digitorn-1.0.0-py3-none-any.whl (3.7 MB view details)

Uploaded Python 3

File details

Details for the file digitorn-1.0.0.tar.gz.

File metadata

  • Download URL: digitorn-1.0.0.tar.gz
  • Upload date:
  • Size: 3.1 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.3.4 CPython/3.11.5 Windows/10

File hashes

Hashes for digitorn-1.0.0.tar.gz
Algorithm Hash digest
SHA256 7909e1d5b01515aa9096815731bfab29c3d24d9ce2e326106086a0acdf3ab483
MD5 f4ff2a90ad5065c98430fbe268b2b92d
BLAKE2b-256 0b326697232f1e196664836790423388e5e6151ad9edd784d884afee8b9b88c6

See more details on using hashes here.

File details

Details for the file digitorn-1.0.0-py3-none-any.whl.

File metadata

  • Download URL: digitorn-1.0.0-py3-none-any.whl
  • Upload date:
  • Size: 3.7 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/2.3.4 CPython/3.11.5 Windows/10

File hashes

Hashes for digitorn-1.0.0-py3-none-any.whl
Algorithm Hash digest
SHA256 aed66e4ebe1193b94f7d2ee869c1137b48ade0dd8c1a420118f42361dedacf99
MD5 8ba525441c7939d31785e5b0f2ff27d9
BLAKE2b-256 137c966beef0f19e72bae784f5df2803a89a59d0ae621efdcb0175ca88afa0b8

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page