Auto-GPT made the autonomous-agent idea real. You hand it a goal, it loops on the goal, it picks tools and chases it. The downside is well known: cost spikes, infinite loops, opaque state. Digitorn keeps the goal-pursuit pattern and adds real safety rails.
An Auto-GPT-style agent without loop guards is one bad night away from a cloud bill that ruins a weekend. Digitorn gives you runtime.max_turns, the security.behavior engine that catches runaway patterns, hooks that gate tool calls before they fire, and a real stop control.
Every Auto-GPT primitive maps to a Digitorn equivalent. Where the mapping is not 1-to-1, the notes call out what changed.
Real apps in both stacks. The Digitorn version is what you would commit to a repo, no scaffolding hidden offscreen.
1{2 "ai_name": "ResearchGPT",3 "ai_role": "Research and write reports on a topic",4 "ai_goals": [5 "Research the topic across the open web",6 "Write a structured report with citations",7 "Save the final report to outputs/report.md",8 "Stop when the report is complete"9 ],10 "api_budget": 5.011}1schema_version: 223app:4 app_id: research-writer5 name: "Research writer"6 version: "1.0.0"78runtime:9 mode: one_shot10 entry_agent: researcher11 max_turns: 251213modules:14 web: {}15 filesystem: { config: { workspace: "." } }16 memory: { config: { working_memory: true } }1718agents:19 - id: researcher20 modules:21 - {web: [search, fetch]}22 - filesystem23 - {memory: [set_goal, remember]}24 brain: { provider: anthropic, model: claude-sonnet-5, credential: anthropic_main }25 system_prompt: |26 Goal: research the topic and write outputs/report.md with citations.27 Use web.search to find sources, web.fetch to read them, then28 write the final report to a file.The Auto-GPT JSON describes a wish, the YAML describes the rails. runtime.max_turns means a stuck loop ends in a fixed number of turns, not in an open-ended bill.
Subtle differences that look the same on paper and break on first run. Read these before you start porting.
Auto-GPT lets the agent monitor its own api_budget. Digitorn enforces max_turns from the runtime config so a confused agent cannot raise its own ceiling.
Most plugins (web search, filesystem, code exec) become built-in modules. For exotic plugins, attach an MCP server, never write Python plumbing.
Without an explicit 'you're done when X' in the prompt, an autonomous agent can keep working right up to max_turns. Say what 'done' looks like.
# 1. install runtime
curl -sSL https://digitorn.ai/install | sh
# 2. save the YAML above as app.yaml in a new folder
mkdir from-autogpt
# 3. install and chat
digitorn install ./from-autogpt
digitorn chat from-autogptEngineering notes from the Digitorn team. No marketing, no launch announcements, no "10 prompts that will change your life". Just the things we write that we'd want to read.