Who it is forA researcher who needs a sourced summary on a topic and wants spending capped in advance.
The problemManual research across many queries is slow, and open-ended agent loops can run up a provider bill.
The outcomeA research answer produced by a loop that stops when it decides it is done, inside its hard budgets.
What you need first
- Docker with Docker Compose, or a free Google account for the Colab route
- At least one provider API key, such as OpenRouter, Google AI Studio or NVIDIA NIM
- A browser to open the app and paste keys into the Vault
Steps
- Start ENZO with
docker compose up -dand open http://localhost:5001. - Paste a provider key in the Vault so Research mode has a model to call.
- Open Research mode and enter the question you want answered.
- Read the final output and check the cited material it reports before using it.
Prompt for your agent
Using the repo theguysudo/ENZO at http://localhost:5001, start Research mode on this question: <research-question>. Expected output: a research answer that states when the loop stopped. Verify the answer lists the sources it read before you rely on any claim.
Caveat. The README describes the budgets as hard limits but does not state their values, so check the docs before a large run.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for theguysudo/ENZO and "Run a deep research loop under fixed budgets"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer