# AI use cases for ENZO (theguysudo/ENZO) Repo: [theguysudo/ENZO](https://github.com/theguysudo/ENZO) | Use cases: 5 | Page: https://dedupedai.com/use-cases/theguysudo-enzo/ ENZO is a self-hosted AI workspace that runs chat, agents, research and code generation on your own provider API keys, with no ENZO account or middleman fee. This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL. - Chat with 300+ models on your own keys: https://dedupedai.com/use-cases/theguysudo-enzo/chat-300-models-with-own-keys/ - Run ENZO on Google Colab with no install: https://dedupedai.com/use-cases/theguysudo-enzo/colab-zero-install-chat/ - Draft an agent's operating manual from one sentence: https://dedupedai.com/use-cases/theguysudo-enzo/agent-drafted-from-plain-english-task/ - Run a deep research loop under fixed budgets: https://dedupedai.com/use-cases/theguysudo-enzo/deep-research-under-hard-budgets/ - Generate a coding project and preview it live: https://dedupedai.com/use-cases/theguysudo-enzo/generate-and-preview-coding-project/ ## How to chat with 300+ models on your own keys with ENZO Repo: [theguysudo/ENZO](https://github.com/theguysudo/ENZO) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Run ENZO locally with Docker and chat across many providers without a subscription. **Who it is for:** A developer who pays several model providers directly and wants one local chat screen for all of them. **The problem:** Switching between provider consoles and paying a vendor markup makes comparing models slow and costly. **The outcome:** A running local ENZO instance at http://localhost:5001 where you can stream chats with models from your own providers. ### Steps 1. Run `git clone https://github.com/theguysudo/ENZO.git` to download the repo. 2. Run `cd ENZO` and then `docker compose up -d` to start the container. 3. Open http://localhost:5001, press Login, and paste a working provider key such as OpenRouter or Google AI Studio. 4. Open the Terminal surface and start a streaming chat with a model from the catalog. ### Prompt to paste into your agent ```text Using the repo theguysudo/ENZO, run `docker compose up -d` inside , then confirm http://localhost:5001 loads. Expected output: the ENZO app reachable in the browser. Verify the health trace in the toolbar is not flatlined red, which would mean the model catalog is unreachable. ``` ### Caveat The README says the first live-validated key you paste claims the instance and is written to the container .env, so use a key you are willing to store there. Risk, credentials: Provider keys are pasted into the local instance, so keep the container and its enzo-memory volume on a machine you control. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/theguysudo-enzo/chat-300-models-with-own-keys/ ## How to run ENZO on Google Colab with no install with ENZO Repo: [theguysudo/ENZO](https://github.com/theguysudo/ENZO) | Difficulty: Beginner | Time: 15 minutes | Basis: From the README Boot ENZO from a Colab notebook and reach it from a phone through a tunnel link. **Who it is for:** A user with no local setup who wants a working ENZO instance for a few hours from any browser or device. **The problem:** Installing dependencies and building the UI on a personal machine is a barrier for a quick test. **The outcome:** A Colab link and a Cloudflare tunnel URL that open a live ENZO workspace, with provider keys you paste after boot. ### Steps 1. Open the Colab notebook from the badge in the README at notebooks/enzo-colab.ipynb in the ENZO repo. 2. Select Runtime → Run all, or press Ctrl/⌘ + F9, and wait about 4 to 5 minutes for the first install and build. 3. Copy the Colab link or the Cloudflare tunnel link printed by the last cell. 4. Paste a provider key into the Vault after boot and start a chat or agent. ### Prompt to paste into your agent ```text Open the ENZO Colab notebook at notebooks/enzo-colab.ipynb in the repo theguysudo/ENZO and run all cells. Expected output: a printed Colab link and a Cloudflare tunnel link to the running server. Verify the tunnel URL returns the ENZO app before pasting any provider key into . ``` ### Caveat The README says the Colab VM is gone when the session ends, so anything not saved elsewhere is lost. Risk, credentials: The tunnel URL is reachable from any device and changes each session, so treat it as a live entry point and do not share it while your keys are loaded. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/theguysudo-enzo/colab-zero-install-chat/ ## How to draft an agent's operating manual from one sentence with ENZO Repo: [theguysudo/ENZO](https://github.com/theguysudo/ENZO) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Describe a task in plain English and let ENZO write the agent's full manual. **Who it is for:** A knowledge worker or builder who needs a repeatable domain agent but does not want to write its instructions by hand. **The problem:** Writing a complete operating manual with edge cases and decision rules takes long, careful effort. **The outcome:** A saved agent with a drafted manual, a record of which model drafted it, and a Neural tab showing ongoing learning. ### Steps 1. Start ENZO with `docker compose up -d` and open http://localhost:5001 after pasting a provider key. 2. Open the Agent builder and describe the task in plain English, for example an agent that researches a specific domain. 3. Wait for the two-pass drafter to finish and review the operating manual it writes. 4. Open the agent's Neural tab to watch NEURAL FOCUS and the learning layer update over time. ### Prompt to paste into your agent ```text Using the repo theguysudo/ENZO running at http://localhost:5001, create an agent from this task: . Expected output: a saved agent with a full operating manual and a recorded drafting model. Verify the agent page names the model that actually drafted it. ``` ### Caveat The README says the agent builder races free candidates from your own providers, so drafts depend on which free-tier models are reachable at that moment. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/theguysudo-enzo/agent-drafted-from-plain-english-task/ ## How to run a deep research loop under fixed budgets with ENZO Repo: [theguysudo/ENZO](https://github.com/theguysudo/ENZO) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Let ENZO write its own queries, read results and stop, without burning your key. **Who it is for:** A researcher who needs a sourced summary on a topic and wants spending capped in advance. **The problem:** Manual research across many queries is slow, and open-ended agent loops can run up a provider bill. **The outcome:** A research answer produced by a loop that stops when it decides it is done, inside its hard budgets. ### Steps 1. Start ENZO with `docker compose up -d` and open http://localhost:5001. 2. Paste a provider key in the Vault so Research mode has a model to call. 3. Open Research mode and enter the question you want answered. 4. Read the final output and check the cited material it reports before using it. ### Prompt to paste into your agent ```text Using the repo theguysudo/ENZO at http://localhost:5001, start Research mode on this 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. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/theguysudo-enzo/deep-research-under-hard-budgets/ ## How to generate a coding project and preview it live with ENZO Repo: [theguysudo/ENZO](https://github.com/theguysudo/ENZO) | Difficulty: Intermediate | Time: 30 minutes | Basis: From the README Have ENZO write a small project, boot it and show it in a live preview. **Who it is for:** A developer who wants a quick working prototype from a prompt and a live preview to check it. **The problem:** Setting up a new project scaffold and running it by hand takes time before any idea can be tested. **The outcome:** A generated project saved in ENZO, running in the preview panel, with ENZO reporting if it is broken. ### Steps 1. Start ENZO with `docker compose up -d` and open http://localhost:5001 after pasting a provider key. 2. Open Code-gen and describe the coding project you want. 3. Wait for ENZO to write the project, boot it and show it in the live preview. 4. Click files in the file strip to inspect the generated code and fix anything ENZO reports as broken. ### Prompt to paste into your agent ```text Using the repo theguysudo/ENZO at http://localhost:5001, use Code-gen to build this project: . Expected output: a generated project running in the live preview. Verify the preview loads and that the file strip shows the project files before you accept the result. ``` ### Caveat The README says generated backends run under Node's runtime permission model, and that a failed sandboxed boot retries once unsandboxed, so a boot can run with fewer limits than you expect. Risk, remote script: ENZO boots the server.js from your prompts, so review generated code before running it outside the preview. Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/ URL: https://dedupedai.com/use-cases/theguysudo-enzo/generate-and-preview-coding-project/