可以给计器为常用的常用器

A note from the builder

I'm one developer. No team, no funding, no VC deck — just me, a laptop, and a stubborn little bird from the Dominican Republic. 🇩🇴

I've poured months into Dulus. Some days it feels like building the loudest thing in an empty room — like nobody's paying attention. And the honest truth: I've spent so long building the features that could genuinely rattle this industry that I've barely shown them. That changes now.

Because this isn't a toy demo. Dulus already does things the funded wrappers can't:

• frontier AI with no keys (the web-session engine above),
• a Round Table where several real models argue their way to a better answer,
• an auto-adapter that installs its own missing tools when it hits a wall,
• 2,186+ MCP tools, 100,000 skills, memory, voice, sub-agents,
• one runtime driving a terminal, a browser, a desktop app, and a full sandbox OS.

My goal is simple and stubborn: put a real agentic AI in the hands of anyone with a terminal — for free — while the door is still open. If that mission means something to you, star the repo, run one command, tell one person. Help the Cigua fly. 🦅

— Kevin (@KevRojo) · Santo Domingo 🇩🇴

---

Install in 30 seconds

If Python 3.11 or newer is already installed:

pip install dulus
dulus

The first-run wizard inspects the machine, recommends a right-sized local model, and can install Ollama for a zero-key, fully local start.

Automatic installer

Linux, macOS, WSL, and Termux:

curl -fsSL https://raw.githubusercontent.com/KevRojo/Dulus/main/install.sh | bash

Windows PowerShell:

iwr -useb https://raw.githubusercontent.com/KevRojo/Dulus/main/install.ps1 | iex

Windows users who do not want Python or a terminal can download the self-contained MSI from GitHub Releases.

Docker

docker run --rm -it \
  -v "${PWD}:/workspace" \
  -w /workspace \
  ghcr.io/kevrojo/dulus:latest

Build with Dulus

Development setup

```bash git clone https://github.com/KevRojo/Dulus cd Dulus python -m venv .venv

Get your Dulus API key (no website required)

Damn brother… are you really waiting for the website update to get your API key?

You don’t need the website. Minting a dulus_sk_* key has been in dulus-public (pip install dulus) for ages. The CLI talks straight to the control plane.

pip install -U dulus
dulus

Inside the REPL:

/login dulus        # sign in (OAuth PKCE — browser opens, no API key pasted by hand)
/login dulus key    # mint a dulus_sk_* key for CI, SDKs, servers (shown once — copy it)

Then point any OpenAI-compatible client at the router and burn $DULUS fuel by the token:

export OPENAI_API_KEY='dulus_sk_...' 
export OPENAI_BASE_URL='https://control.dulus.ai/v1'

from openai import OpenAI
client = OpenAI(
    api_key="dulus_sk_...",                 # from /login dulus key
    base_url="https://control.dulus.ai/v1",
)
r = client.chat.completions.create(
    model="dulus-a-9b",  # or dulus-b-27b, dulus-x-397b, …
    messages=[{"role": "user", "content": "hola desde el router"}],
)
print(r.choices[0].message.content)

Or stay inside Dulus and use the built-in provider (same login, Fuel-metered):

/login dulus
/model dulus-a-9b

It was a surprise u,u — have fun. 🦅 $DULUS

---

/login dulus key # mint dulus_sk_* for SDKs

Unix pipeline

git diff | dulus -p "review this diff and find the dangerous parts" ```

No third-party key yet? Use /login dulus for the hosted router, start with Ollama, NVIDIA NIM's free tier, or a browser-backed provider from the welcome flow.

---

Three extension paths

The MCP marketplace indexes more than 2,000 servers. Composio exposes 800+ ready-made skills and app integrations. Auto-Adapter covers the long tail: code that nobody packaged for an agent.

{
  "mcpServers": {
    "git": {
      "type": "stdio",
      "command": "uvx",
      "args": ["mcp-server-git"]
    },
    "playwright": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@playwright/mcp"]
    }
  }
}

/mcp search postgres
/mcp install <name>
/mcp installed
/mcp reload
/plugin recommend
/plugin list
/skills

---

FAQ

<details> <summary><strong>Does Dulus require an API key?</strong></summary>

No. Ollama and LM Studio run locally. NVIDIA NIM provides a free-tier route. Supported browser-backed providers can also be configured through the welcome flow. Cloud API keys remain available when you want direct paid access.

</details>

<details> <summary><strong>Which local models work best with tools?</strong></summary>

Use a model trained for function calling, such as Qwen2.5-Coder, Llama 3.3, Mistral, or Phi-4. Base models without tool-use training may produce valid text but unreliable tool calls.

</details>

<details> <summary><strong>Can Dulus use a remote GPU?</strong></summary>

Yes. Point custom_base_url at any OpenAI-compatible server:

/config custom_base_url=http://your-server:8000/v1
/model custom/your-model

</details>

<details> <summary><strong>Is <code>--accept-all</code> safe for production repositories?</strong></summary>

It deliberately removes approval prompts. Use it in trusted sandboxes or controlled automation. Use the default auto mode or read-only plan mode for sensitive environments.

</details>

<details> <summary><strong>Can I use Dulus as a library?</strong></summary>

Yes. The agent loop, provider layer, registry, memory system, MCP client, and task system are regular Python modules. The API guide and dependency graph are the best entry points.

</details>

---