Instructions to use Frankenstein-Labs/Cortex.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Frankenstein-Labs/Cortex.0 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Frankenstein-Labs/Cortex.0:Q8_0 # Run inference directly in the terminal: llama cli -hf Frankenstein-Labs/Cortex.0:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Frankenstein-Labs/Cortex.0:Q8_0 # Run inference directly in the terminal: llama cli -hf Frankenstein-Labs/Cortex.0:Q8_0
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf Frankenstein-Labs/Cortex.0:Q8_0 # Run inference directly in the terminal: ./llama-cli -hf Frankenstein-Labs/Cortex.0:Q8_0
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf Frankenstein-Labs/Cortex.0:Q8_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf Frankenstein-Labs/Cortex.0:Q8_0
Use Docker
docker model run hf.co/Frankenstein-Labs/Cortex.0:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use Frankenstein-Labs/Cortex.0 with Ollama:
ollama run hf.co/Frankenstein-Labs/Cortex.0:Q8_0
- Unsloth Desktop
- Pi
How to use Frankenstein-Labs/Cortex.0 with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Frankenstein-Labs/Cortex.0:Q8_0
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Frankenstein-Labs/Cortex.0:Q8_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use Frankenstein-Labs/Cortex.0 with Docker Model Runner:
docker model run hf.co/Frankenstein-Labs/Cortex.0:Q8_0
- Lemonade
How to use Frankenstein-Labs/Cortex.0 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Frankenstein-Labs/Cortex.0:Q8_0
Run and chat with the model
lemonade run user.Cortex.0-Q8_0
List all available models
lemonade list
- Hermes Agent
How to use Frankenstein-Labs/Cortex.0 with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Frankenstein-Labs/Cortex.0:Q8_0
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Frankenstein-Labs/Cortex.0:Q8_0
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Frankenstein-Labs/Cortex.0 with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf Frankenstein-Labs/Cortex.0:Q8_0
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "Frankenstein-Labs/Cortex.0:Q8_0" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download cortex0/fusion.py from Frankenstein-Labs/Cortex.0: direct link, hf CLI and curl.
- Browser
- Download file 3.53 kB
-
https://huggingface.co/Frankenstein-Labs/Cortex.0/resolve/main/cortex0/fusion.py
- Command line
-
hf download hf://Frankenstein-Labs/Cortex.0/cortex0/fusion.py
-
curl -L -o fusion.py https://huggingface.co/Frankenstein-Labs/Cortex.0/resolve/main/cortex0/fusion.py
3.53 kB
| """The fusion itself: Cortex.0 driving the OpenHands action-perception loop.""" | |
| from __future__ import annotations | |
| import logging | |
| from pathlib import Path | |
| from typing import Any | |
| from openhands.sdk import Conversation | |
| from cortex0.agent import build_agent | |
| from cortex0.health import ServerProbe, probe_server | |
| from cortex0.settings import Cortex0Settings | |
| logger = logging.getLogger("cortex0.fusion") | |
| class Cortex0Agent: | |
| """A single unified system: Cortex.0 as the brain, the SDK as the body. | |
| The model is not invoked as an external tool. It is the reasoning engine | |
| the SDK calls on every turn, and the SDK's tools (terminal, file editor, | |
| browser) are exposed to it as its own action space. | |
| """ | |
| def __init__( | |
| self, | |
| settings: Cortex0Settings | None = None, | |
| verify: bool = True, | |
| ) -> None: | |
| self.settings = settings or Cortex0Settings.load() | |
| self.probe: ServerProbe | None = None | |
| if verify: | |
| self.probe = probe_server( | |
| base_url=self.settings.base_url, | |
| api_key=self.settings.api_key, | |
| model=self.settings.served_model_name, | |
| timeout=min(self.settings.timeout, 120.0), | |
| ) | |
| if not self.probe.reachable: | |
| raise RuntimeError( | |
| "Cortex.0 inference server is unreachable at " | |
| f"{self.settings.base_url}. {self.probe.detail}\n" | |
| "Start the server (see scripts/serve_llamacpp.sh) or point " | |
| "CORTEX0_BASE_URL at a running endpoint." | |
| ) | |
| if not self.probe.chat_ok: | |
| raise RuntimeError( | |
| "Cortex.0 answered /models but not chat/completions. " | |
| f"{self.probe.detail}" | |
| ) | |
| if not self.probe.tool_calling_ok: | |
| logger.warning( | |
| "Cortex.0 did not emit tool_calls during the probe (%s). " | |
| "The agent will still run, but autonomous tool use may be weak.", | |
| self.probe.detail or "no tool call returned", | |
| ) | |
| self.agent = build_agent(self.settings) | |
| def start_conversation(self, workspace: str | Path | None = None) -> Conversation: | |
| """Create a conversation whose workspace is the agent's sandbox.""" | |
| target = Path(workspace or self.settings.workspace) | |
| target.mkdir(parents=True, exist_ok=True) | |
| return Conversation(agent=self.agent, workspace=str(target)) | |
| def run(self, task: str, workspace: str | Path | None = None) -> Any: | |
| """Run one task end to end and return the conversation.""" | |
| conversation = self.start_conversation(workspace) | |
| conversation.send_message(task) | |
| conversation.run() | |
| return conversation | |
| def summary(self) -> dict: | |
| """Report the state of the fusion, for logs and the CLI.""" | |
| return { | |
| "model": self.settings.model, | |
| "base_url": self.settings.base_url, | |
| "context_window": self.settings.context_window, | |
| "tools": list(self.settings.tools), | |
| "server_reachable": bool(self.probe and self.probe.reachable), | |
| "chat_ok": bool(self.probe and self.probe.chat_ok), | |
| "tool_calling_ok": bool(self.probe and self.probe.tool_calling_ok), | |
| "probe_detail": self.probe.detail if self.probe else "", | |
| "probe_latency_s": self.probe.latency_s if self.probe else None, | |
| } | |