An AI agent based on the Ollama large model, capable of executing Linux commands through natural language and invoking kernel hooks to delve into the underlying system.

[![go](https://img.shields.io/badge/Go-1.24+-66C9D6)]() [![ver](https://img.shields.io/badge/version-0.3.0.dev-E940AF)]() [![go](https://img.shields.io/badge/license-MIT-E940AF)]()

## Abilities & Possibilities [✔] Support all large models locally in Ollama [✔] langchain and langgraph integration [✔] multi-modal LLM's support [✔] only tool calling support [✔] redis-vector and RAG integration [✔] eBPF integration (Only supports Linux kernel 5.10 and above.) [✔] dangerous command detection [×] support memory and context （Coming soon） [×] It will not run directly at the moment.（Currently, it is an experimental version and not suitable for direct execution.） ## Mechanism

## How to run 1. This project uses Redis vector as the vector database, so Redis must be started first. ``` docker run -p 6379:6379 docker.io/redislabs/redisearch:latest ``` 2. Set environment variables ```shell export KPT_MODEL="" # "please select the llm export KPT_OLLAMA_URL="http://127.0.0.1:11434" export KPT_REDIS_URL="redis://127.0.0.1:6379" ``` 3. Compile the code ``` make ``` 4. ```shell # ./kernal_gpt _ _ _ | | __ ___ _ __ _ __ __ _ | | __ _ _ __ | |_ | |/ / / _ \ | '__| | '_ \ / _` | | | _____ / _` | | '_ \ | __| | < | __/ | | | | | | | (_| | | | |_____| | (_| | | |_) | | |_ |_|\_\ \___| |_| |_| |_| \__,_| |_| \__, | | .__/ \__|

Agents

LightningRAG

kernal-gpt