A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

The most no-nonsense, locally or API-hosted AI code completion plugin for Visual Studio Code - like GitHub Copilot but completely free and 100% private.

Create chatbots with ease

Local CLI Copilot, powered by CodeLLaMa. 💻🦙

The leading open-source AI copilot for JetBrains. Connect to any model in any environment, and customize your coding experience in any way you like.

An open-source alternative to GitHub copilot that runs locally.

Make Llama2 use Code Execution, Debug, Save Code, Reuse it, Access to Internet

Use Code Llama with Visual Studio Code and the Continue extension. A local LLM alternative to GitHub Copilot.

An AI code interpreter for sensitive data, powered by GPT-4 or Code Llama / Llama 2.

Local first semantic code search and chat powered by vector embeddings and LLMs

Loz is a command-line tool that enables your preferred LLM to execute system commands and utilize Unix pipes, integrating AI capabilities with other Unix tools.

Octogen is an Open-Source Code Interpreter Agent Framework

Open source chat kit engineered for seamless interaction with AI models.

Deploy a RESTful API Server to interact with Ollama and Stable Diffusion

Benchmark your local LLMs.

Codellama Instruct OpenAi style api.

RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair http://arxiv.org/pdf/2312.15698

codellama on CPU without Docker

SHUKUN AI is an AI-native database search application that helps companies explore and analyze data. SHUKUN AI provides a feature that helps you split complex natural language tasks into smaller parts then combines them into the results.