Devika is a self-hosted AI coding agent for developers who want to give a software task in plain language and have an agent plan the work, research it and write code. Modeled after Cognition AI's Devin, it runs on your own machine with a browser interface and supports local LLMs through Ollama. It's open source under the MIT license.
The agent breaks a high-level request into smaller steps and uses web searches and browsing to gather relevant information. It can write code in multiple programming languages for tasks such as adding features, fixing bugs or starting a project. The chat interface lets you give further guidance and review generated code and project files, while a visual progress view shows the agent's state. Work is organized by project.
You can choose local inference or hosted models. Supported cloud options include Claude, GPT-4, Gemini, Mistral and Groq, which require API keys and send model requests to those services. Ollama handles model inference locally; web research still uses external search and websites. Devika runs on macOS, Linux and Windows, and the repository also includes Docker deployment files.
Its extensible architecture lets developers add features and integrations. The project warns that some features are incomplete or broken, so it suits experimentation with coding agents where you can inspect the output and tolerate failures.
Claim this page and we'll verify you by hand. Devika gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find Devika?Promote it
Something wrong or outdated on this page?
41.9KUpdated 6 days agoGPL-3.0
macOS · Windows · Linux · iOS · Android · Web#MCP#Multimodal input#Ollama integration
Chatbox is an AI chat client for people who want local models and cloud providers in the same app. It connects to Ollama for local LLM use and supports GPT, Claude, Gemini, Grok and DeepSeek with your own API keys. Chatbox also offers its own hosted model service.
42Updated 12 hours ago
macOS · Windows · Linux · Docker#Agent Skills#Code execution#Distributed execution
127.2KUpdated 24 hours agoApache-2.0
macOS · Windows · Linux#Code execution#Git integration#Human approval
54.8KUpdated 3 hours agoApache-2.0
macOS · Windows · Linux#MCP#Multi-agent workflows#Ollama integration
4.4KUpdated 19 hours agoMIT
macOS · Windows · Linux · Web · JetBrains#Agent Client Protocol#Code execution#Git integration
28.2KUpdated 1 day agoApache-2.0
macOS · Windows · Linux · Web · VS Code · JetBrains#Code execution#Git integration#MCP
Code Buddy is an AI coding assistant for developers who want a terminal agent running on their own machine, with a choice of local or cloud models. It reads repositories, edits code and runs commands on Linux, macOS and Windows. Ollama keeps model inference local without an API key or account; cloud providers send model requests off the machine. Routing includes automatic provider failover.
Codex CLI is an open source coding assistant that runs on your computer and works with local repositories. It's for developers who want to explore code, make changes, and use their existing development tools from the terminal. It runs on macOS, Windows, and Linux under the Apache 2.0 license.
Goose is a general-purpose AI agent that runs on your computer. It suits people who want an agent for coding, research, writing, automation, or data analysis, without committing to one model provider. The desktop app runs on macOS, Windows, and Linux; there's also a CLI for terminal work and an API for use in other software.
gptme is a self-hosted AI agent that works directly in your terminal, with access to your files and installed tools. It's for developers who want a coding assistant in their own environment, and people who want an agent for data analysis or other knowledge work. The software is free under the MIT license and doesn't require a gptme account.
Qwen Code is an Apache 2.0 licensed AI coding agent for developers who want help working through a codebase, changing code and checking the result. It runs on macOS, Windows and Linux, with a terminal interface and a desktop app. It builds on Google Gemini CLI and has developed into an agent that can use Qwen models alongside other model providers.