Search

More Filters

Show More
Add Listing
Go Back

Dive

0
New
Multi-Agent Platforms & Frameworks
Report

Report Abuse

Basic Information

Dive is an open-source desktop host application designed to run and manage Model Context Protocol (MCP) tools and to integrate those tools with large language models that support function calling. It provides a user-friendly host for both local MCP servers and managed cloud MCP services so users can run agent-style tools like web fetchers, filesystem accessors, and media downloaders alongside ChatGPT, Anthropic, Ollama and other OpenAI-compatible models. The app targets both beginners and advanced users by offering one-click cloud connections to managed MCP servers and configurable local server commands. It ships in two architectures, Electron and a smaller modern Tauri build, and includes internationalization, auto-update support, and configurable model and API key management.

Links

Stars
1529
App URL
https://github.com/OpenAgentPlatform/Dive
Github Repository
https://github.com/OpenAgentPlatform/Dive/blob/main/README.md

Categorization

App Details

Features
Dive offers universal LLM compatibility with models that support function calling and supports multiple transports including stdio, SSE and streamable HTTP for external MCP servers. It has dual architecture builds with a compact Tauri installer and a traditional Electron client. OAP cloud integration provides one-click connections to managed MCP servers and zero-configuration usage for beginners. Advanced users can configure local MCP servers through JSON settings and add tools such as fetch, filesystem server and yt-dlp driven YouTube downloaders. The app exposes model_settings.json for managing multiple API keys and model switching, granular enable/disable control for individual MCP tools, multilingual UI and custom system prompts, plus an auto-update mechanism.
Use Cases
Dive reduces friction for deploying and using MCP-based agents by centralizing configuration, tool management and model connections in a desktop app. Beginners can avoid installing Python, Docker or complex dependencies by using managed cloud MCP servers, while experienced users retain full local control and can extend functionality with custom MCP server commands. The application simplifies switching models and API keys, enables streamed and SSE-based tool integrations for real-time agent behavior, and provides a smaller installer option for resource-constrained environments. Its tool enable/disable controls, model configuration file, and built-in update system make it practical for testing, demonstration and production hosting of tool-augmented LLM workflows. Community support and build guidance are available through the project channels and build documentation.

Categories

Content Creation (5042)
Monetization & Business (2246)
Development Tools (1407)
Marketing & Social Media (1403)
Education & Career (1380)
Multi-Agent Platforms & Frameworks (1009)
Health & Life (957)
AI Resources (920)
Agents & Automation (778)
Data & Analytics (764)
Productivity Tools (679)
Writing & Editing (666)

Similar Listings

listing image

virtual lab

0 (0 review)
listing image

mnemo

0 (0 review)
listing image

EdgeChains

0 (0 review)
listing image

RAG Agents Accelerator

0 (0 review)
listing image

LLM Zero to Hundred

0 (0 review)

Featured Listings

Tags

Please fill the required fields*