Logo
Deploy Now

Categories

Self-Hosted Developer Tools AI LLM MCP Team Collaboration Agents

Stars

522

Forks

6

Watchers

1

Developer links

Last Updated: 08-22-2026 08:48 AM (UTC)

GoRaven

GoRaven transforms AI chat from a question-answer window into a full engineering workstation where agents read files, write code, run shell commands, query databases via MCP tools, and deliver structured results — orchestrating across OpenAI, Claude, DeepSeek, Gemini, Qwen, GLM, and Ollama with task-based routing that allocates the right model for each job based on cost and capability. Built on a Go backend using the Freedom framework with Iris HTTP and a React/TypeScript frontend powered by Vite and Tailwind CSS, each user operates in an isolated workspace with team-shared project areas and centrally managed model quotas. The skill marketplace packages prompts, scripts, and workflows as reusable installable units with automatic dependency resolution and centralized versioning. MCP toolchain integration connects agents to internal APIs, databases, private services, and CLI tools so they query data, invoke services, and trigger actions directly. RAG-powered knowledge bases ingest policies, documentation, and business data for real-time retrieval during planning, coding, and Q&A with source attribution. Long-running task support decomposes complex work through a main agent coordinating sub-agents that execute in parallel across sessions. Plugin hooks inject custom logic at conversation start and end, tool calls, and SSE event streams without forking core code. The operations dashboard tracks usage metrics, model consumption, and team activity. Supports SQLite, MySQL, or PostgreSQL with Redis or local memory caching. Deploy with a single Docker command. Running on a dedicated VPS on RepoCloud with guaranteed CPU, RAM, and SSD, full root SSH access, and a browser serial console. Apache 2.0 licensed.

GoRaven
GoRaven
GoRaven
GoRaven

Benefits

  • Multi-Model Task Routing
  • Route tasks across OpenAI, Claude, DeepSeek, Gemini, Qwen, GLM, and Ollama based on cost and quality requirements with no vendor lock-in or API key restrictions.
  • Isolated Team Workspaces
  • Each team member gets an independent filesystem workspace with shared project areas while admins control model quotas, tool permissions, and data access policies centrally.
  • Reusable Skill Marketplace
  • Package prompts, scripts, and workflows as installable skills with automatic dependency resolution and centralized versioning so solutions discovered once benefit the entire team.
  • MCP Tool Integration
  • Connect agents to internal APIs, databases, private services, and CLI tools via the Model Context Protocol so they query data, invoke services, and trigger actions directly.

Features

  • Model Orchestration
  • Task-based routing across OpenAI, Claude, DeepSeek, Gemini, Ollama, Qwen, and GLM with cost-quality allocation and no vendor lock-in.
  • RAG Knowledge Base
  • Ingest documents, policies, and business data into vector storage for real-time retrieval during agent planning and execution with source attribution.
  • Long-Running Tasks
  • Main agent decomposes complex work into sub-agents that execute in parallel across sessions, breaking free from single-turn constraints.
  • Plugin Hooks
  • Lifecycle hooks inject custom logic at conversation boundaries, tool calls, and SSE event streams without modifying core code.
  • Operations Dashboard
  • Track usage metrics, model consumption, cost allocation, and team activity in a unified admin view for continuous optimization.