GenKitKraft

Self-hostable platform for configuring and running LLM agents. Built on Google Genkit (Go SDK). Configure providers, create agents with custom instructions, connect MCP tool servers, and expose everything through an OpenAI-compatible API.

Features

• Any LLM provider: Google AI, OpenAI, Anthropic, Vertex AI, Bedrock, Azure, xAI, DeepSeek, Ollama
• Agent builder UI: Create agents with system prompts, model selection, temperature, and tool config
• MCP tool support: Connect tools via MCP servers (SSE and Streamable HTTP transports)
• MCP server: All management APIs exposed as MCP tools — build agents on top of GenKitKraft with any MCP client
• OpenAI-compatible API: /v1/chat/completions with streaming support, works with any OpenAI client
• Single binary: Frontend embedded in the Go binary, SQLite by default, zero external dependencies
• Smart tool selection: Three tool modes (manual, auto-search, hybrid) to avoid context pollution

MCP Server — Build Agents Programmatically

GenKitKraft exposes all management APIs as MCP tools. Connect any MCP client (Claude Desktop, Cursor, custom agents) to create providers, agents, prompts, and tools — no UI needed.

// Claude Desktop config (~/.config/Claude/claude_desktop_config.json)
{
  "mcpServers": {
    "genkitkraft": {
      "command": "npx",
      "args": ["mcp-remote", "http://localhost:8080/mcp"]
    }
  }
}

A built-in create-agent prompt guides the LLM through the full workflow. See the MCP Quickstart and Agent Creation Guide for details.

Docs

https://DEEJ4Y.github.io/genkitkraft/

Developer docs live under docs/:

• Hexagonal Architecture Guide - project structure, patterns, dependency rules
• TypeSpec Guide - API contract definitions

API spec implementations and generated OpenAPI output are in spec/.

License

MIT