Skip to main content

​
Summer Engine with Local Models

Summer Engine is the game engine built for AI, and you don’t need an AI subscription to use it. Any local model that handles tool calling can drive the engine through MCP: add nodes, set properties, search and import assets, run the game, and debug. Engine control and asset search are free; cloud generation (3D models, images, audio) uses credits. This page covers the three setups that actually work in 2026.

​
Prerequisites

  • A GPU with 12 GB+ of VRAM (or Apple Silicon with 16 GB+ unified memory). 24 GB is the sweet spot.
  • Node.js 22+: For running the MCP server
  • Summer Engine: Open with your project, for engine work only
  • Sign in once: npx -y summer-engine@latest login. One browser sign-in also connects the store, publishing and Grow tools

​
Option 1: LM Studio (easiest)

LM Studio is both the model runtime and an MCP host — one app, no terminal.
This writes the summer-engine server into ~/.lmstudio/mcp.json. Then, in LM Studio:
  1. Download a model in the Discover tab (see model picks below).
  2. Toggle the summer-engine MCP server on in the Program tab.
  3. Raise the model’s context length to 32k or higher when loading it. Models load with the context baked into their metadata — often ~4k, which MCP tool schemas overflow silently.
  4. Keep KV-cache quantization off for long agent sessions. On Apple Silicon, prefer the MLX builds.
Every engine call shows a confirmation dialog you can review before it runs.

​
Option 2: OpenCode + Ollama (terminal)

The most common pairing in 2026. Ollama serves the model; OpenCode is the agent.
Then point OpenCode’s provider at Ollama (http://localhost:11434/v1 as an OpenAI-compatible endpoint) and select your model. Run ollama ps to confirm the bigger context hasn’t pushed the model off the GPU. The same Ollama backend works with Kilo Code in VS Code (npx -y summer-engine@latest setup kilo-code --yes) — set the context window to 32k+ in Kilo’s provider settings.

​
Option 3: Goose (agent-first)

Goose is an open-source agent that treats MCP servers as extensions.
  1. Run npx -y summer-engine@latest setup goose --yes (it writes the extension into ~/.config/goose/config.yaml), or run goose configure → Add Extension → Command-line Extension, command: npx -y summer-engine@latest mcp
  2. Run goose configure → Configure Providers → Ollama, host localhost:11434
  3. Pick a model with native tool calling — Goose’s toolshim mode for non-tool-calling models is slower and less reliable.
In Goose Desktop, both live under Settings → Extensions and Settings → Providers.

​
Which Model to Run

Tool calling is the hard part for local models. Use Q4_K_M quantization or better — heavier quantization breaks tool calls before it breaks chat.

​
Troubleshooting

  • The model never calls tools, or hallucinates them: context window too small. MCP tool schemas plus the system prompt overflow a 4k–8k window instantly. Set 32k minimum, 64k recommended. To list fewer tools, set up with the engine profile: npx -y summer-engine@latest setup <agent> --yes --profile engine.
  • Tool calls come out malformed: quantization too aggressive (use Q4_K_M+), or the model is too small (7B is the practical floor, 14B+ for multi-server setups).
  • Cline users: Cline’s “compact prompt” option for local models disables MCP entirely. Keep the full system prompt on.
  • Slow first response: keep only a couple of MCP servers enabled so tool schemas leave room for actual work.

​
What’s Free and What Isn’t

Sign in once with npx -y summer-engine@latest login: the account is the rate-limit key, not a paywall.
Need help? Ask in Discord first. That is where you get the fastest reply and support. For concrete help, email support@summerengine.com or founders@summerengine.com.