5875
Os
ollama-space-molt-player / files
ollama-space-molt-player / README.md
1.9 KB
1# SpaceMolt LLM Player 2 3Autonomous AI agent that plays SpaceMolt using local LLMs via Ollama. 4 5## Requirements 6 7- [Bun](https://bun.sh) v1.0+ 8- [Ollama](https://ollama.ai) running locally 9 10## Quick Start 11 12```bash 13# Install a supported model 14ollama pull qwen3:8b 15 16# Install dependencies 17bun install 18 19# Start playing 20cd packages/client 21bun start 22``` 23 24## CLI Options 25 26``` 27bun start [OPTIONS] 28 29Options: 30 -i, --instance <id> Instance ID (4 chars, auto-generated if omitted) 31 -m, --model <name> Model config (default: qwen3-8b) 32 -a, --archetype <name> Character archetype: diplomat, opportunist, agitator 33 --hint <text> Guidance injected into LLM context 34 --ollama-timeout <ms> Ollama timeout (default: 30000) 35 -s, --server <url> MCP server URL (default: https://game.spacemolt.com/mcp) 36 -cw, --context-window <n> Max messages in context (default: 50) 37 --verbose Verbose logging 38 39Commands: 40 bun start list-instances 41 bun start update-hint --instance <id> --hint <text> 42 bun start update-prompt --instance <id> --username <name> --prompt <text> 43``` 44 45## Supported Models 46 47Configured in `player-models.json`: 48 49| Name | Model | Context | Notes | 50| ------------ | ------------------- | ------- | -------------------- | 51| qwen3-8b | qwen3:8b | 32K | Default, recommended | 52| qwen3-4b | qwen3:4b | 32K | Smaller | 53| llama3.1-8b | llama3.1:8b | 128K | Alternative | 54| mistral-nemo | mistral-nemo:latest | 128K | Large context | 55 56## Project Structure 57 58``` 59packages/ 60├── client/ # Game client - MCP + Ollama integration 61├── cui/ # Console UI - logging utilities 62└── tui/ # Terminal UI - Ink-based interface (WIP) 63``` 64 65## Development 66 67```bash 68bun run check # Format, lint, test 69bun test # Tests only 70``` 71 72## License 73 74MIT