SiliconDevBuilt for Apple Silicon.

Local inference. MLX-native fine-tuning. Your data never leaves your machine.

MLX-Native Training & DPO

LoRA, QLoRA, and DPO preference training on M-series unified memory. Every diff approve/reject becomes training data automatically.

Full-context chat runs offline. Conversations, branching, search, and syntax validation included.

Ingest documents into local collections. Query them at inference time. Optional web retrieval via DuckDuckGo.

NanoCore agent with diff proposals, self-healing, and subagent workers. Delegate code review, test writing, docs, and bug fixing to focused workers.

Connect to MCP servers. Discover and execute tools. Generate training datasets from tool schemas.

CSV and JSONL preview. Column mapping, format conversion, PII stripping. Synthetic data generation via MCP.

Pull from Hugging Face. Auto-discover from LM Studio and Ollama. Load, unload, quantize, export. Route different models to different agent roles.