Vibe Coding Discoverneedle
View on GitHubAutomation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.
Needle is an 8-29 MB 2-bit foundation model and Python toolkit for on-device tool calling, structured JSON extraction and text embeddings. It ships inference, LoRA fine-tuning and per-platform builds for phones, wearables, robots, cars and microcontrollers.
Use Cases
on-device tool calls on phones and wearablesstructured JSON extraction from messy textlocal text embedding for search and routingsmart home and IoT voice assistantsrobotics and automotive on-device agentsoffline or air-gapped inferencecustom LoRA fine-tuning on a product's own toolsdeploying to microcontrollers with sub-1MB enginesschema-constrained extraction and classificationconfidence-based act/confirm/refuse routing
Built With
- Language
- Python
- Frameworks
- JAX · Flax · Optax · Hugging Face Hub · safetensors · SentencePiece · NumPy · pytest · Pydantic · setuptools
Tags
on-device-ai · edge-ai · tinyml · tool-calling · function-calling · llm · embeddings · structured-extraction · quantization · 2-bit · lora · fine-tuning · foundation-model · microcontrollers · wearables · offline-inference