
needle
by cactus-compute (organization)
Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers. (description from the project’s GitHub page)
Repository facts
- Stars
- 14,078
- Forks
- 1,059
- Open issues and pull requests
- 28
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- cactus-compute · Organization
- Created
- Feb 24, 2026
- Last push
- Oct 17, 2026
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 8,162: DenisovAV/flutter_edge_ai
On-device AI for Flutter — Gemma and other LLMs, multimodal, function calling, embeddings, RAG and speech on Android, iOS, Web, macOS, Windows and Linux.
641 starsDartMITLast push Oct 18, 2026
Rank 3,327: antoinezambelli/forge
A Python framework for self-hosted LLM tool-calling and multi-step agentic workflows
2,257 starsPythonMITLast push Oct 15, 2026
Rank 1,326: cactus-compute/cactus
Quantization, kernels, runtime and inference engine for mobiles, wearables, smart home and robots.
6,128 starsC++Other licenseLast push Sep 26, 2026
Rank 4,946: feder-cr/jev
jevos: an open-source alternative to Jev and Microsoft-Decision-1. Yes/no decisions, choices and scores with probabilities, on your laptop's CPU.
1,354 starsC++MITLast push Oct 16, 2026
Rank 8,244: Helldez/BigMoeOnEdge
Run MoE models bigger than your RAM. Frontier-size MoE on a 12 GB phone, lossless, on stock llama.cpp
631 starsC++Apache-2.0Last push Oct 18, 2026
Rank 2,456: TanStack/ai
🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.
3,202 starsTypeScriptMITLast push Oct 18, 2026