Device-native foundation models: 145B on a laptop, 35B on a phone. Latent MoE, SSD-streamed weights, a router that predicts loads a step ahead. Mac, iPhone, Android, Windows.
- edge-ai
- foundation-model
- on-device-ai
96,838 visible repositories in the index
121–144 of 1,046 · Most stars
Device-native foundation models: 145B on a laptop, 35B on a phone. Latent MoE, SSD-streamed weights, a router that predicts loads a step ahead. Mac, iPhone, Android, Windows.
The Open Runtime for AI Agents
MiniCPM5: SOTA on-device LLMs, small yet powerful.
Low-code framework for building custom LLMs, neural networks, and other AI models
free online AI resume editor,the only official website is https://magicv.art
Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.
Official JavaScript / TypeScript library for the OpenAI API
QLoRA: Efficient Finetuning of Quantized LLMs
A self-hosted, offline, ChatGPT-like chatbot. Powered by Llama 2. 100% private, with no data leaving your device. New: Code Llama support!
Generates original ARC-AGI-1-style tasks distribution-matched to the public eval set.
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
All-in-one LLM CLI tool featuring Shell Assistant, Chat-REPL, RAG, AI Tools & Agents, with access to OpenAI, Claude, Gemini, Ollama, Groq, and more.
Open-source AI brand visibility and competitor reports. Official website: https://niubigeo.ai/ | Paid services: AI testing by real people and GEO optimization. Pricing: https://niubigeo.ai/pricing
An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)
Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.
Open-source inference platform for language, vision, embedding, reranking, image, audio, and video models. Deploy with multiple engines across heterogeneous hardware, from a laptop to a distributed cluster. Serve models through OpenAI-compatible APIs.
An Application Framework for AI Engineering
High accuracy RAG for answering questions from scientific documents with citations
~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private documents. Everything Local & Encrypted.
Observability and enforcement for AI agent harnesses. Capture every run and runtime reliability with policy enforcement.
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
An AI-powered search engine with a generative UI
❯ Lightweight, beautiful and user-friendly interactive prompts