AtomicBot-ai/Atomic-Chat

Health v2 · maintenance only

Flags: young no_license

Adoption not part of the score

1374 stars · 158 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Atomic Chat is an open-source desktop and mobile application with a built-in inference engine for running open-weight LLMs fully locally and offline. It supports GGUF and MLX models, one-click agent setups, MCP integration, and includes TurboQuant quantization for faster, memory-efficient inference.

Use cases

• run chatgpt-like ai locally without internet
• chat with local llms privately on my mac
• run deepseek or qwen models offline on windows
• use ai agents without sending data to the cloud
• run open-weight models on iphone or android
• quantized local llm inference with low memory

When to choose

• you need fully private, 100% offline LLM usage on desktop or mobile
• you want one-click setup for local models and agents with MCP support
• you're on Apple Silicon and want MLX/GGUF inference with quantization speedups

When to avoid

• you need cloud-scale serving or multi-user deployment
• you rely on the latest proprietary frontier models (GPT-4, Claude)
• you need a permissive open-source license - the license is custom/unverified

Facets

application · maturity active

llm-inference chatbot chat-interface agent-framework mcp large-language-models artificial-intelligence self-hosted privacy windows cross-platform local-llm gguf llamacpp mlx apple-silicon offline-ai turboquant open-weight-models local-first ai-agents macos linux ios android desktop mobile tauri

Member repositories

For agents

markdown · JSON · MCP: product_card(name="AtomicBot-ai/Atomic-Chat")