Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// Software stack

Local private LLM

Keep data on-device while running chat, APIs and simple agents.

4 pieces4 setup stepsscenario: Run models on your own machine

💡 Beginners: LM Studio or Ollama + Open WebUI (see “Run LLMs on your computer”). The chat UI and memory parts here are trending GitHub projects, better for experimenting.

What goes in it

  1. 1

    LM Studio Local inference & serving Closed / commercial

    Inference runtime

    Desktop app to download and run local LLMs with an OpenAI-compatible server.

    Or: osaurus · OpenLLM · colibri

  2. 2

    llmfit Local inference & serving Open source

    Hardware fit check

    One command to find which models and providers fit your hardware.

    Or: whichllm · magnitude

    ★ 38k
  3. 3

    Open-LLM-VTuber AI apps & chat clients Open source

    Chat UI

    Talk to any LLM with hands-free voice and Live2D.

    Or: airi · private-gpt

    ★ 14k
  4. 4

    mempalace Memory & context Open source

    Memory

    Open-source AI memory system with strong public benchmarks.

    Or: supermemory · engram

    ★ 60k

How to set it up

  1. 01Use llmfit / whichllm to see what your machine can run
  2. 02Install LM Studio or osaurus and download a model
  3. 03Turn on the OpenAI-compatible API
  4. 04Connect a memory layer and your usual clients

Similar stacks: what’s different

Data updated: AI software & hot ranks · Solutions & stack guides(UTC+8)