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

Low-code AI workflows

Build AI apps and automations by drag and drop, self-hostable, for teams that do not want to code from scratch.

4 pieces4 setup stepsscenario: Choose tools and avoid pitfalls

What goes in it

  1. 1

    dify Workflow & agent platforms Open source

    LLM app and knowledge-base platform

    Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.

    ★ 159k
  2. 2

    n8n Workflow & agent platforms Open source

    General automation with hundreds of integrations

    Open-source workflow automation with AI agents and hundreds of integrations.

    ★ 208k
  3. 3

    Flowise optional Workflow & agent platforms Open source

    Visual builder for agents and RAG flows

    Build AI Agents, Visually

    ★ 56k
  4. 4

    langfuse optional Observability & tracing Open source

    Monitors model calls inside workflows

    🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

    ★ 36k

How to set it up

  1. 01Choose Dify for chat + knowledge-base apps and n8n for triggered automations across SaaS tools
  2. 02Self-host with Docker Compose (Dify requires at least 2 CPU cores and 4 GiB RAM) or try the official cloud first
  3. 03Add your model provider API key and get one minimal flow working
  4. 04Check licences: Dify and n8n both have extra terms; read them before offering a SaaS

✓ Good fit

  • Build internal AI tools fast without coding from scratch

✗ Look elsewhere if

  • Complex multi-agent logic with full testing: use a code framework

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