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

Enterprise knowledge RAG

Governed RAG over company docs, tickets and wikis with permissions and observability.

4 pieces4 setup stepsscenario: Private LLMs and knowledge bases for the enterprise

What goes in it

  1. 1

    WeKnora AI notes & knowledge management Open source

    Parsing & ingestion

    Tencent's open LLM knowledge platform: docs → RAG → agents.

    Or: opendataloader-pdf · chandra · unstract

    ★ 35k
  2. 2

    PageIndex Retrieval, vector DBs & embeddings Open source

    Indexing & retrieval

    Document index for vectorless, reasoning-based RAG.

    Or: zvec · airweave · OpenViking

    ★ 39k
  3. 3

    DB-GPT AI notes & knowledge management Open source

    App layer

    Open-source agentic AI data assistant.

    Or: WrenAI · Glean · private-gpt

    ★ 20k
  4. 4

    OpenRouter Model gateways, routing & usage Closed / commercial

    Model gateway

    Unified API gateway to hundreds of models with pay-as-you-go billing.

    Or: OmniRoute · llm-gateway

How to set it up

  1. 01Inventory data sources and the permission model
  2. 02Pick a parser for PDFs and tables
  3. 03Deploy a vector or vectorless index
  4. 04Call models through a gateway with logging and evaluation

Similar stacks: what’s different

  • Enterprise RAG knowledge baseThat one uses mature mainstream parts (RAGFlow, Milvus, LiteLLM) and is the safer default; this one lists newer trending projects

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