TinySearch
Web research for the model. It searches, reads and reranks pages locally, then returns compact evidence with its sources attached. No search API key.
- Search and page reading
- Source-grounded results
- A browser for pages that need clicking
TinyWebUIOpen source
A local chat that can
search and remember.
TinyWebUI is a small chat workspace for any OpenAI-compatible model. It comes with web research and long-term memory already connected, and keeps your chats, documents and tool output in one SQLite file on your machine.
npx tinywebuiBundled with web search and memory.
TinyWebUI ships with two TinySuite MCP servers switched on. One brings in evidence from the web. One keeps the useful parts close. Both also work on their own with any MCP client.
TinyContext
Memory across chats. It stores concise facts in local SQLite and recalls only the ones that fit the available context.
- Local, durable memory
- Hybrid keyword and vector recall
- Token-aware retrieval
From zero to a working chat.
No account, no hosted backend, no build step and no frontend framework. Settings live in a config file you can read, and every change in the Settings panel is written back to it.
Run one command
npx tinywebui starts the server on 127.0.0.1:7777. It needs Node.js 22.13 or later, and uv for the bundled tools.
Point it at a model
OpenRouter, OpenAI, Groq, or a local runtime like Ollama, vLLM, LM Studio or llama.cpp. Anything that speaks the OpenAI API.
Ask something real
TinySearch and TinyContext are already connected, so the first chat can search the web and remember what matters.
Context is a budget.
TinySuite favors selected evidence and durable facts over raw pages, old transcripts, and undifferentiated history. TinyWebUI applies the same rule to the chat itself: large tool results are compacted once, prompt caches stay warm, and every round shows where its tokens went.