MarcellM01/TinySearch
by Various
Shrink the web for your agents! Token-efficient, fast and fully local web search and research.
MCP
MarcellM01/TinySearch
Added 3 Sept 2026
Overview
TinySearch is a Python library that provides token-efficient, fast, and fully local web search and research for AI agents. It shrinks web content to reduce token usage, enabling agents to search and research without relying on external APIs.
Best for
Best for
Developers building local, token-conscious search for AI agents
Use cases
- Building local search tools for AI agents
- Reducing token costs in research workflows
- Running web research without external services
How to use
Install
uvx --from "tinysuite-search[server]" tinysearch setupClients listed in this record (not verified here)
Continue, ChatGPT
Notes
224 stars on GitHub. Last updated 2026-09-02. Licensed MIT.
Pros
- Fully local, no external API dependencies
- Token-efficient, reduces context size
- Fast search and research
Cons
- Limited community support at 224 stars
- Python only
- May not match the coverage of commercial search APIs
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Crewai
Community
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
OpenDevin
Community
🙌 OpenHands: AI-Driven Development
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.