Skip to main content

Blog

Notes on smaller agent workflows.

Engineering, releases, and design tradeoffs for token-light local AI agents.

Recent posts

Engineering · Aug 22, 2026

What We Learned From Benchmarking Web Research Agents

We built an agent-in-the-loop benchmark to compare web research systems. The scores were useful, but the traces taught us much more about retrieval, context, latency, and tool design.

Releases · Aug 19, 2026

Link Discovery Without a Crawler: TinySearch 0.6.0

Scraping needs URLs you already have. Crawling follows links on its own budget. TinySearch 0.6.0 adds bounded related links so the agent picks the next page, plus support for an external browser over CDP.

Ideas · Aug 16, 2026

TinySearch vs. Tavily, Exa, Perplexity Sonar, and Brave Search API

How TinySearch's self-hosted, no-key research pipeline compares to Tavily, Exa, Perplexity's Sonar API, and Brave's Search API for AI agents.

Ideas · Aug 15, 2026

TinyContext vs. Mem0 and Zep: Memory for AI Agents Without a Second Database

Mem0 and Zep give agents durable memory, but both expect you to run a vector or graph database alongside them. TinyContext keeps memory in one SQLite file.

Engineering · Aug 14, 2026

What Crawl4AI Does, and What TinySearch Adds on Top of It

Crawl4AI turns a known URL into clean markdown. TinySearch uses it for exactly that, then adds the search step, chunk ranking, and an MCP interface around it.

Engineering · Aug 12, 2026

How to Add Web Search to a Local LLM Agent

A practical shape for adding source-grounded web research to local MCP agents, using search, crawl, chunk, and rerank instead of raw pages.

Ideas · Aug 10, 2026

Why Raw Webpages Are Bad Context for AI Agents

Raw HTML is long, noisy, and expensive to put in a prompt. Agents need ranked evidence, not pasted webpages.

Engineering · Aug 7, 2026

SearXNG vs DuckDuckGo for Agent Search

What actually differs between SearXNG and DDGS as a search backend for local MCP research agents, and how to configure either one in TinySearch.

Ideas · Aug 5, 2026

How to Reduce Token Usage in AI Agent Workflows

Reduce token usage in agent workflows by retrieving selectively, chunking aggressively, and treating context as a budget instead of a dump.

Releases · Aug 3, 2026

TinySearch: Open-Source MCP Web Research for Local LLMs

TinySearch is the first TinySuite tool: a self-hosted research layer for MCP agents that turns a question into cited, chunked evidence.