wellread
Shared research cache for AI agents. Caches web research across sessions and users - hit means instant answer from verified sources, miss means your research saves the next dev's tokens. Semantic search with freshness tracking, gap detection, and real-time token measurement via JSONL. Free, open source.
README
wellread — Another dev already searched that.
The problem
- ❌ Your agent researches every technical question from scratch — 10-20 turns per query
- ❌ When it doesn't search, it hallucinates — outdated APIs, wrong examples, broken code
- ❌ Each turn re-sends your entire conversation history, and the cost compounds
- ❌ Thousands of devs burning tokens on the same questions, every day
The fix
Before your agent searches the web, wellread checks what other devs already found.
- Hit → instant answer from verified sources. Zero web searches. One turn.
- Partial → starts from what exists, only researches the gaps.
- Miss → normal research, then saves it for the next person.
The compounding effect
| Without wellread | With wellread | |
|---|---|---|
| Turn 1 (fresh session) | 200K tokens · 10 turns · 67s | 647 tokens · 1 turn · 28s |
| Turn 30 (~40K context) | 1.2M tokens | 647 tokens |
| Turn 100 (~150K context) | 3.5M tokens | 647 tokens |
| Turn 250 (~480K context) | 11M tokens | 647 tokens |
The deeper your session, the more expensive research gets, and the more wellread saves.
Install
npx wellread
Restart your editor. That's it.
Update: npx wellread@latest · Uninstall: npx wellread uninstall
Singleplayer
Your own research comes back to you. No repeat searches, no hallucinations from stale training data — real sources, verified.
Multiplayer
27 devs already used that Auth.js research before you got here. One person researched, everyone benefits.
Freshness
Each entry knows how fast its topic changes:
| Type | Fresh | Re-check | Re-research |
|---|---|---|---|
| Stable (React, PostgreSQL) | 6 months | 1 year | after |
| Evolving (Next.js, Bun) | 30 days | 90 days | after |
| Volatile (betas, pre-release) | 7 days | 30 days | after |
When an agent re-verifies, the clock resets for everyone.
Privacy
Only generalized research summaries are shared. No code, no file paths, no credentials, no project names. Your agent strips everything private before saving.
Supported tools
Works with any MCP client. Best experience with Claude Code. Also supports Cursor, Windsurf, Gemini CLI, VS Code, OpenCode.
Stats
Ask your agent "show me my wellread stats" to see your search savings, top contributions, and network impact.
Links
License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.