#Local context for AI agents
AgentGraph is a local-first, self-hosted CLI and MCP server that turns the sources you choose into a graph of messages, documents, people, feeds, pages, and relationships that your agent can use for reasoning.
AgentGraph observes the sources that you give it access to, so that it can provide your AI agents with the context they need.
#Connectors
Connectors provide access to the services you use. AgentGraph provides a number of connectors for common services, but new connectors can also be added to allow integration with other services.
You can extend AgentGraph by adding connectors for other online services and APIs.
- GmailEmail threads and participants
- Google Drive, Docs, SheetsFiles, content, and ownership
- SlackMessages, threads, and people
- DiscordChannels, threads, and people
- RSSFeeds, posts, and authors
- WebPages and bookmarks
Explore connectors or build your own.
#Local by design
Indexed content is stored in SQLite on your machine. Source API calls run from your machine under your credentials. The project does not operate a hosted graph service or receive indexed content through a project-controlled backend.
An MCP client can read content from the local graph and is governed by that client's data practices. Read the Privacy Policy, Terms of Service, and retention model.
#Explore the docs
- Install to connect sources and an optional MCP client.
- How it works for observation, fetch, refresh, and the graph model.
- CLI reference for command details. MCP clients discover the tools exposed by the server directly.