Summary
GLIA launched as a local memory infrastructure that runs both as a browser extension and an MCP server, letting chats and coding tools read and write to the same SQLite-backed memory store. The product emphasizes zero-cloud persistence, native MCP tools, and project-scoped recall for tools such as Cursor, Claude Code, Windsurf, and VS Code.
What changed
GLIA introduced a shared local memory layer spanning browser chats and coding agents, with a browser extension, MCP server, and one shared SQLite database.
Why it matters
Developers increasingly split work between browser chats and coding agents, which creates fragmented context. GLIA matters because it treats memory portability across those surfaces as the product, reducing the need to restate prior decisions or manually sync context between tools.
Evidence excerpt
GLIA says it provides persistent memory for browser chats and coding agents through one local database, exposes native MCP tools such as recall_context and store_memory, and keeps memory scoped by project.