Mcp
Long-term memory for AI coding agents: durable project facts, recalled by every MCP client.
Brainfeather is a memory layer for coding agents, served over MCP. Memories are scoped to a repository and can be narrowed to a branch or a task. Inferred facts wait at a review queue and do not enter recall until you approve them.
Superseded facts are kept for history but no longer returned. A memory server exposed over MCP works with every compatible client at once: Claude Code, Cursor, OpenCode and agents you build yourself read and write the same store. Brainfeather is in early development and free while it is.
Summary drafted from the project's own website. Every sentence is backed by text on that page and was reviewed before publishing.