Docmancer runs locally to create a durable, shared memory layer for AI coding agents like Claude Code, Cursor, and Gemini. It scans existing agent outputs, builds a canonical Markdown knowledge base, and serves it back through a CLI, MCP server, or agent plugins. This eliminates repetitive context provision and enables consistent project understanding across multiple agents.
In the Other AI space, Docmancer takes a focused approach. AI coding agents losing context when switching between different tools or sessions, requiring repeated project explanations. Docmancer is an open-source project aimed at developers using AI coding agents. Docmancer follows a freemium model. It runs on the command line, and it can be self-hosted.
Docmancer builds and maintains Docmancer, and it first shipped in 2026. The project is developed in the open on GitHub with 115 stars and 126 commits in the last 90 days. Key capabilities include Shared Agent Memory, Markdown Knowledge Base, and CLI Interface. It exposes integrations via an MCP server.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do