LoreKit gives AI coding agents persistent, shared memory that survives across sessions, repos, and tools like Claude Code, Cursor, and Codex. Memories are scoped (global, project, repo, branch) and automatically retrieved with the narrowest applicable context. It integrates via MCP, supports GitHub webhooks for PR feedback, and includes a dashboard to browse, curate, and monitor agent memory in real time.
LoreKit is a Coding AI & assistants project. AI coding agents forgetting context and repeating questions between sessions and across different tools. It is built as an open-source project for developers using AI coding agents. The project is open source (MIT). It runs on the web and the command line, and it can be self-hosted.
It is developed by LoreKit, and it first shipped in 2026. The project is developed in the open on GitHub with 491 commits in the last 90 days. Among its 5 catalogued features are Persistent Memory, Scope-aware Storage, and Session Sharing. 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