isaachinman/encephalon

Persistent, searchable engineering memory for AI coding agents. Saves ~50% tokens and ~30% time while planning

Open-source, Git-native memory for AI coding agents — deterministic local recall for Claude Code, Codex, Cursor, Gemini CLI, and compatible tools.

Persistent memory plugin for Codex. Obsidian-style knowledge base that survives across sessions

Local, git-versioned memory for AI coding agents. No RAG, no Docker, no external service. Capture, compile, recall over a local LLM wiki with on-device embeddings and an MCP server.

Memory Engine is a local-first MCP server that gives coding agents persistent, evidence-backed project memory. It automatically builds a project knowledge base, retrieves relevant architecture, constraints, incidents, and source context before complex tasks, and retains verified lessons after successful work.

Git-native memory for coding agents. Repo memory before the diff.

Your coding agent starts every session blank. Rekal is the memory your team is missing

Team memory for engineers and their AI agents. Lives in your repo. Shared through Git.

Markdown-first shared memory vault for Claude Code and Codex with SQLite, Zvec, Git, closeout, and audit