Introduction

Engrams gives your AI coding assistant a persistent memory. Instead of forgetting everything between sessions, your AI remembers the decisions you've made, the patterns you follow, and the progress you've tracked — and brings up the right information exactly when it's needed.

Just want to dive in? Skip straight to Installation or the Quick Start guide.

What problem does Engrams solve?

Have you ever had to remind your AI assistant — again — that your project uses a specific framework, or that you already decided on a certain database? AI coding tools are powerful, but they start every conversation with a blank slate. The bigger your project gets, the more time you spend catching your AI up.

Engrams fixes this. It gives your AI a long-term memory for your project. When you make a decision, Engrams saves it. Next time your AI needs that context, it's already there — automatically. No copy-pasting, no re-explaining.

Stored knowledge types

TypeDescriptionExample
Decisions Choices you've made and why "Use PostgreSQL for the database — it handles complex queries better"
Progress What's done, what's in progress, what's next TODO → IN_PROGRESS → DONE
Patterns Repeatable approaches your team follows "All API responses use the same error format"
Context The big picture — project goals, current focus What the project is about and what you're working on now
Custom Data Anything else worth remembering Glossary terms, internal specs, style guides

Key capabilities

  • Team sync via Git — decisions are written to .engrams/ as markdown files, committed alongside your code
  • Decision enforcement — your AI checks existing team decisions before proposing changes
  • Smart search — find relevant decisions even if you use different words
  • Codebase links — connect decisions to specific files so context appears when your AI opens them
  • Cost control — only the most relevant items are included, so your AI stays fast and affordable
  • Team rules — set project-wide standards that every contributor's AI respects
  • Visual dashboard — explore your project knowledge in an interactive browser-based view

Architecture overview

Engrams runs quietly alongside your AI coding tool. It works with popular tools like Roo Code, Cline, Cursor, and Windsurf. Each project gets its own storage — a .engrams/ directory for team-shared markdown files (committed to Git) and a local engrams/context.db SQLite cache. Your data stays local and separate per project.

You
↔
AI Agent
(Roo, Cline, Cursor…)
↔
Engrams MCP
(uvx engrams-mcp)
↔
.engrams/
Team markdown (Git)
SQLite DB
engrams/context.db (local)

Next steps