Engraphis

Building Engraphis for coding agents

About

Founder of Engraphis, an open-source, local-first memory engine for coding agents. I build developer tools that make agent context durable, scoped, and inspectable across sessions and repositories.

Links

Engraphis

Badges

Tastemaker

Gone streaking

Maker History

EngraphisInspectable memory for coding agents
Nov 2026

🎉

Joined Product HuntJuly 10th, 2026

Forums

p/engraphis

•

24h ago

What should a coding agent remember between sessions?

I keep seeing the same failure: the agent can solve a task in one session, then starts the next session without the decisions that shaped the code. I built Engraphis to make memory scoped by repo and session and inspectable. Before launch tomorrow, I am curious what people here think is actually worth remembering: architecture decisions, bug fixes, team conventions, failed approaches, or something else? And what should the agent deliberately forget?

•

4h ago

Engraphis - Local-first memory for coding agents

Engraphis gives Claude Code, Cursor, and Codex durable memory across sessions. Decisions are stored in local SQLite with workspace and repo scope, retrieved with vector, lexical, graph, and code-aware search, and exposed over MCP. The local core is free and Apache-2.0. Pro adds hosted memory health and sync.

•

5mo ago

What are you building? Drop your AI product below

Doing one of these because I get more from reading what others are building than from any newsletter.

I'll start.