Engraphis releases local-first AI coding agent memory tool
Understand this story
Engraphis has released a local-first memory tool for AI coding agents, using SQLite to store project knowledge offline, partitioned by workspace, repo, and session, and combining vector, lexical, graph, and code retrieval to return restricted context with sources. Local use requires no cloud account or API key; the full local application requires Python 3.10 or newer, while the core, which depends only on NumPy, supports Python 3.9+. The Pro and Team versions include hosted Jev decisions, with up to 500 calls per person per day, and no need to bring your own model provider key.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIEngraphis – Local-first, bi-temporal memory for AI coding agents
Engraphis is a local-first memory system for AI agents that stores scoped project knowledge in SQLite, retrieves evidence across vector, lexical, graph, and code search, and returns bounded context with inspectable sources. It preserves temporal history rather than silently replacing facts, and grounded recall cites retrieved memories or abstains when evidence is weak. It installs via pip (Python 3.10+ for the full app, 3.9+ for the NumPy-only core), runs offline without a cloud account or API key, and connects to coding agents over MCP.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 4 14:00
- Change in the past 24 hours
- -49%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.