engraphis MCP Server
Coding-Dev-Tools/engraphis
[](https://agentrank-ai.com/tool/Coding-Dev-Tools--engraphis/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
Coding-Dev-Tools/engraphis is a Python tool licensed under Apache-2.0. Local-first, inspectable memory for coding agents: durable context across sessions and repositories, code-aware recall, bi-temporal history, MCP, and a self-hosted WebUI. Topics: agent-memory, ai-agents, developer-tools, knowledge-graph, local-first, mcp, python, self-hosted.
Ranked #6750 out of 24846 indexed tools.
Ecosystem
Score Breakdown
180 stars → growing community
Last commit 1mo ago → recently updated
0/6 issues closed → many open issues
5 contributors → small team
No dependents → no downstream usage
107 weekly installs → early adoption
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
How to Improve
Badge all embed codes →
[](https://agentrank-ai.com/tool/Coding-Dev-Tools--engraphis/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) <a href="https://agentrank-ai.com/tool/Coding-Dev-Tools--engraphis/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/Coding-Dev-Tools--engraphis" alt="AgentRank"></a> Matched Queries
From the README
# Engraphis
**Persistent, local-first memory for AI agents.** Engraphis stores scoped project knowledge, retrieves relevant evidence across vector, lexical, graph, and code search, and returns bounded context with sources an agent can inspect.
The local engine uses SQLite and works offline. It keeps changes over time instead of silently replacing facts, and grounded recall cites retrieved memories or abstains when evidence is weak.
<p align="center">
<br>
<sup>Explore memories and their relationships in the local dashboard.</sup>
</p>
## Install and try it
The full local application requires Python 3.10 or newer. The NumPy-only core supports Python 3.9+.
```bash
python -m pip install "engraphis[all]"
engraphis-dashboard
```
The dashboard opens at [http://127.0.0.1:8700](http://127.0.0.1:8700). Local use needs no cloud account or API key.
To use the Python service directly:
```python
from engraphis.service import MemoryService
memory = MemoryService.create("engraphis.db Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.