Engraphy

Name: Engraphy
Author: devon-clarkk

作者：devon-clarkk版本 0.3.0i★ –i在你的电脑上运行

注册名称io.github.devon-clarkk/engraphy

安装

概览

作者提供的说明（英文原文）

Self-hosted MCP memory server: a typed knowledge graph on Postgres 16 and pgvector.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数：意见、测量和人气是不同的东西。

用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
我们的基础检查i1 项中通过 1 项依据公开信息检查；尚未扫描代码
使用情况i非常新★ –

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

连接方式: 在你的电脑上运行
传输方式: Streamable HTTP
分类: 搜索与 AI 记忆
你需要填写：ENGRAPHY_DATABASE_URL

安装

选择你使用的 AI 应用，然后复制设置。

安装之前

基础检查：1 项中通过 1 项
在你的电脑上运行，拥有你的用户账户的权限（文件、网络、应用）。
需要你自己填写： ENGRAPHY_DATABASE_URL, ENGRAPHY_BIND_HOST, ENGRAPHY_BIND_PORT

标为机密的值是你账户的钥匙。千万不要分享给别人，也不要粘贴到聊天里。

你需要

Docker已安装 Docker

你用的是哪个应用？

ClaudeClaude CodeCursorVS CodeChatGPT

在上方选择你的应用。我们会记住它，下次按钮会显示“安装到 …”。

打开 Claude Desktop → Settings → Developer → Edit Config，把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "engraphy": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "ENGRAPHY_DATABASE_URL",
        "-e",
        "ENGRAPHY_BIND_HOST",
        "-e",
        "ENGRAPHY_BIND_PORT",
        "ghcr.io/devon-clarkk/engraphy:0.3.0"
      ],
      "env": {
        "ENGRAPHY_DATABASE_URL": "your-value",
        "ENGRAPHY_BIND_HOST": "your-value",
        "ENGRAPHY_BIND_PORT": "your-value"
      }
    }
  }
}

在终端中运行这条命令

claude mcp add engraphy --env ENGRAPHY_DATABASE_URL=your-value --env ENGRAPHY_BIND_HOST=your-value --env ENGRAPHY_BIND_PORT=your-value -- docker run -i --rm -e ENGRAPHY_DATABASE_URL -e ENGRAPHY_BIND_HOST -e ENGRAPHY_BIND_PORT ghcr.io/devon-clarkk/engraphy:0.3.0

运行前请先填写空着的值。

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json，或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "engraphy": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "ENGRAPHY_DATABASE_URL",
        "-e",
        "ENGRAPHY_BIND_HOST",
        "-e",
        "ENGRAPHY_BIND_PORT",
        "ghcr.io/devon-clarkk/engraphy:0.3.0"
      ],
      "env": {
        "ENGRAPHY_DATABASE_URL": "your-value",
        "ENGRAPHY_BIND_HOST": "your-value",
        "ENGRAPHY_BIND_PORT": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "engraphy": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "ENGRAPHY_DATABASE_URL",
        "-e",
        "ENGRAPHY_BIND_HOST",
        "-e",
        "ENGRAPHY_BIND_PORT",
        "ghcr.io/devon-clarkk/engraphy:0.3.0"
      ],
      "env": {
        "ENGRAPHY_DATABASE_URL": "your-value",
        "ENGRAPHY_BIND_HOST": "your-value",
        "ENGRAPHY_BIND_PORT": "your-value"
      }
    }
  }
}

浏览器会先询问是否打开应用，然后应用会显示设置并请你确认。密钥的值会留空，由你自己填写。

这个服务器在你的电脑上运行，而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

你的选择通过 Cookie 保存在这台设备上，无需账户。

需要你填写的值

ENGRAPHY_DATABASE_URL 机密必填 env
libpq connection string for a Postgres 16 database with the pgvector extension, reached as the non-superuser `engraphy_app` role. Required: the server refuses to start without it, and refuses to star…
ENGRAPHY_BIND_HOST env
Interface the server binds. Containers reach their own loopback only, so a published container sets 0.0.0.0 and puts the boundary at the port publication and the reverse proxy.
ENGRAPHY_BIND_PORT env
Port the server binds inside the container, matching the port in the transport URL.

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同，请以 README 为准。

它能做什么

它在你的电脑上运行；安装后，工具列表会显示在你的 AI 应用中。

基础检查i

我们检查的是任何人都能看到的信息；我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月9日

✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 devon-clarkk 验证，该账户拥有此仓库
… 尚未检查
仍在维护
我们还没有从 GitHub 读取这个仓库
… 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
– 不适用
端点有响应
它在你的电脑上运行，没有互联网端点
– 不适用
使用 OAuth 登录
在你的电脑上运行，改用本地设置
… 尚未检查
工具描述中没有隐藏指令
它在你的电脑上运行；我们只能读取互联网端点的工具列表

与“搜索与 AI 记忆”中的其他服务器比较i

星标数多于此分类中其他 5747 个服务器的 0%
发布到注册中心的时间比此分类中其他 5747 个服务器的 43% 更新
基础检查结果等于或优于此分类中其他 5747 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时，星标数才计入。

常见问题

Engraphy 安全吗？

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前，请先看看这个服务器要求哪些权限，并使用只具备所需权限的密钥。

它需要哪些密钥或代码？

你需要填写：ENGRAPHY_DATABASE_URL

它在我的电脑上运行还是在云端？

它在你的电脑上运行。你的 AI 应用会在需要时启动它，数据不会经过作者的服务器（除非它自己调用在线服务）。

它还在维护吗？

GitHub 仓库最后更新于–，最新版本（0.3.0）于2个月前进入注册中心。

哪些应用可以使用它？

支持 MCP 的应用，例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Docker。

有什么可以替代它？

同一分类中有：Context7, Codebase Memory, Exa

替代选择

同一分类中其他作者的服务器，按星标数排序。

如何看卡片：↓ 每周下载量i★ GitHub 星标i三大支柱：评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

Context7

Up-to-date docs for AI agents

作者：upstash广泛使用↓ 97.3万/周★ 6.4万前天更新

电脑或云端

安装

Codebase Memory

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

作者：DeusData广泛使用↓ 1.8万/周★ 4.8万22天前更新

在你的电脑上运行

安装

Exa

Connect AI agents to Exa for web search, content fetching, and multi-step research.

作者：exa-labs广泛使用★ 52132个月前更新

在云端运行✓ exa.ai

安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

Engraphy

An MCP server giving AI agents associative memory, modelled on the human mind.

Quickstart · Documentation · Tool reference · Design set · Contributing

The name comes from *engraphy*, an old term from memory science for the process of laying down an *engram*, the trace a memory leaves in the brain. Engraphy does that for agents: it checks each new memory against what it already knows before the write lands, merging restatements, linking genuinely new facts, and never silently overwriting. Nothing is deleted, so history stays walkable.

Engraphy is self-hosted. It stores what an agent learns as a typed knowledge graph on Postgres + pgvector: writes deduplicate themselves against existing memory, retrieval fuses semantic and lexical search, isolation between users is enforced by the database, and the whole shape of memory is declared per application as a pack.

It exists to replace the reference MCP memory server's flat-JSON, single-user, stdio model with something that survives concurrency, paraphrase, duplicates, and years of accumulated memory. It speaks the Model Context Protocol, so any MCP client (a VS Code extension, a desktop app, another agent) can use it over HTTP.

Source-available. Licensed under the Business Source License 1.1: read it,

run it, build on it, and use it in production for your own product. Offering

Engraphy itself as a hosted or managed service to third parties is reserved to

the Licensor until the Change Date, when it converts to Apache-2.0. See

License.

What it does

A typed memory graph. Memories are typed nodes (fact, decision, person, event, …) joined by typed edges (involves, references, supersedes, …). The types, their attribute schemas, and the rules for which edges may connect which types are declared per space in a pack and enforced in Postgres.
Writes that deduplicate themselves. Every write is embedded and banded against existing memory. A near-verbatim restatement auto-merges; a genuinely new but related fact is kept as its own searchable node and joined by an edge (nothing is silently absorbed); a borderline case parks as a pending duplicate-check verdict for the caller to resolve. Every write returns a *resonance report* of what it touched.
Hybrid retrieval. search fuses a vector leg (cosine over embeddings) and a lexical leg (Postgres full-text) with Reciprocal Rank Fusion, and traverse walks the edges. Attribute values are folded into the searchable surface, so a fact stored only in a typed attribute is still findable.
Isolation the database enforces. Multiple spaces, and multiple principals within a space, are separated by Postgres Row-Level Security running under a non-superuser role, not by application checks that can be forgotten. The server connects as a NOBYPASSRLS role.
Scope routing built for LLMs. Every scope carries a description of what it governs; the read-only scope_guide tool returns that routing manifest so an agent can decide *where* a new memory belongs before it writes.
An operator CLI and an MCP tool surface for everything from bootstrapping a space to minting tokens, importing data, applying packs, and verifying restores.

How it works

flowchart LR

C[MCP client VS Code · desktop · agent] -->|HTTP + bearer token| S[Engraphy server FastMCP] S --> E[Embedding nomic-embed-text-v1.5] S --> DB[(Postgres 16 + pgvector nodes · edges · scopes RLS · schema enforcement)] P[Pack types · edges · briefing] -.declares.-> DB

A write is embedded, banded by similarity into merge / merge-link / pending / new, and committed under the caller's identity. A read (search, get, traverse, briefing) runs under RLS so a caller only ever sees the scopes they were granted. A pack declares the node types, edge types, attribute schemas, and session-start briefing for a space, so one engine serves many differently shaped memory applications. The architecture overview walks the full write and read paths.

Quickstart

Requirements: Docker (with Compose). The cloud profile brings up Postgres, runs migrations, provisions the app role, and starts the server in one command.

# 1. Configure secrets (never committed)

cp deploy/.env.example .env # then edit, or: printf 'POSTGRES_PASSWORD=%s\nENGRAPHY_APP_ROLE_PASSWORD=%s\n' \ "$(openssl rand -hex 16)" "$(openssl rand -hex 16)" > .env

2. Bring up Postgres + migrate + provision + serve

docker compose up -d # the embedding model ships baked into the image

3. Create a space, apply the starter pack, mint a client token

docker compose --profile admin run --rm admin \ engraphy-admin space create --id personal --display-name "My Memory" --principal me docker compose --profile admin run --rm admin \ engraphy-admin pack apply packs/starter/pack.yaml --space personal docker compose --profile admin run --rm admin \ engraphy-admin token create --space personal --principal me \ --client-name my-editor --role readwrite

The server is now on 127.0.0.1:8000 (put a TLS-terminating reverse proxy in front to expose it). Point any MCP client at it with the bearer token. The setup guide covers the local, no-Docker path as well.

Or let the scripts do it

up.sh and provision.sh (with up.ps1 / provision.ps1 as Windows equivalents) wrap exactly the sequence above, and add the waiting that a copy-paste quickstart cannot:

./up.sh          # writes .env with random passwords, starts the stack,

then blocks until /healthz returns 200

./provision.sh # creates the space, applies the starter pack, mints a token,

and prints the client settings to paste in

up.sh polls /healthz rather than compose's health status, because on first boot compose reports starting for as long as the model cache takes to seed, which looks identical to a crash-loop from the outside. A 200 is the real signal.

Both scripts are safe to re-run: an existing .env is never overwritten, and an existing space or an already-applied pack is skipped rather than treated as an error, so a re-run still mints a fresh token.

Everything is parameterised, with defaults that work unchanged:

	default	override
space id	`default`	`./provision.sh myspace` or `-Space myspace`
principal	`me`	`./provision.sh myspace alice` or `-Principal alice`
client name	`my-client`	third positional arg, or `-ClientName`
pack	`/app/packs/starter/pack.yaml`	`ENGRAPHY_PACK` or `-Pack`
host port	`8000`	`ENGRAPHY_HOST_PORT` in `.env`, or `-Port`
health timeout	1800s up, 600s provision	`ENGRAPHY_WAIT_SECS` or `-WaitSeconds`

The token is printed once and never written to disk by the scripts; the server stores only its SHA-256. If you lose it, re-run provision.sh for a new one.

Using it from a client

Engraphy is an MCP server, so a client connects and calls tools:

Tool	What it does
`write`	Dedup-banded write; returns the node or a duplicate-check verdict plus a resonance report.
`search`	Hybrid semantic + lexical retrieval across one scope or all.
`traverse`	Recursive graph walk from a starting node.
`get`	Full nodes plus edge summaries, by id.
`briefing`	Pack-declared session-start sections (due commitments, relevant notes, …).
`scope_guide`	The routing manifest: every writable scope and what it governs.
`scope_list` / `scope_create`	List readable scopes / create a private one.
`link` · `update` · `supersede` · `resolve_duplicate`	Edit the graph and settle pending verdicts.
`pending_list` · `stats` · `inbox_review`	Inspect pending writes, usage metrics, and the capture inbox.
`admin_*`	Space administration (members, tokens, grants, visibility).

See the tool reference for parameters, returns, and an example per tool. A first-party VS Code extension lives in vscode-extension/.

Documentation

[docs/](docs/): developer documentation, architecture, setup, packs, tool reference, deployment, and an end-to-end tutorial.
[design/](design/README.md): the design set, the data model, retrieval and dedup, auth and tenancy, operations, the pack/ontology system, and the benchmark harness. This is where the engineering reasoning lives.
[skills/](skills/): concise guidance an LLM agent can load to use Engraphy well (writing and dedup, retrieval, scopes and visibility, answer discipline).

Requirements

Postgres 16 with pgvector (the pgvector/pgvector:pg16 image ships both).
Python ≥ 3.12.
[dbmate](https://github.com/amacneil/dbmate) for migrations (bundled in the admin container; only needed on PATH for the no-Docker path).
The embedding model `nomic-ai/nomic-embed-text-v1.5` (384-dim, on ONNX Runtime, downloaded and cached on first boot).

Project status

v0.1.0. The schema and enforcement kernel, engine behaviors (dedup, hybrid retrieval, graph traversal, briefings), the MCP server with auth and admin, and the operator CLI are implemented and covered by a live-Postgres test suite plus a CI job that exercises the shipped deploy artifacts end to end. A benchmark harness (bench/, design/09) runs the engine against public long-term-memory datasets; it is a tool for measuring changes, not a source of marketing numbers. bench/RUN-LOCOMO.md is the walkthrough for running LoCoMo yourself: it needs an OpenAI-compatible base URL and key, and it pins the dataset, the arm, the models and the judge.

Contributing

Issues and pull requests are welcome. CONTRIBUTING.md covers getting a development database up, running the suite, what the three CI jobs check, and the house style. Security problems go through a private advisory rather than a public issue.

License

Engraphy is licensed under the Business Source License 1.1 (see LICENSE).

You may read, modify, redistribute, self-host, and use Engraphy in production as the memory layer for your own applications and agents.
You may not offer Engraphy itself to third parties as a hosted or managed service before the Change Date.
Change Date: 2026-08-22 + 4 years (2030-08-22), on which the license converts to the Apache License, Version 2.0.

Engraphy

概览

PopNx MCP 的三大支柱

它能帮你做什么

安装

安装之前

需要你填写的值

它能做什么

基础检查i

作者与仓库一致

仍在维护

有许可证

端点有响应

使用 OAuth 登录

工具描述中没有隐藏指令

与“搜索与 AI 记忆”中的其他服务器比较i

常见问题

替代选择

Context7

Codebase Memory

Exa

作者的 README

Engraphy

What it does

How it works

Quickstart

2. Bring up Postgres + migrate + provision + serve

3. Create a space, apply the starter pack, mint a client token

Or let the scripts do it

then blocks until /healthz returns 200

and prints the client settings to paste in

Using it from a client

Documentation

Requirements

Project status

Contributing

License