Zekra

io.github.fadymondy由 GitHub 账号 fadymondy 发布v0.1.0更新于 Nov 1, 2026

Long-term memory and a knowledge graph for AI agents: recall, notes, secrets and data sources.

已验证Streamable HTTP可网页运行数据库知识与记忆AI 与机器学习

概览

AI 生成的概览

Zekra 是一个托管的长期记忆与知识图谱服务，让 AI 助手跨会话保存、检索和整理所学内容。

可以做什么
  • 保存、检索、读取、编辑与软遗忘记忆，采用向量加 BM25 混合检索、重排并附带引用
  • 查询知识图谱：遍历实体与带类型的关系，查找邻居与路径，查看本体结构
  • 管理大脑与访问权限：列出大脑、授权与令牌，在智能体之间共享记忆
  • 管理密钥保险库，查看知识缺口与活动日志
  • 接入外部数据源（text、markdown、crawler、github、sql、webhook），分块后写入记忆
  • 通过工具调用型智能体与某个大脑对话，回答带引用和可审计轨迹
适用场景
适合希望助手在会话之间或跨多个智能体延续知识、按项目或团队隔离记忆命名空间，或基于整理好的知识图谱给出带引用回答的场景。
运行要求
远程 MCP 端点 mcp.zekra.dev，使用 Streamable HTTP 与 OAuth 登录。需要 app.zekra.dev 上的托管账号、一个大脑和访问令牌；或自建 Docker Compose 部署（含 VectorChord 的 Postgres、Go API、控制台、TEI 嵌入与重排模型，约 6 GB 磁盘）并自行配置密钥。
安装前请注意
服务会保存智能体与用户提供的内容，其中包含密钥保险库，应视为敏感数据并按智能体分别限定令牌。写入会更新或作废既有事实而非硬删除，历史仍可查询。crawler、github、sql、webhook 等数据源会把外部内容拉入大脑。自建部署需设置 POSTGRES_PASSWORD、AUTH_SECRET、ZEKRA_SECRETS_KEY 和 MFA_CHALLENGE_SECRET。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Zekra，将其添加到工作区。
  2. 连接 所需的 凭据。它们会被私密存储，绝不会在公开页面上展示。
  3. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/io.github.fadymondy%2Fzekra/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。 客户端会在首次连接时完成 OAuth 登录。

{
  "mcpServers": {
    "zekra": {
      "type": "http",
      "url": "https://mcp.zekra.dev/"
    }
  }
}

README

[Zekra]

Zekra — ذكرى

Shared long-term memory for AI agents. What one session learns, the next one already knows.

Zekra is a memory service that any agent (Claude Code, Codex, Gemini, Cursor, your own fleet) reaches over MCP. It stores what agents and people learn, deduplicates and updates it on write, and returns the right memory on recall, with citations.

[Built with ToGO] [ToGO on GitHub] [CI] [License: AGPL-3.0] [Discord] [GitHub stars]

Website · Docs · Discord · Discussions · Issues

[Zekra console: memories land in a graph, then a plain-words recall returns the right memory with its source note]

Features

  • Retain / recall — hybrid retrieval: dense vectors + multilingual BM25 fused with RRF, a salience nudge, reranking, and 1-hop entity expansion. A write-decision step (ADD / UPDATE / INVALIDATE / NOOP) updates contradicted facts instead of duplicating them. Nothing is hard-deleted: forget soft-invalidates and history stays queryable.
  • Many brains — one namespace per project or team, with per-agent grants and access tokens (cbt_…) enforced server-side.
  • Knowledge graph — entities and typed relations extracted from memories, with traverse / neighbors / path / ontology queries and a graph "spine".
  • Data sources — connectors (text, markdown, crawler, github, sql, webhook) pull external content, chunk it and retain it through the same write pipeline. See Data sources.
  • Chat with a brain — a tool-calling agent that uses the brain's own recall / search / graph / retain as tools and answers with citations and an auditable trace.
  • Knowledge gaps, secrets vault, activity log — plus a web console to manage it all.
  • Tiers — Redis L1 working-memory cache, hot Postgres tier, object-store cold tier.

Quick start

Hosted

Sign up at app.zekra.dev, create a brain and mint a token, then connect your agent:

bash
curl -fsSL https://app.zekra.dev/install.sh | sh     # installs the `zekra` CLIzekra auth login --token <cbt_…>zekra mcp:install claude-code                        # or claude-desktop | codex | gemini | cursor

The CLI lives in fadymondy/zekra-cli.

Self-host with Docker Compose

Requirements: Docker with Compose v2, and about 6 GB of disk for the embedding and reranker models.

bash
git clone https://github.com/fadymondy/zekra.git && cd zekracp .env.selfhost.example .env.selfhost# fill in POSTGRES_PASSWORD, AUTH_SECRET, ZEKRA_SECRETS_KEY and MFA_CHALLENGE_SECRET# (generate each with: openssl rand -hex 32), and your email in ADMIN_EMAILSdocker compose -f docker-compose.selfhost.yml --env-file .env.selfhost up -d --build

Open http://localhost:3020 and register. The stack runs Postgres 17 with VectorChord, a one-shot schema job, the Go API, the Next.js console and two CPU TEI servers (embeddings and reranking), which download their models on first start. Then mint a token under Admin → Tokens and run zekra auth login --url http://localhost:3020 --token cbt_….

For a public deployment, put a TLS reverse proxy in front and set APP_URL. Every setting is covered in docs/self-hosting.md and DEPLOY.md.

MCP tools

MCP tools include memory_retain, memory_recall, memory_get, memory_forget, memory_share, memory_edit, graph_*, memory_gaps, brain_* (list, grants, tokens, chat), secret_* and datasource_*. Full reference: MCP server · contracts: contracts/tools.md.

Architecture

  Claude Code · Codex · Cursor · your agents        web console · mobile · desktop · extension          │ MCP (Streamable HTTP or stdio)                    │ REST / GraphQL / SSE          └───────────────────────┬───────────────────────────┘                 ┌────────────────▼─────────────────────────────────────┐                 │ Go API (ToGO: plugins on a microkernel)               │                 │  brain plugin: retain → write-decision (ADD/UPDATE/    │                 │  INVALIDATE/NOOP) · recall: vectors + BM25 → RRF →    │                 │  rerank → 1-hop graph · graph · data sources · chat   │                 └──────┬──────────────────┬─────────────────┬───────────┘                        │                  │                 │           ┌────────────▼──────┐   ┌───────▼──────┐   ┌──────▼─────────┐           │ Postgres + vchord │   │ TEI embed /  │   │ Redis L1 ·     │           │ BM25 · partman    │   │ rerank       │   │ Cognee (opt.)  │           └───────────────────┘   └──────────────┘   └────────────────┘

Zekra is a ToGO app built from plugins:

PartWhereRole
brainplugins/brain (module github.com/togo-framework/brain)the memory organ: schema, retain/recall, graph, connectors, chat, REST
brain-teiplugins/brain-teiembeddings + rerank via TEI (Qwen3-Embedding-0.6B, bge-reranker-v2-m3)
brain-cogneeplugins/brain-cogneeentity / graph extraction engine (Cognee)
cache-redisplugins/cache-redisL1 cache
harnesscmd/api, cmd/migrate, internal/, web/the app: API server, migrations, React console
zekra-mcpcmd/zekra-mcpstdio MCP server — thin adapter over the REST API
zekractlcmd/zekractlops CLI: inspect DB, apply schema/BM25, BM25 smoke test, graph mirror

Design: SPEC.md · decisions: contracts/internal/decisions.md · deploy: DEPLOY.md.

Built on ToGO

Zekra is built on ToGO (GitHub), the open-source, API-first framework for Go + sqlc + Atlas + GraphQL/OpenAPI + Next.js with a Laravel-style CLI. The kernel is small and everything else is a plugin; these are the pieces Zekra uses:

ToGO pieceWhat it does in Zekra
KernelConfig, the hook/event bus, the plugin registry and server bootstrap
CLItogo generate (sqlc → gqlgen → Atlas → OpenAPI), togo serve, togo install
authSign-in, JWT sessions, roles and API tokens; MFA, passkeys and OAuth come from the auth plugin family
db-postgresThe Postgres driver under the brain schema
queue · cache · storage · mailIngestion jobs, caching, media and transactional email
Plugin modelThe memory organ itself ships as ToGO plugins: brain, brain-tei, brain-cognee, cache-redis

Want the same foundation for your own app? Run go install github.com/togo-framework/cli@latest && togo new myapp, then read the ToGO docs and browse the plugin marketplace.

Read the case study: MCP Server in Go: How Zekra Is Built on ToGO Plugins.

Documentation

Full docs at https://zekra.dev/en/docs (source: docs/):

Contributing

Bug reports, docs and code contributions are all welcome. Start with CONTRIBUTING.md, which covers setup, conventions and the DCO sign-off. Then look for a good first issue. AI coding agents should start with AGENTS.md.

Translations

[Translation status]

Zekra is translated on Hosted Weblate, help us translate it into your language: https://hosted.weblate.org/projects/zekra/. See CONTRIBUTING.md for how it works.

Community

Please follow the Code of Conduct.

Sponsor

Zekra is built on ToGO, the open-source Go + React framework that powers this whole family of apps. The best way to support Zekra is to sponsor ToGO: every sponsorship goes into the framework and the apps built on it.

Sponsor ToGO →

[Sponsor ToGO] [GitHub Sponsors] [Buy Me a Coffee]

License

Copyright (C) 2026 Fady Mondy. Zekra is free software, licensed under the GNU Affero General Public License v3.0 (AGPL-3.0-only). If you run a modified version as a network service, you must offer its source to your users. Third-party components keep their own licenses.

Commercial licensing available: for a license without the AGPL obligations, contact [email protected].

More open source from the same author

  • TomatoPHP: 60+ open-source FilamentPHP plugins for Laravel
  • Laravilt: Laravel admin panels rendered with Inertia on Vue 3 or React 19
  • ToGO: the Laravel-style workflow for Go + React apps, with a plugin marketplace

Built by Fady Mondy.

来源：README.md，提交 58340a0

工具

0
该服务器需要登录，因此 SourceWeft 无法在没有账号的情况下读取其工具，也未收录。已连接账号所能看到的内容可能因账号及其权限而异。

版本历史

1
  1. v0.1.0最新Oct 11, 2026

评分

已满足适用检查项的 85%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具15 分

    请让服务器在无凭据时响应 tools/list，或发布可在沙箱中无凭据启动的软件包。

  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分