Memory

io.github.VelixarAi由 GitHub 账号 VelixarAi 发布v0.2.4更新于 Oct 24, 2026

Persistent memory for AI assistants. Store, search, and recall across sessions.

发布方自己的服务：Memory.fit

已验证STDIO仅桌面知识与记忆AI 与机器学习

概览

AI 生成的概览

Velixar Memory 为 AI 助手提供跨会话的持久记忆，并附带知识图谱、身份画像与矛盾检测能力。

可以做什么
  • 存储、语义搜索、分页浏览、修改和删除记忆，支持批量存储与批量搜索
  • 一键获取工作区简报，查看记忆的完整来源链，追溯话题演变，发现矛盾与重复模式
  • 构建并遍历实体与关系的知识图谱，维护持久的用户身份与偏好画像
  • 保存与恢复会话摘要，将会话提炼为长期记忆，合并与批量重打标签
  • 以 JSON 或 Markdown 导出记忆，并从 JSON、Markdown、Notion 或 Obsidian 导入
  • 检查后端连通性、调试状态、功能清单与内容扫描模式
适用场景
适合希望助手在多次对话之间记住偏好、决策与项目背景的场景，也适合需要跨会话、跨工作区维护结构化知识图谱和用户画像的用户。
运行要求
以 npm 包 velixar-mcp-server 通过 stdio 在本地运行，需要 Node.js。需要 Velixar API 密钥，通过环境变量 VELIXAR_API_KEY 提供，并需能访问 Velixar 后端网络。可选变量用于设置工作区范围、API 地址、用户身份、日志与健康检查端口。
安装前请注意
记忆保存在 Velixar 后端，对话内容、会话摘要和画像信息会离开本机。API 密钥属于机密，应避免写入共享配置。相关工具可修改、删除、合并、批量重打标签和批量导入记忆，身份工具还能更改已存储的用户画像。工作区范围决定可见的记忆，存放敏感内容前请先确认。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Memory，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Velixar MCP Server

[npm] [License]

The first cognitive memory server for AI assistants. Not a vector database wrapper — a full reasoning layer that gives your AI persistent memory, a knowledge graph, identity awareness, contradiction detection, and belief tracking across every session.

Works with any Model Context Protocol client: Claude Desktop, Kiro, Cursor, Windsurf, Continue.dev, or custom hosts.

Why This Exists

Every AI assistant starts from zero every conversation. Velixar fixes that — but not by just storing and retrieving text. The MCP server gives your assistant the ability to:

  • Orient itself in a workspace with a single call — no manual context assembly
  • Track how beliefs evolve over time and surface when they contradict
  • Build and traverse a knowledge graph of entities and relationships it discovers
  • Maintain a persistent identity model of who you are, what you prefer, and how you work
  • Distill sessions into durable memories automatically, with deduplication
  • Import and export your entire memory corpus for backup or migration

40 tools. 5 live resources. 19 workflow prompts. One npm install.

Quick Start

bash
npm install -g velixar-mcp-server

Get an API key at velixarai.com/settings/api-keys, then add to your MCP client:

json
{  "mcpServers": {    "velixar": {      "command": "velixar-mcp-server",      "env": {        "VELIXAR_API_KEY": "vlx_your_key_here"      }    }  }}

Restart your assistant. Done.

Tool Surface

Memory

ToolWhat it does
velixar_storeStore a memory with tags, tier, and type
velixar_searchSemantic search across all memories
velixar_listBrowse with pagination and filtering
velixar_updateEdit content or tags on an existing memory
velixar_deleteRemove a memory

Cognitive

ToolWhat it does
velixar_contextSynthesized workspace briefing — orientation in one call
velixar_identityGet, store, or update the user's profile, preferences, and expertise
velixar_contradictionsSurface conflicting facts or beliefs with resolution guidance
velixar_timelineHow a topic or belief evolved over time
velixar_patternsRecurring problem/solution motifs across your history
velixar_inspectDeep inspection of a specific memory with full provenance chain
velixar_graph_traverseWalk entity relationships — "what connects to X?"
velixar_distillExtract durable memories from session content with deduplication

Lifecycle

ToolWhat it does
velixar_session_saveSave a session summary for later recall
velixar_session_recallRestore context from a previous session
velixar_batch_storeStore up to 20 memories in one call
velixar_batch_searchRun up to 10 search queries simultaneously
velixar_consolidateMerge related memories into a single durable memory
velixar_retagBulk update tags across memories
velixar_exportExport memories as JSON or Markdown, optionally with graph data
velixar_importBulk import from JSON, Markdown, Notion, or Obsidian exports

System

ToolWhat it does
velixar_healthBackend connectivity, latency, workspace status
velixar_debugCache state, circuit breaker, API timings
velixar_capabilitiesFeature list, tool inventory, resource URIs
velixar_securityGet or set content scanning mode

Live Resources

Resources are injected into your assistant's context automatically — no tool call needed.

ResourceWhat it provides
velixar://system/constitutionBehavioral rules and cognitive modes for the assistant
velixar://identity/currentYour persistent user profile
velixar://memories/recentMost recent memories (compact)
velixar://memories/relevantContextually relevant memories based on current activity
velixar://domains/{domain}/shadow_graphKnowledge graph view for a specific domain

Workflow Prompts

16 built-in prompts that guide multi-step reasoning workflows:

  • Orientation — recall prior reasoning, build project context, profile an entity, orient-then-narrow
  • Conflict — resolve contradictions, identify knowledge gaps
  • Continuity — trace belief evolution, resume sessions, reconstruct decision paths
  • Lifecycle — distill sessions, consolidate topic memory, retag recent memories
  • Identity — summarize user identity, detect preference shifts, align response style
  • Enterprise — evaluate enterprise fit for a domain

Workspace Isolation

Memories are scoped to workspaces. Your personal project never bleeds into work.

PrioritySourceHow
1VELIXAR_WORKSPACE_ID env varExplicit
2.velixar.json in project root{ "workspace_id": "my-project" }
3Git root directory nameAutomatic

Host Compatibility

HostToolsResourcesPrompts
Kiro CLI✅✅✅
Claude Desktop✅✅✅
Cursor✅⚠️—
Windsurf✅⚠️—
Continue.dev✅✅✅

When a host doesn't support resources or prompts, the server degrades gracefully — all tools still work independently.

Environment Variables

VariableRequiredDescription
VELIXAR_API_KEYYesYour API key (starts with vlx_)
VELIXAR_WORKSPACE_IDNoExplicit workspace scope
VELIXAR_API_URLNoCustom API endpoint
VELIXAR_USER_IDNoExplicit end-user identity. Leave unset (recommended): the API derives scope from your key — you see your own memories, same as the dashboard. Set it only when one key serves multiple named end users
VELIXAR_DEBUGNotrue for verbose logging
VELIXAR_LOG_FORMATNojson for structured Datadog/CloudWatch logging
VELIXAR_HEALTH_PORTNoPort for HTTP health check endpoint

Reliability

  • Automatic retry with exponential backoff (3 attempts)
  • Circuit breaker — opens after sustained failures, auto-recovers
  • Cache fallback — serves stale data during outages rather than failing
  • Structured logging compatible with Datadog and CloudWatch

SDKs

Use Velixar directly from code:

  • JavaScript/TypeScript: npm install velixar — docs
  • Python: pip install velixar — docs

CI/CD Integration

License

MIT

来源：README.md，提交 3723fb6

工具

0
SourceWeft 尚未在沙箱中启动过该软件包，因此其工具未知。

版本历史

1
  1. v0.2.4最新Sep 16, 2026

评分

已满足适用检查项的 50%

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25 分

    请保持端点能够响应 MCP 握手；SourceWeft 每 30 天探测一次。

  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 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

其他 Memory 集成

Memory.fit

fit.memory官方发布者

托管式 Memory.fit 服务器，让 AI 读取你的训练、睡眠、恢复与饮食数据，并写回每周计划、每日目标和饮食计划。

Streamable HTTP可网页运行鉴权
位置与生活需要凭据Oct 29, 2026

pg.ddx.io: the PostgreSQL community's memory

io.ddx.pg官方发布者

pg.ddx.io: the PostgreSQL community's memory 的托管 MCP 服务，由 pg.ddx.io 发布；无需登录；Streamable HTTP；29 个工具。

Streamable HTTP可网页运行
数据库29 个工具Oct 24, 2026

var.gg Naming Memory

gg.var官方发布者

远程 MCP 服务器，可根据领域概念推荐并检索韩、日、中、越、英多语言的代码标识符名称，并提供 ERD 结构查询。

Streamable HTTP可网页运行
数据库7 个工具Oct 27, 2026

Counterparts

ai.counterparts

面向 Claude Code 与 Claude Desktop 的本地优先长期记忆：助手自行写下关于你和项目的笔记，并在之后的会话中回忆起来。

STDIO仅桌面
AI 与机器学习尚未验证Nov 7, 2026

LAHZE - Persian AI Memory Platform

由 GitHub 账号 pedramgholizadeh 发布

以波斯语为先的地理记忆平台：发现地点，起草并发布仅限波斯语的记忆。AI 翻译

Streamable HTTP可网页运行
位置与生活13 个工具Nov 3, 2026