经 AI Skill Hub 精选评估,MCP工具:AI连续性层 获评「推荐使用」。这款MCP工具在功能完整性、社区活跃度和易用性方面表现出色,AI 评分 7.5 分,适合有一定技术背景的用户使用。
MCP工具是开源的AI连续性层,提供自主托管的AI工具,支持AI代理和记忆功能,突出其在AI应用中的价值。
MCP工具:AI连续性层 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
MCP工具是开源的AI连续性层,提供自主托管的AI工具,支持AI代理和记忆功能,突出其在AI应用中的价值。
MCP工具:AI连续性层 是一款遵循 MCP(Model Context Protocol)标准协议的 AI 工具扩展。通过 MCP 协议,它可以让 Claude、Cursor 等主流 AI 客户端直接访问和操作外部工具、数据源和服务,实现 AI 能力的无缝扩展。无论是文件操作、数据库查询还是 API 调用,都可以通过自然语言在 AI 对话中直接触发,极大提升生产效率。
# 方式一:通过 Claude Code CLI 一键安装
claude skill install https://github.com/nram-ai/nram
# 方式二:手动配置 claude_desktop_config.json
{
"mcpServers": {
"mcp---ai----": {
"command": "npx",
"args": ["-y", "nram"]
}
}
}
# 配置文件位置
# macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
# Windows: %APPDATA%/Claude/claude_desktop_config.json
# 安装后在 Claude 对话中直接使用 # 示例: 用户: 请帮我用 MCP工具:AI连续性层 执行以下任务... Claude: [自动调用 MCP工具:AI连续性层 MCP 工具处理请求] # 查看可用工具列表 # 在 Claude 中输入:"列出所有可用的 MCP 工具"
// claude_desktop_config.json 配置示例
{
"mcpServers": {
"mcp___ai____": {
"command": "npx",
"args": ["-y", "nram"],
"env": {
// "API_KEY": "your-api-key-here"
}
}
}
}
// 保存后重启 Claude Desktop 生效
<p align="center"> <img src="ui/public/brand.png" alt="Neural Ram" width="150" /> </p>
<p align="center"><sub><code>nram</code> for short</sub></p>
<p align="center"> <strong>The continuity layer for everything you do with AI.</strong><br /> One open source server you run yourself: every tool you use, every machine you work from, and the continuity is yours. </p>
<p align="center"> <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-7FCFFA?style=flat-square" alt="License: MIT" /></a> <img src="https://img.shields.io/badge/Go-1.26%2B-00ADD8?style=flat-square&logo=go&logoColor=white" alt="Go 1.26+" /> <img src="https://img.shields.io/badge/MCP-Streamable_HTTP-7FCFFA?style=flat-square" alt="MCP over Streamable HTTP" /> <img src="https://img.shields.io/badge/storage-SQLite_%7C_PostgreSQL-7FCFFA?style=flat-square" alt="SQLite or PostgreSQL" /> <a href="https://github.com/nram-ai/nram/stargazers"><img src="https://img.shields.io/github/stars/nram-ai/nram?style=flat-square&color=7FCFFA" alt="GitHub stars" /></a> <img src="https://img.shields.io/github/last-commit/nram-ai/nram?style=flat-square&color=7FCFFA" alt="Last commit" /> </p>
<p align="center"> <a href="#quick-start">Quick Start</a> · <a href="#reference">Docs</a> · <a href="https://nram.ai">nram.ai</a> </p>
Work in progress: under active development. Expect rough edges, and feedback is welcome.
Memory and recall. Hybrid retrieval fuses vector and lexical search (FTS5 on SQLite, tsvector on Postgres) with Reciprocal Rank Fusion, boosted by the knowledge graph and scored by six tunable terms (similarity, recency, importance, frequency, graph relevance, confidence). MMR reranking demotes near-duplicate results so recall stays diverse. Embedding runs off the write path, so stores stay fast. Semantic search backs onto pgvector, a pure-Go HNSW index, or Qdrant.
Enrichment and the knowledge graph. Background workers extract facts, entities, and relationships from your free-text memories and build a multi-hop graph that connects them over time. An optional ingestion judge decides add / update / delete / none against near-duplicates before extraction runs. Query augmentation paraphrases each memory into short retrieval queries so recall matches the way people actually ask.
Dreaming. An offline nine-phase consolidation cycle: entity dedup, embedding and augmentation backfill, paraphrase dedup, transitive-relationship inference, contradiction detection, consolidation, pruning (with optional confidence decay), and weight recalculation. An LLM novelty audit demotes low-value syntheses. See docs/operations.md.
Tiers. Procedural memory is a verbatim per-user tier for rules and protocols, stored byte-for-byte and never embedded, enriched, or rewritten. The persona (about_me) and global tiers are reserved, auto-provisioned, and always join the recall aperture so relevant self-knowledge and world-knowledge surface alongside project results.
Access and multi-tenancy. Authentication via JWT, per-user API keys, WebAuthn passkeys, and per-organization OIDC SSO. Full OAuth 2.0 (Authorization Code + PKCE, dynamic client registration, resource indicators, discovery metadata). Five RBAC roles across REST and MCP. Organizations, hierarchical namespaces, and projects for isolation, plus share tokens for granting scoped external access without an account.
Operability. The Web Console, a React app, manages providers, settings, the graph, dreaming, the enrichment queue, and analytics. Run on SQLite (zero-config) or PostgreSQL, with SQLite-to-Postgres migration tooling. Provider-agnostic across OpenAI, Anthropic, Google Gemini, Ollama, OpenRouter, and any OpenAI-compatible endpoint, with per-call token accounting. Real-time updates over SSE, HMAC-signed webhooks, Prometheus metrics at /metrics, and JSON / NDJSON import/export.
A full feature-by-feature reference lives across the docs.
| Tool | Required | Check |
|---|---|---|
| Go | 1.26.1+ | go version |
| Node.js | 18+ | node --version |
| npm | any (build uses npm ci, not pnpm or yarn) | npm --version |
| Ollama | optional, for local LLMs | ollama --version (skip if using a hosted provider) |
git clone <repo-url> nram && cd nram
make build
Output is a single ./nram binary with the Web Console embedded.
Navigate to http://localhost:8674, create the initial admin account, and save the API key shown on the completion screen. It is not shown again.
nram needs an LLM provider to do anything beyond storing raw text. Without one, recall falls back to keyword-only matching and the knowledge graph stays empty. No error is raised; the system runs degraded. Configure providers in Step 5, and pick a long-context embedding model (see docs/models.md).
Open Settings → Providers and configure three slots: Embedding (semantic search), Fact Extraction, and Entity Extraction (the knowledge graph and dreaming). Any of OpenAI, Anthropic (chat slots only; it has no embeddings API), Google Gemini, Ollama, OpenRouter, or an OpenAI-compatible endpoint works. Changes hot-reload; no restart needed.
See docs/models.md for which model to put in each slot and how to size local models.
The deep reference is split out to keep this page approachable:
num_ctx and keep-alive tuning.该项目是一个开源的MCP工具,提供了AI连续性层的功能,支持自主托管和AI代理记忆功能,值得关注。
AI Skill Hub 为第三方内容聚合平台,本页面信息基于公开数据整理,不对工具功能和质量作任何法律背书。
建议在沙箱或测试环境中充分验证后,再部署至生产环境,并做好必要的安全评估。
✅ MIT 协议 — 最宽松的开源协议之一,可自由商用、修改、分发,仅需保留版权声明。
AI Skill Hub 点评:MCP工具:AI连续性层 的核心功能完整,质量良好。对于Claude Desktop / Claude Code 用户来说,这是一个值得纳入个人工具库的选择。建议先在非生产环境试用,再逐步推广。
| 原始名称 | nram |
| 原始描述 | 开源MCP工具:The continuity layer for everything you do with AI. A self-hosted, open source s。⭐4 · Go |
| Topics | mcpagent-memoryai-agentsai-memorychatgptclaudego |
| GitHub | https://github.com/nram-ai/nram |
| License | MIT |
| 语言 | Go |
收录时间:2026-06-06 · 更新时间:2026-06-06 · License:MIT · AI Skill Hub 不对第三方内容的准确性作法律背书。
选择 Agent 类型,复制安装指令后粘贴到对应客户端