Google PageRank for AI agents. 25,000+ tools indexed.

ai-localbase MCP Server

veyliss/ai-localbase

Score: 73.3 Rank #3444 Search & RAG
[![AgentRank](https://agentrank-ai.com/api/v1/badge/veyliss--ai-localbase)](https://agentrank-ai.com/tool/veyliss--ai-localbase/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
Are you the maintainer of veyliss/ai-localbase? Claim this listing →

一个本地优先的AI知识库系统(RAG),用于把本地文档接入辅导搜索与大模型对话流程。目前支持md、txt、pdf(文本)、xlsx、cvs类型。支持mcp服务

Add AgentRank to Claude Code Discover and compare tools like veyliss/ai-localbase — your AI finds the right one automatically
Get API Access →
claude mcp add agentrank -- npx -y agentrank-mcp-server

Overview

veyliss/ai-localbase is a Go tool licensed under MIT. 一个本地优先的AI知识库系统(RAG),用于把本地文档接入辅导搜索与大模型对话流程。目前支持md、txt、pdf(文本)、xlsx、cvs类型。支持mcp服务 Topics: ai, go, ollama, qdrant, rag, react, knowledge-base, mcp.

Ranked #3444 out of 24846 indexed tools.

Ecosystem

Go MIT
aigoollamaqdrantragreactknowledge-basemcp

Score Breakdown

StarsFreshnessIssue HealthContributorsDependents
Stars 15% 379

379 stars → growing community

Freshness 25% 1mo ago

Last commit 1mo ago → moderate activity

Issue Health 25% 71%

5/7 issues closed → decent issue management

Contributors 10% 3

3 contributors → small team

Dependents 25% 0

No dependents → no downstream usage

npm Downloads N/A
PyPI Downloads N/A
Forks 57
Description Good
License MIT

Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →

How to Improve

Description low impact

Expand your description to 150+ characters for better discoverability

Freshness high impact

Last commit was 55 days ago — a recent commit would boost your freshness score

Dependents medium impact

No downstream dependents detected yet — adoption by other projects is the strongest trust signal

Badge all embed codes →

AgentRank score for veyliss/ai-localbase
[![AgentRank](https://agentrank-ai.com/api/v1/badge/veyliss--ai-localbase)](https://agentrank-ai.com/tool/veyliss--ai-localbase/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge)
<a href="https://agentrank-ai.com/tool/veyliss--ai-localbase/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge"><img src="https://agentrank-ai.com/api/v1/badge/veyliss--ai-localbase" alt="AgentRank"></a>

Embed Widget docs →

Embed a rich score widget on your site or blog.

<script src="https://agentrank-ai.com/embed.js" data-tool="veyliss/ai-localbase"></script>

Matched Queries

topic:mcp

From the README

# AI LocalBase

一个本地优先的 AI 知识库系统(RAG),用于将本地文档接入向量检索与大模型对话流程。项目提供 Web UI,支持知识库管理、文档上传、检索增强问答、聊天记录持久化,以及基于 Ollama 或 OpenAI 兼容接口的模型接入。

## 项目简介

AI LocalBase 适合个人或小团队在本地环境、自托管环境中快速搭建可用的知识库问答系统。

- 后端:Go + Gin
- 前端:React + Vite + TypeScript
- 向量数据库:Qdrant
- 模型接入:Ollama / OpenAI Compatible API
- 部署方式:Docker Compose(推荐),本地单进程调试作为补充
- 扩展能力:内置 MCP Server,可供外部 Agent / 工具系统接入

---

## 核心能力

- 知识库管理:创建、删除知识库,查看文档列表
- 文档上传与索引:支持 TXT、Markdown、PDF、xlsx、csv 文件上传与解析
- 检索增强问答:基于 Qdrant 做向量检索并把命中内容注入对话上下文
- 聊天记录持久化:会话消息保存到本地 SQLite 数据库
- 配置持久化:模型配置与知识库状态保存到本地 JSON 文件
- Docker Compose 部署:支持一键拉起前端、后端、Qdrant

### 检索增强能力

- 文本自动切分与批量嵌入
- 候选结果动态召回
- 关键词覆盖增强重排
- MMR 去冗余选择
- 低置信度场景二次扩召回
- 嵌入缓存与可选语义缓存
- 可选 Hybrid Search、Semantic Reranker、Query Rewrite、Context Compression
- 可从现有知识库文档生成 RAG 评估数据集,用于小样本效果验证

---

## 适用场景

- 本地个人知识库
- 团队内部文档问答
- 自托管 RAG 原型验证
- Ollama / OpenAI 兼容模型接入测试
- 检索策略实验与评估
- 作为 MCP 能力后端供 Agent 调用
- 批量文档支持异步索引 Job,可查询进度并取消任务

---

## 快速开始

最短体验路径:

1. 复制环境变量模板:

```bash
cp .env.example .env
`
Read full README on GitHub →

Get the weekly AgentRank digest

Top movers, new tools, ecosystem insights — straight to your inbox.