Team Memory Hub (TMH)

AI 上下文记忆管理与分发系统

AI Context Memory Management & Distribution System

简介 | Introduction

Team Memory Hub 是一个面向 AI 辅助开发团队的集体记忆管理系统。它帮助团队积累、组织、检索和分发项目经验、架构决策、编码规范等知识，让 AI 助手能够基于团队积累的上下文提供更精准的协助。

Team Memory Hub is a collective memory management system for AI-assisted development teams. It helps teams accumulate, organize, retrieve, and distribute project experiences, architectural decisions, coding standards, and other knowledge, enabling AI assistants to provide more accurate assistance based on accumulated team context.

核心特性 | Key Features

特性 Feature	描述 Description
双引擎存储 Dual-Engine Storage	SQLite 索引 + 文件系统原文，兼顾查询性能与内容完整性 / SQLite index + filesystem originals, balancing query performance and content integrity
混合搜索 Hybrid Search	BM25 关键词 + 向量语义搜索，Score Fusion 融合排序 / BM25 keyword + vector semantic search with Score Fusion ranking
三层 Context Three-Layer Context	L0 核心规范 → L1 项目上下文 → L2 按需搜索 / L0 core specs → L1 project context → L2 on-demand search
三层上传 Three-Tier Upload	Hook 零 token → Script ~100 token → MCP ~200 token
MCP Server	5 个工具（全 CRUD），tool_set 配置 / 5 tools (full CRUD), tool_set config (read_only/read_write/full_crud)
记忆整合 Memory Consolidation	语义聚类 → LLM 合并建议 → 人工确认 / Semantic clustering → LLM merge suggestions → manual review
自动维护 Auto Curation	11 项自动维护任务（去重、过时检测、归档等）/ 11 auto maintenance tasks (dedup, staleness, archival, etc.)
质量生命周期 Quality Lifecycle	community → verified → pinned / stale → archived
RBAC 权限 Role-Based Access	admin > maintainer > member > viewer
双重认证 Dual Auth	JWT + API Key（5 种 scope）/ JWT + API Key (5 scopes)
SSE 实时事件 Real-time Events	8 种事件类型，按团队/类型过滤 / 8 event types, filtered by team/type
Web Dashboard	Jinja2 + HTMX 动态交互，管理后台 + 搜索调试 / Jinja2 + HTMX interactive admin panel + search debugger
CLI 工具 CLI Tool	`tmh` 全局命令，覆盖所有核心操作 / `tmh` global command covering all core operations

技术栈 | Tech Stack

组件 Component	技术 Technology
后端 Backend	Python 3.11+, FastAPI, Uvicorn
数据库 Database	SQLite (WAL) + aiosqlite + FTS5 + sqlite-vec
数据模型 Models	Pydantic v2
认证 Auth	JWT (python-jose) + API Keys (bcrypt)
前端 Dashboard	Jinja2 + HTMX + Pico CSS + Chart.js
嵌入 Embedding	OpenAI / Gemini / ONNX 本地 / OpenAI-compatible (Ollama/vLLM)
LLM	Claude (anthropic) / Gemini / Rules Engine (无 LLM 降级 / no-LLM fallback)

安装 | Installation

方式一：Docker 运行（推荐）| Option 1: Docker Run (Recommended)

最快的体验方式，无需安装 Python 环境。

The fastest way to get started, no Python installation required.

# 基础启动 | Basic start
docker run -d \
  --name team-memory-hub \
  -p 8000:8000 \
  -v tmh-data:/app/data \
  xiaoclab/team-memory-hub:latest

启动后访问 / After starting, visit:

API: http://localhost:8000/api/v1/health
Dashboard: http://localhost:8000/dashboard/
API 文档 Docs: http://localhost:8000/docs

自定义配置 | Custom Configuration

通过环境变量覆盖默认配置：

Override defaults with environment variables:

docker run -d \
  --name team-memory-hub \
  -p 8000:8000 \
  -v tmh-data:/app/data \
  -e TMH_JWT_SECRET=your-secure-secret \
  -e TMH_LOG_LEVEL=DEBUG \
  -e TMH_EMBEDDING_PROVIDER=openai_compatible \
  -e TMH_EMBEDDING_BASE_URL=http://host.docker.internal:11434 \
  -e TMH_EMBEDDING_MODEL=nomic-embed-text \
  xiaoclab/team-memory-hub:latest

提示 / Tip: 连接宿主机上的 Ollama 等服务时，使用 host.docker.internal 代替 localhost。

When connecting to services on the host (e.g., Ollama), use host.docker.internal instead of localhost.

常用环境变量 | Environment Variables

变量 Variable	说明 Description	默认值 Default
`TMH_SERVER_PORT`	监听端口 / Listen port	`8000`
`TMH_JWT_SECRET`	JWT 签名密钥 / JWT signing secret	`change-me-in-production`
`TMH_DATABASE_PATH`	数据库路径 / Database path	`/app/data/team_memory.db`
`TMH_DATA_DIR`	数据目录 / Data directory	`/app/data`
`TMH_EMBEDDING_PROVIDER`	嵌入服务商 / Embedding provider	`openai_compatible`
`TMH_EMBEDDING_BASE_URL`	嵌入服务地址 / Embedding service URL	`http://localhost:11434`
`TMH_EMBEDDING_MODEL`	嵌入模型 / Embedding model	`nomic-embed-text`
`TMH_EMBEDDING_API_KEY`	嵌入 API 密钥 / Embedding API key	-
`TMH_MCP_TOOL_SET`	MCP 工具集 / MCP tool set	`read_only`
`TMH_LOG_LEVEL`	日志级别 / Log level	`INFO`

数据持久化 | Data Persistence

-v tmh-data:/app/data 将数据库和记忆文件持久化到 Docker named volume，容器重建后数据不丢失。

-v tmh-data:/app/data persists the database and memory files to a Docker named volume, surviving container recreation.

# 查看数据卷 | Inspect volume
docker volume inspect tmh-data

# 停止并删除容器（数据保留）| Stop and remove container (data preserved)
docker stop team-memory-hub && docker rm team-memory-hub

# 彻底删除数据（谨慎）| Delete data permanently (caution)
docker volume rm tmh-data

配合 Ollama 使用 | With Ollama

如果需要本地 Embedding 服务，先启动 Ollama 再启动 TMH：

For local embedding, start Ollama first, then TMH:

# 1. 启动 Ollama 并下载模型 | Start Ollama and pull model
docker run -d --name ollama -p 11434:11434 -v ollama-data:/root/.ollama ollama/ollama
docker exec ollama ollama pull nomic-embed-text

# 2. 启动 TMH，连接 Ollama | Start TMH, connect to Ollama
docker run -d \
  --name team-memory-hub \
  -p 8000:8000 \
  -v tmh-data:/app/data \
  -e TMH_EMBEDDING_BASE_URL=http://host.docker.internal:11434 \
  xiaoclab/team-memory-hub:latest

方式二：Docker Compose | Option 2: Docker Compose

适合需要 TMH + Ollama 一键编排的场景。

Best for orchestrating TMH + Ollama together.

git clone https://github.com/xiaoc/team-memory-hub.git
cd team-memory-hub

# 默认模式：仅 TMH | Default: TMH only
docker compose up -d

# 开发模式：TMH（热重载）+ Ollama | Dev: TMH (hot-reload) + Ollama
docker compose --profile dev up -d

# 生产模式：TMH + Ollama（资源限制）| Prod: TMH + Ollama (resource limits)
docker compose --profile prod up -d

模式 Mode	命令 Command	说明 Description
默认 Default	`docker compose up -d`	仅 TMH，适合已有外部 Embedding 服务 / TMH only, for existing embedding service
开发 Dev	`docker compose --profile dev up -d`	源码热重载 + Ollama，DEBUG 日志 / Hot-reload + Ollama, DEBUG logs
生产 Prod	`docker compose --profile prod up -d`	资源限制（1G 内存 / 2 CPU）+ 日志轮转 / Resource limits + log rotation

方式三：pip 安装 | Option 3: pip Install

适合需要 tmh CLI 工具或将 TMH 作为 Python 库集成的场景。

Best for using the tmh CLI or integrating TMH as a Python library.

# 从 PyPI 安装 | Install from PyPI
pip install team-memory-hub

# 含 embedding 支持 | With embedding support
pip install team-memory-hub[embedding]

# 含 LLM 支持 | With LLM support
pip install team-memory-hub[llm]

# 全功能安装 | Full install
pip install team-memory-hub[all]

安装后 tmh 命令全局可用：

After installation, the tmh command is globally available:

tmh --help

方式四：开发环境 | Option 4: Development

git clone https://github.com/xiaoc/team-memory-hub.git
cd team-memory-hub
pip install -e ".[dev]"

配置 | Configuration

TMH 使用 tmh.toml 配置文件，环境变量可覆盖任意配置项。

TMH uses tmh.toml for configuration. Environment variables override any config value.

最小配置 | Minimal Configuration

[server]
host = "0.0.0.0"
port = 8000
data_dir = "./data"

[auth]
jwt_secret = "your-secret-key"  # 必须修改 | Must change

[database]
path = "./data/team_memory.db"

完整配置 | Full Configuration

[server]
host = "0.0.0.0"
port = 8000
debug = false
data_dir = "./data"
cors_origins = ["http://localhost:3000"]

[auth]
jwt_secret = "CHANGE-ME-IN-PRODUCTION"
jwt_algorithm = "HS256"
access_token_expire_minutes = 15
refresh_token_expire_days = 30

[database]
path = "./data/team_memory.db"
wal_mode = true
busy_timeout_ms = 10000

[storage]
memories_dir = "./data/memories"
specs_dir = "./data/specs"
chats_dir = "./data/chats"

[write_queue]
batch_timeout_ms = 100
batch_max_size = 50

[search]
engine = "hybrid"           # hybrid | keyword_only | vector_only
semantic_weight = 0.7
keyword_weight = 0.3
candidate_multiplier = 3
score_normalization = "min_max"

[embedding]
provider = "openai_compatible"  # openai_compatible | openai | gemini | onnx
dimensions = 384

[embedding.openai_compatible]
base_url = "http://localhost:11434"
model = "nomic-embed-text"
api_key = ""

[consolidation]
enabled = true
scan_schedule = "0 4 * * *"
scan_days = 30
cluster_threshold = 0.85
max_suggestions_per_scan = 20

[logging]
level = "INFO"
format = "json"

启动服务 | Starting the Server

# 方式一：使用入口脚本 | Option 1: Entry script
python main.py                     # 默认 0.0.0.0:8000 | Default
python main.py --port 9000         # 自定义端口 | Custom port
python main.py --reload            # 开发模式热重载 | Dev hot-reload
python main.py --config my.toml    # 指定配置文件 | Custom config

# 方式二：使用 uvicorn | Option 2: uvicorn directly
uvicorn team_memory_hub.server.app:app --host 0.0.0.0 --port 8000 --reload

# 方式三：模块调用 | Option 3: Module invocation
python -m team_memory_hub --port 8000

使用教程 | Usage Tutorial

1. 用户注册与认证 | Registration & Authentication

注册新用户 | Register a New User

curl -X POST http://localhost:8000/api/v1/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "Alice",
    "email": "alice@example.com",
    "password": "secure-password",
    "team_id": "team_default"
  }'

获取 JWT Token | Get JWT Token

curl -X POST http://localhost:8000/api/v1/auth/token \
  -H "Content-Type: application/json" \
  -d '{"email": "alice@example.com", "password": "secure-password"}'

# 响应 Response:
# {
#   "access_token": "eyJ...",
#   "refresh_token": "eyJ...",
#   "token_type": "bearer",
#   "expires_in": 900
# }

创建 API Key | Create an API Key

curl -X POST http://localhost:8000/api/v1/keys \
  -H "Authorization: Bearer <access_token>" \
  -H "Content-Type: application/json" \
  -d '{"name": "my-cli-key", "scope": "full_access"}'

# scope 可选值 Options: full_access | mcp_only | read_only | sync_only | ingest_only

后续请求使用 API Key 更方便：

For subsequent requests, API Key is more convenient:

export TMH_API_KEY="tmk_xxxxxxxx"

2. CLI 工具使用 | CLI Usage

tmh 命令在 pip install 后全局可用。

The tmh command is globally available after pip install.

项目初始化 | Project Initialization

# 在项目根目录执行 | Run in project root
tmh init

# 指定 AI 工具 | Specify AI tool
tmh init --tool claude-code
tmh init --tool cursor

# 指定服务器 | Specify server
tmh init --server http://tmh.example.com:8000

tmh init 会自动检测项目语言、框架、包管理器，创建 .tmh/ 目录和配置，并根据指定工具生成 Hook/Script。

tmh init auto-detects project languages, frameworks, and package managers, creates .tmh/ directory and config, and generates Hook/Script for the specified tool.

同步上下文 | Sync Context

# 同步团队上下文和 AGENTS.md | Sync team context and AGENTS.md
tmh sync

# 静默模式 | Quiet mode
tmh sync --quiet

存储记忆 | Store Memory

# 存储团队决策 | Store a team decision
tmh store --content "JWT 采用滑动窗口刷新策略" \
  --category decision --scope team --tags "auth,jwt"

# 存储经验教训 | Store a lesson learned
tmh store --content "连接池超时设为 30s 可避免数据库锁" \
  --category experience --scope project

# 从 stdin 读取 | Read from stdin
echo "新的编码规范..." | tmh store --content - --category coding_standard

搜索记忆 | Search Memory

# 基础搜索 | Basic search
tmh search "JWT token"

# 按分类过滤 | Filter by category
tmh search "数据库" --category decision

# 限制结果数 | Limit results
tmh search "性能优化" --limit 5

查看详情 | View Details

tmh detail mem_abc12345

导入聊天记录 | Ingest Chat Sessions

# 从文件导入 | Import from file
tmh ingest --file chat.json --tool claude-code

# 指定项目 | Specify project
tmh ingest --file session.json --tool cursor --project proj_xxx

# 支持的工具 Supported tools: claude-code | cursor | opencode | chatbox | codex

偏好管理 | Preference Management

# 查看用户偏好 | List user preferences
tmh prefs list

# 设置偏好 | Set preference
tmh prefs set --key theme --value dark

# 查看生效偏好（含继承）| View effective preferences (with inheritance)
tmh prefs get

# 团队默认偏好 | Team default preferences
tmh prefs team-list
tmh prefs team-set --key max_results --value 50

# 查看自动学习建议 | View auto-learned suggestions
tmh prefs suggestions

规范管理 | Spec Management

# 检测项目画像 | Detect project profile
tmh specs detect

# 规范化规则 | Normalize rules
tmh specs normalize

# 对比规则差异 | Compare rule differences
tmh specs compare

记忆整合 | Memory Consolidation

# 触发扫描 | Trigger scan
tmh consolidation scan

# 查看合并建议 | List merge suggestions
tmh consolidation list

# 接受/拒绝建议 | Accept/reject suggestion
tmh consolidation accept --id sug_xxx
tmh consolidation reject --id sug_xxx

3. HTTP API 使用 | HTTP API Usage

所有 API 端点使用 /api/v1/ 前缀，认证方式为 JWT 或 API Key。

All API endpoints use the /api/v1/ prefix, authenticated via JWT or API Key.

记忆 CRUD | Memory CRUD

# 创建记忆 | Create memory
curl -X POST http://localhost:8000/api/v1/memories \
  -H "Authorization: Bearer $TMH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "content": "使用 pytest-asyncio 的 auto mode 简化异步测试",
    "summary": "pytest-asyncio auto mode 配置",
    "category": "experience",
    "scope": "team",
    "tags": ["testing", "pytest"]
  }'

# 列出记忆 | List memories
curl http://localhost:8000/api/v1/memories \
  -H "Authorization: Bearer $TMH_API_KEY"

# 获取详情（含原文）| Get detail (with content)
curl http://localhost:8000/api/v1/memories/mem_xxx/detail \
  -H "Authorization: Bearer $TMH_API_KEY"

# 更新记忆 | Update memory
curl -X PUT http://localhost:8000/api/v1/memories/mem_xxx \
  -H "Authorization: Bearer $TMH_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"content": "更新的内容", "tags": ["updated"]}'

# 删除记忆 | Delete memory
curl -X DELETE http://localhost:8000/api/v1/memories/mem_xxx \
  -H "Authorization: Bearer $TMH_API_KEY"

搜索 | Search

# 混合搜索 | Hybrid search
curl "http://localhost:8000/api/v1/search?q=JWT%20token&limit=10" \
  -H "Authorization: Bearer $TMH_API_KEY"

Context 引擎 | Context Engine

# 获取 AI 上下文（自动组装 L0+L1+L2）| Get AI context
curl "http://localhost:8000/api/v1/context/agent?project_id=proj_xxx" \
  -H "Authorization: Bearer $TMH_API_KEY"

质量管理 | Quality Management

# 验证记忆 | Verify memory
curl -X POST http://localhost:8000/api/v1/memories/mem_xxx/verify \
  -H "Authorization: Bearer $TMH_API_KEY"

# 置顶记忆 | Pin memory
curl -X POST http://localhost:8000/api/v1/memories/mem_xxx/pin \
  -H "Authorization: Bearer $TMH_API_KEY"

# 标记过时 | Mark as stale
curl -X POST http://localhost:8000/api/v1/memories/mem_xxx/stale \
  -H "Authorization: Bearer $TMH_API_KEY"

SSE 实时事件 | SSE Real-time Events

# 订阅事件流 | Subscribe to event stream
curl -N http://localhost:8000/api/v1/events/stream \
  -H "Authorization: Bearer $TMH_API_KEY"

# 按类型过滤 | Filter by type
curl -N "http://localhost:8000/api/v1/events/stream?types=memory.created,memory.updated" \
  -H "Authorization: Bearer $TMH_API_KEY"

4. MCP Server 集成 | MCP Server Integration

TMH 内置 MCP Server，AI 工具可通过 MCP 协议直接调用。

TMH includes a built-in MCP Server for direct integration with AI tools.

工具列表 | Available Tools

工具 Tool	说明 Description	最低角色 Min Role
`search_memory`	搜索记忆 / Search memories	viewer
`get_memory_detail`	获取记忆详情 / Get memory detail	viewer
`store_memory`	存储新记忆 / Store new memory	member
`update_memory`	更新记忆 / Update memory	member
`delete_memory`	删除记忆 / Delete memory	member

tool_set 配置 | tool_set Configuration

# 只读（推荐给 AI 助手）| Read-only (recommended for AI assistants)
TMH_MCP_TOOL_SET=read_only     # search_memory + get_memory_detail

# 读写 | Read-write
TMH_MCP_TOOL_SET=read_write    # + store_memory

# 全 CRUD（管理工具）| Full CRUD (admin tools)
TMH_MCP_TOOL_SET=full_crud     # + update_memory + delete_memory

传输协议 | Transport

SSE: GET /api/v1/mcp/sse + POST /api/v1/mcp/messages
Streamable HTTP: POST /mcp

Claude Code 集成示例 | Claude Code Integration

在 Claude Code 的 MCP 配置中添加：

Add to Claude Code MCP config:

{
  "mcpServers": {
    "tmh": {
      "command": "curl",
      "args": ["-N", "http://localhost:8000/api/v1/mcp/sse"],
      "env": {
        "TMH_API_KEY": "tmk_your_key"
      }
    }
  }
}

5. Web Dashboard | Web 仪表板

访问 http://localhost:8000/dashboard/ 进入 Web 界面。

Visit http://localhost:8000/dashboard/ for the web interface.

主要页面 | Main Pages

页面 Page	路径 Path	说明 Description
首页概览 Overview	`/dashboard/`	统计数据、趋势图、最近活动 / Stats, trends, recent activity
记忆浏览 Memories	`/dashboard/memories`	记忆列表、过滤、搜索 / Memory list, filter, search
搜索调试 Search Debug	`/dashboard/search`	搜索引擎测试、权重调整 / Search engine testing, weight tuning
规范管理 Specs	`/dashboard/specs`	团队规范查看 / Team specs viewer
记忆整合 Consolidation	`/dashboard/consolidation`	合并建议审核 / Merge suggestion review

管理后台 | Admin Panel

页面 Page	路径 Path	权限 Permission
团队管理 Teams	`/dashboard/admin/teams`	admin
项目管理 Projects	`/dashboard/admin/projects`	maintainer+
用户管理 Users	`/dashboard/admin/users`	admin
API 密钥 API Keys	`/dashboard/admin/api-keys`	admin
审核管理 Curation	`/dashboard/admin/curation`	maintainer+
系统配置 System	`/dashboard/admin/system`	admin

6. AI 工具集成 | AI Tool Integration

TMH 支持多种 AI 编码工具的自动集成。

TMH supports automatic integration with multiple AI coding tools.

支持的工具 | Supported Tools

工具 Tool	上传方式 Upload Tier	说明 Description
Claude Code	Tier 1 - Hook	零 token，post_session Hook 自动回调 / Zero token, auto Hook callback
OpenCode	Tier 1 - Hook	零 token，Hook 自动回调 / Zero token, auto Hook callback
Cursor	Tier 2 - Script	~100 tokens/次，.tmh/upload.py
Codex	Tier 2 - Script	~100 tokens/次，脚本上传 / Script upload
Chatbox	Tier 3 - MCP	~200 tokens/次，MCP 工具调用 / MCP tool call

项目接入流程 | Project Onboarding

# 1. 初始化（选择你使用的 AI 工具）| Initialize (choose your AI tool)
tmh init --tool claude-code

# 2. 同步团队上下文 | Sync team context
tmh sync

# 3. 开始使用 | Start using
# AI 工具会自动获取团队记忆作为上下文
# AI tools will automatically get team memories as context

API 端点总览 | API Endpoints Overview

端点 Endpoint	方法 Method	说明 Description
`/api/v1/auth/register`	POST	用户注册 / User registration
`/api/v1/auth/token`	POST	获取 JWT / Get JWT
`/api/v1/auth/refresh`	POST	刷新 JWT / Refresh JWT
`/api/v1/keys`	GET/POST	API Key 管理 / API Key management
`/api/v1/memories`	GET/POST	记忆列表/创建 / List/create memories
`/api/v1/memories/{id}`	GET/PUT/DELETE	记忆 CRUD / Memory CRUD
`/api/v1/memories/{id}/detail`	GET	记忆原文 / Memory content
`/api/v1/memories/{id}/verify`	POST	验证记忆 / Verify memory
`/api/v1/memories/{id}/pin`	POST	置顶记忆 / Pin memory
`/api/v1/memories/{id}/stale`	POST	标记过时 / Mark stale
`/api/v1/search`	GET	混合搜索 / Hybrid search
`/api/v1/context/agent`	GET	AI Context 组装 / AI context assembly
`/api/v1/teams`	GET/POST	团队管理 / Team management
`/api/v1/projects`	GET/POST	项目管理 / Project management
`/api/v1/consolidation/scan`	POST	触发合并扫描 / Trigger merge scan
`/api/v1/consolidation/suggestions`	GET	合并建议列表 / Merge suggestions
`/api/v1/consolidation/suggestions/{id}/accept`	POST	接受合并 / Accept merge
`/api/v1/curation/run`	POST	运行维护任务 / Run curation
`/api/v1/preferences/user`	GET/POST	用户偏好 / User preferences
`/api/v1/preferences/effective`	GET	生效偏好 / Effective preferences
`/api/v1/events/stream`	GET	SSE 事件流 / SSE event stream
`/api/v1/specs`	GET/POST	规范管理 / Spec management
`/api/v1/chats/ingest`	POST	聊天记录导入 / Chat ingest
`/api/v1/mcp/sse`	GET	MCP SSE 传输 / MCP SSE transport
`/mcp`	POST	MCP Streamable HTTP
`/api/v1/health`	GET	健康检查 / Health check
`/api/v1/admin/*`	-	管理后台 API / Admin API

完整 API 文档：启动服务后访问 http://localhost:8000/docs

Full API docs: visit http://localhost:8000/docs after starting the server

项目结构 | Project Structure

src/team_memory_hub/
  cli.py                   # CLI 入口 / CLI entry (tmh global command)
  config.py                # TOML + 环境变量配置 / TOML + env config
  __main__.py              # python -m 服务器入口 / Module server entry
  core/
    memory_store.py        # 记忆 CRUD + 文件一致性 / Memory CRUD + file consistency
    memory_file_store.py   # Markdown 文件存储 / Markdown file storage
    search_engine.py       # 混合搜索引擎 / Hybrid search engine
    context_engine.py      # 三层 Context 组装 / Three-layer context assembly
    context_cache.py       # Context 缓存 / Context cache
    context_syncer.py      # 上下文同步 / Context sync
    preference_engine.py   # 用户偏好引擎 / User preference engine
    memory_consolidator.py # 合并建议生成 / Merge suggestion generation
    memory_extractor.py    # 聊天记忆提取 / Chat memory extraction
    curation.py            # 自动维护任务 / Auto curation tasks
    rbac.py                # 权限矩阵 / Permission matrix
    audit.py               # 审计日志 / Audit log
    write_queue.py         # 异步写队列 / Async write queue
    agents_generator.py    # AGENTS.md 生成 / AGENTS.md generation
    project_detector.py    # 项目画像检测 / Project profile detection
    rule_normalizer.py     # 规则规范化 / Rule normalization
    spec_matcher.py        # 规范匹配 / Spec matching
    spec_deduplicator.py   # 规范去重 / Spec deduplication
    spec_manager.py        # 规范管理 / Spec management
  server/
    app.py                 # FastAPI 应用工厂 / FastAPI app factory
    dependencies.py        # 认证 & DI 依赖 / Auth & DI dependencies
    event_bus.py           # SSE 事件总线 / SSE event bus
    mcp_server.py          # MCP JSON-RPC Server
    routes/                # API 路由模块 / API route modules
  providers/
    embedding/             # 嵌入提供商 / Embedding providers (Gemini, OpenAI, ONNX, Compatible)
    llm/                   # LLM 提供商 / LLM providers (Claude, Gemini, Rules)
  chat_adapters/           # 聊天适配器 / Chat adapters (Claude Code, Cursor, OpenCode, Chatbox, Codex)
  client_adapters/         # 客户端适配器 / Client adapters
  dashboard/
    templates/             # Jinja2 + HTMX 模板 / Templates
    static/                # CSS, JS
  storage/
    database.py            # aiosqlite 封装 + 迁移管理 / aiosqlite wrapper + migration
    models.py              # Pydantic 数据模型 / Pydantic data models
    migrations/            # Schema 迁移 / Schema migrations (v1, v1_5, v1_6)

测试 | Testing

# 运行所有测试 | Run all tests
pytest

# 带覆盖率 | With coverage
pytest --cov=team_memory_hub

# 单个测试文件 | Single test file
pytest tests/test_memories.py
pytest tests/test_cli.py
pytest tests/test_mcp.py

# 快速失败 | Fail fast
pytest -x --tb=short

许可证 | License

MIT

FilesExpand file tree

README.md

Latest commit

History