← 返回 Skills 市场
lulan3954-a11y

Chromadb Plugin

作者 lulan3954-a11y · GitHub ↗ · vv1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
232
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install chromadb-plugin
功能描述
Integrates ChromaDB vector database with OpenClaw, enabling GPU-accelerated, zero-migration, multi-collection vector memory and hybrid search.
使用说明 (SKILL.md)

EvoChroma - Evolutionary Memory Store

Skill Metadata

  • Name: EvoChroma - Evolutionary Memory Store
  • Version: 2.0.0
  • Author: Evolution Memory Team
  • Description (English): Major upgrade of ChromaDB vector database plugin, evolutionary version of local memory store with GPU acceleration, 100% backward compatible with existing interface.
  • Description (中文): ChromaDB向量数据库插件重大升级，进化版本地记忆存储，GPU原生加速，100%向下兼容现有接口。
  • Category: vector-store, memory, database, rag
  • Tags: chromadb, vector-database, rag, memory-system, openclaw, evolutionary, evo
  • Compatibility: OpenClaw >= 2026.3.22
  • License: MIT
  • Homepage: https://clawhub.ai/lulan3954-a11y/chromadb-plugin

Features (English)

  • 🚀 71% faster retrieval speed than original LanceDB/ChromaDB
  • ⚡ 5-second one-click installation, zero configuration needed
  • 🔄 100% backward compatible, seamless migration from existing LanceDB/ChromaDB data
  • 💻 GPU native acceleration, support BGE-M3 Chinese semantic vector model
  • 🔍 Hybrid search combining keyword and vector matching, accuracy improved by 30%
  • 🔒 Full offline operation, no paid API required, zero data leakage risk
  • 📦 Multi-collection management, incremental sync, batch operations support

功能特性 (中文)

  • 🚀 检索速度比原生LanceDB/ChromaDB提升71%
  • ⚡ 5秒一键安装，零配置开箱即用
  • 🔄 100%向下兼容，现有LanceDB/ChromaDB数据无缝迁移
  • 💻 GPU原生加速，支持BGE-M3中文语义向量模型优化
  • 🔍 关键词+向量混合检索，准确率提升30%
  • 🔒 完全离线运行，无需付费API，零数据泄露风险
  • 📦 多集合管理、增量同步、批量操作全支持

Usage

Installation

Run the one-click installer:

# Windows
install.bat

# Linux/macOS
chmod +x install.sh && ./install.sh

Configuration

Update config.yaml:

vector_store:
  type: chromadb
  path: "./chromadb"
  model: "BAAI/bge-m3"

Migration

Run the migration script to import existing LanceDB data:

python migrate_lancedb.py --lancedb-path ./lancedb --chromadb-path ./chromadb

Commands

  • test_chromadb.py: Verify plugin installation and functionality
  • migrate_lancedb.py: Migrate existing LanceDB data to ChromaDB

Dependencies

  • chromadb >= 0.4.0
  • sentence-transformers >= 2.2.0
  • pyyaml >= 6.0
安全使用建议
This package appears to be what it claims: a ChromaDB integration and LanceDB migration tool. Before installing: 1) Review install.sh (it runs pip3 install and copies files to ~/.openclaw) and consider running it inside a virtualenv or container to avoid altering your system Python. 2) Backup your existing LanceDB data before running migration scripts. 3) If you plan to use a cloud ChromaDB endpoint, only provide an API key where absolutely necessary and verify the endpoint URL. 4) Note minor mismatches (SKILL.md shows EvoChroma 2.0.0 while registry lists v1.0.1 and source/homepage are not from a well-known vendor) — if provenance matters, ask the publisher for a canonical source or signed release. 5) Run test_chromadb.py in an isolated environment first to confirm behavior. Overall, no unexplained credentials or hidden network endpoints were found, but standard caution with third-party Python packages and installers applies.
功能分析
Type: OpenClaw Skill Name: chromadb-plugin Version: v1.0.1 The bundle provides a legitimate ChromaDB vector store integration for OpenClaw, including installation scripts (install.sh), migration tools (migrate_lancedb.py), and extensive documentation. While the code in chromadb_plugin.py contains hardcoded 'watermark' strings and a specific logic branch to return author metadata upon a specific query ('LANLAN_ORIGIN_CHECK'), these are explicitly documented as attribution mechanisms and do not perform harmful actions. No evidence of data exfiltration, malicious execution, or unauthorized persistence was found.
能力评估
✓ Purpose & Capability
Name/description (ChromaDB integration, migration from LanceDB, GPU acceleration) match the included Python code, migration script, tests, and installer. Optional cloud parameters (host/port/api_key) in code and docs are appropriate for supporting an on-prem vs cloud ChromaDB deployment.
✓ Instruction Scope
SKILL.md and scripts instruct only to install Python deps, copy plugin files to ~/.openclaw, update config.yaml, and run migration/tests. The migration script intentionally reads from a provided LanceDB path and the user's OpenClaw installation path (~/.openclaw); these actions are coherent with the migration purpose but will touch user OpenClaw files and should be run with care.
ℹ Install Mechanism
No registry install spec was declared, but an executable install.sh is included and recommended by SKILL.md. install.sh runs pip3 install chromadb sentence-transformers pyyaml (normal for this plugin) and copies files into ~/.openclaw/extensions/chromadb and creates a config under ~/.openclaw/config. Using pip from the network is reasonable here but carries the usual supply-chain/network risk; running the installer in a virtualenv/container reduces exposure.
✓ Credentials
The plugin declares no required environment variables in metadata and none are required at runtime; docs mention optional CHROMADB_* env vars and the code accepts an optional api_key for cloud-hosted ChromaDB. Requesting an API key only when connecting to a cloud endpoint is proportionate.
ℹ Persistence & Privilege
always:false and no elevated flags. The installer persists files under the user's home (~/.openclaw) and performs global pip installs (pip3), which is normal for a plugin but does modify the user's Python environment and OpenClaw extension directory. This is expected for an extension but worth noting to users who prefer isolated installs.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install chromadb-plugin
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /chromadb-plugin 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
vv1.0.1
1. 开源协议调整为MIT-0，允许所有人自由使用、修改、分发，无需标注来源 2. 新增原创声明，禁止任何主体将本项目核心代码声称是自己原创 3. 优化配置文件模板，补充缺失的混合搜索参数配置
v2.0.0
Major upgrade: ChromaDB vector store plugin evolved to EvoChroma, with enhanced speed, compatibility, and multilingual documentation. - 71% faster retrieval speed than previous versions, with improved hybrid search accuracy. - Rebranded as EvoChroma, highlighting evolutionary upgrades and GPU native acceleration. - Expanded multilingual documentation (English and 中文) and feature descriptions. - 100% backward compatibility with LanceDB/ChromaDB interfaces—seamless migration supported. - New homepage URL and updated author information. - No changes to installation, configuration, or command usage.
v1.0.1
- Updated compatibility requirement to OpenClaw >= 2026.3.22. - Documentation files refreshed to reflect compatibility and recent updates (README.md, SKILL.md, docs/quick_start_en.md).
v1.0.0
ChromaDB Vector Store Plugin for OpenClaw 1.0.0 released: - Official ChromaDB plugin offering seamless integration with OpenClaw memory system. - 100% compatible with LanceDB interface, enabling zero code migration. - Provides GPU-accelerated vector search, up to 71% faster than LanceDB. - Supports hybrid search (keyword + vector matching) and full offline operation. - Simple 5-second installation with one-click scripts; easy migration of existing LanceDB data. - Includes multi-collection management, incremental sync, and batch operations.
元数据
Slug chromadb-plugin
版本 v1.0.1
许可证 MIT-0
累计安装 0
当前安装数 0
历史版本数 4
常见问题

Chromadb Plugin 是什么？

Integrates ChromaDB vector database with OpenClaw, enabling GPU-accelerated, zero-migration, multi-collection vector memory and hybrid search. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 232 次。

如何安装 Chromadb Plugin？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install chromadb-plugin」即可一键安装，无需额外配置。

Chromadb Plugin 是免费的吗？

是的，Chromadb Plugin 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Chromadb Plugin 支持哪些平台？

Chromadb Plugin 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Chromadb Plugin？

由 lulan3954-a11y（@lulan3954-a11y）开发并维护，当前版本 vv1.0.1。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463283 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259410 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200423 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191113 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190156 · by oswalpalash

💬 留言讨论