AI Skill Hub 强烈推荐:PrivAiTe 是一款优质的AI工具。AI 综合评分 8.0 分,在同类工具中表现稳健。如果你正在寻找可靠的AI工具解决方案,这是一个值得深入了解的选择。
PrivAiTe 是一款基于 Python 开发的开源工具,专注于 ai-gateway、anonymization、chatgpt-privacy 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
PrivAiTe 是一款基于 Python 开发的开源工具,专注于 ai-gateway、anonymization、chatgpt-privacy 等核心功能。作为 GitHub 开源项目,它拥有活跃的社区支持和持续的版本迭代,代码完全透明可审计,支持本地部署以保护数据隐私。无论是个人使用还是集成到企业工作流,都能提供稳定可靠的解决方案。
# 方式一:pip 安装(推荐)
pip install privaite
# 方式二:虚拟环境安装(推荐生产环境)
python -m venv .venv
source .venv/bin/activate # Windows: .venv\Scripts\activate
pip install privaite
# 方式三:从源码安装(获取最新功能)
git clone https://github.com/crp4222/PrivAiTe
cd PrivAiTe
pip install -e .
# 验证安装
python -c "import privaite; print('安装成功')"
# 命令行使用
privaite --help
# 基本用法
privaite input_file -o output_file
# Python 代码中调用
import privaite
# 示例
result = privaite.process("input")
print(result)
# privaite 配置文件示例(config.yml) app: name: "privaite" debug: false log_level: "INFO" # 运行时指定配置文件 privaite --config config.yml # 或通过环境变量配置 export PRIVAITE_API_KEY="your-key" export PRIVAITE_OUTPUT_DIR="./output"
A drop-in, self-hosted LLM proxy that reversibly redacts PII before it reaches the provider, including inside tool-call arguments and multimodal content, with zero telemetry.
Keep personal data out of your LLM calls. PrivAiTe is a local proxy that sits between your app and the model provider. It finds names, emails, phone numbers, cards, IBANs, secrets and more, swaps them for stand-ins before anything leaves your machine, and puts the real values back in the reply. It does this across message text, tool-call arguments, and multimodal content, which is where most tools stop looking. Detection runs on your machine and nothing phones home. By default it runs the full ONNX suite, so it also catches secrets and passwords, not just the easy regex entities. Point any OpenAI-compatible client at it.
You type: "Je m'appelle Marie Dupont, email marie@acme.com"
LLM sees: "Je m'appelle <PERSON_1>, email <EMAIL_ADDRESS_1>"
LLM says: "Bonjour <PERSON_1>, votre email <EMAIL_ADDRESS_1> est noté."
You see: "Bonjour Marie Dupont, votre email marie@acme.com est noté."
This is local pseudonymization, not anonymization, and detection is best-effort rather than a guarantee. You remain the data controller. The Threat model spells out exactly what it protects against and what it does not.
The default onnx preset does detect personal addresses (as LOCATION) and personal URLs (as URL) through the Privacy Filter model, and replaces them. What stays off by default are Presidio's broad recognizers for those types, because they cause heavy false positives:
onnx preset keeps this recognizer off and relies on the model's context-aware address detection instead.logging.getLogger because .ge is a valid TLD. The onnx preset keeps it off, and the model still catches genuine personal URLs.On the light preset (Presidio only), addresses and URLs are not detected. Secrets and passwords are detected only by the onnx preset. Any recognizer can be turned on in the YAML config.
pip install -e .
python -m spacy download en_core_web_lg
python -m spacy download fr_core_news_md
The default onnx preset downloads its model the first time the proxy starts. Want the lighter, faster path with no model download? Set preset: "light" in your config.
docker compose up -d
cp .env.example .env
cp config/privaite.example.yaml config/privaite.yaml
Edit .env with your API keys and config/privaite.yaml with your LLM providers.
OpenAI-compatible:
| Endpoint | Description |
|---|---|
POST /v1/chat/completions | Chat (streaming + non-streaming) |
POST /v1/completions | Text completions |
POST /v1/embeddings | Embeddings (anonymized, no de-anonymization) |
GET /v1/models | List configured models |
GET /health | Health check |
GET /ready | Readiness check |
GET /stats | PII detection stats per session |
Keeping PII out of LLM calls is a crowded space, and PrivAiTe is not always the right pick. Based on each project's public docs as of June 2026:
Where PrivAiTe differs: it anonymizes PII inside tool-call arguments and multimodal content, not just message text (LangChain's gateway docs, for instance, note that tool-call arguments are not scanned), it restores the original values in the response, and it ships a reproducible benchmark. If your traffic is agentic or multimodal, that gap is the reason this exists.
一个有用的开源AI工具,保护聊天记录隐私
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。
✅ BSD 3-Clause — 宽松协议,可商用修改分发,禁止使用原作者名称进行背书宣传。
总体来看,PrivAiTe 是一款质量优秀的AI工具,在同类工具中具备一定竞争力。AI Skill Hub 将持续追踪其更新动态,建议收藏备用,结合自身场景选择合适时机引入使用。
| 原始名称 | PrivAiTe |
| 原始描述 | 开源AI工具:Drop-in self-hosted LLM proxy that reversibly redacts PII before OpenAI, ChatGPT。⭐9 · Python |
| Topics | ai-gatewayanonymizationchatgpt-privacydata-masking |
| GitHub | https://github.com/crp4222/PrivAiTe |
| License | BSD-3-Clause |
| 语言 | Python |
收录时间:2026-07-02 · 更新时间:2026-07-02 · License:BSD-3-Clause · AI Skill Hub 不对第三方内容的准确性作法律背书。