open-sentinel
bởi sentinel199
Web & Frontend DevelopmentTóm tắt
Transparent LLM proxy that monitors and enforces policies on AI agent behavior — evaluates responses.
Mô tả
Kỹ năng này làm gì
A transparent proxy that sits between your application and any LLM provider, evaluating every response against plain-English rules before output reaches users. Rules are defined in YAML and cover hallucinations, PII leaks, prompt injection, and multi-turn workflow violations. Any OpenAI-compatible client works with it without code changes.
Because it operates at the proxy layer, any OpenAI-compatible client gets policy enforcement without modifying application code.
Khi nào nên dùng
- Blocking PII leaks in customer-facing chatbots
- Enforcing multi-step refund workflows in support agents
- Catching hallucinated citations before they reach end users
- Detecting prompt injection attempts in user-facing AI tools
- Auditing model responses against internal company policy rules
Quy trình ví dụ
User asks: 'What are the internal pricing tiers for enterprise plans?'
- 1
Client sends request to proxy at localhost:4000 instead of the LLM provider directly
- 2
Proxy forwards the request to the configured LLM and receives the response
- 3
Judge engine evaluates the response asynchronously against the active policy rules
- 4
Proxy detects that the response contains restricted internal pricing information
- 5
Response is blocked before it reaches the user
Request is blocked; the user does not receive the restricted pricing information
Yêu cầu
- API key from Anthropic (ANTHROPIC_API_KEY), OpenAI (OPENAI_API_KEY), or Google (GEMINI_API_KEY)
Cài đặt
clawhub install sentinel199/open-sentinelChạy lệnh CLI, hoặc dán prompt vào Claude Code, Cursor, Codex hay coding agent bạn đang dùng.