#redaction

Encrypt PII, not meaning. Locally.

Detect and redact secrets in key-value pairs, dicts, and environment variables. Library and CLI.

Strip common prompt injection surfaces.

Self-hosted PII redaction proxy for LLM APIs and agent CLIs. Scrubs names, emails and secrets from Claude Code, Codex and any OpenAI-compatible app before requests leave your machine, tool-call arguments included, then restores them in the reply. Local detection, zero telemetry.

HTTP traffic recording, sanitization, and replay library for Go. Record real API interactions, automatically redact secrets and PII, replay as mock server. Embeddable, zero dependencies, sanitize-on-write.

SunLit Security Libraries: Rust security crates for OWASP-aligned services

A Rust library that lets you automatically redact sensitive data for safe logging and debugging.

Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.

Cross-platform layered configuration loader for Python

Redact sensitive information from strings, arrays and objects.

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-boundary leaks), mcp-ssrf-check, and a self-hosted redacting gateway.

PHP 8.5+ shared exception contracts, context-aware bases, and secret redaction for the JOOservices ecosystem. Zero runtime dependencies.

Schema-backed contract layer for governed AI/security workflows: intent, policy decisions, approvals, execution receipts, evidence, and replayable audit traces.

Zero-dependency TypeScript secret and PII redaction for any SDK, logs, HTTP, LLM prompts, and scoped MCP tool boundaries.