Releases·Tool Release
Show HN: Open-source tool lets coding agents read files with secrets while redacting values from LLM context
Show HN: Tool redacts secret values from file contents before they enter LLM context
4 engagement1 sourceTue, Sep 15, 2026, 02:24 PM
AI Overview
- A Show HN post links to a GitHub project that redacts secret values from file contents before they enter an agent's LLM context
Entities
Related
Products·concept
preflight — local proxy that scans LLM requests for secrets before they reach the model
preflight is a local proxy that intercepts LLM API requests and attachments, scanning them for secrets before they reach the model. It sits between any OpenAI-compatible client and the model, decoding and inspecting payloads, then redacting or blocking sensitive content. It solves accidental secret leakage for developers using coding harnesses and LLM tools.
preflight is a local proxy that intercepts LLM API requests and attachments, scanning them for secrets before they reach the model. It sits between any OpenAI-compatible client and the model, decoding and inspecting payloads, then redacting or blocking sensitive content. It solves accidental secret leakage for developers using coding harnesses and LLM tools.
71 engagement1 sourcegithubSun, Sep 20, 2026, 02:11 PM
Products·launched
Sanitizer: Strip sensitive data from documents locally before an LLM
Sanitizer is a tool that removes sensitive information from documents locally before sending them to an LLM, ensuring privacy and compliance. It addresses the real problem of data leakage when using LLMs with confidential documents, targeting businesses and individuals who need to protect sensitive data.
Sanitizer is a tool that removes sensitive information from documents locally before sending them to an LLM, ensuring privacy and compliance. It addresses the real problem of data leakage when using LLMs with confidential documents, targeting businesses and individuals who need to protect sensitive data.
1 engagement1 sourcehackernewsSat, Aug 1, 2026, 01:42 AM
Products·launched
Keyfence: local proxy that blocks secrets from reaching LLM APIs
Keyfence is a local proxy that sits between applications and LLM APIs to stop secrets and API keys from being sent in prompts. It addresses the risk of developers accidentally leaking credentials when using LLM services. It is aimed at developers and teams using LLM APIs.
Keyfence is a local proxy that sits between applications and LLM APIs to stop secrets and API keys from being sent in prompts. It addresses the risk of developers accidentally leaking credentials when using LLM services. It is aimed at developers and teams using LLM APIs.
1 engagement1 sourcehackernewsTue, Sep 8, 2026, 07:16 PM
Products·launched
Prompt-scrub: local-first PII redaction for LLM prompts and responses
Prompt-scrub is a local-first tool that redacts personally identifiable information (PII) from LLM prompts and responses before they leave the user's environment. It helps developers and organizations protect sensitive data when using LLM APIs, ensuring privacy and compliance.
Prompt-scrub is a local-first tool that redacts personally identifiable information (PII) from LLM prompts and responses before they leave the user's environment. It helps developers and organizations protect sensitive data when using LLM APIs, ensuring privacy and compliance.
6 engagement1 sourcehackernewsFri, Jul 31, 2026, 03:32 PM
Products·launched
PrivateRedact: Offline PII redaction using local LLM
PrivateRedact is a tool that redacts personally identifiable information (PII) from documents entirely offline using a local LLM, ensuring privacy by avoiding cloud services. It addresses the need for secure data sanitization in sensitive environments where data cannot leave the premises.
PrivateRedact is a tool that redacts personally identifiable information (PII) from documents entirely offline using a local LLM, ensuring privacy by avoiding cloud services. It addresses the need for secure data sanitization in sensitive environments where data cannot leave the premises.
1 engagement1 sourcehackernewsMon, Aug 10, 2026, 03:43 PM