Secret Guard is a lightweight local LLM gateway that protects your secrets. Outbound requests have secrets replaced with equal-length realistic mocks, and responses are restored back to real values on the way in, so the LLM never touches a real secret while your agent's tools keep working. It is written in Rust and supports multiple protocols.
Be the first to rate Secret Guard. Your feedback helps other users decide.
Swap real credentials for equal-length mocks before a request leaves your machine.
Put the real values into the response locally so tools still function.
Preserve token shape so redaction does not disturb the model's formatting.
Similar tools in the same category — compare side-by-side
GoRoute is a high-performance LLM gateway and multi-provider router for coding agents, with a Go cor...
CtxWise is a multi-agent context firewall, MCP schema tree-shaker and token budget guard for Claude ...
Quorus puts your AI agents in a group chat. You message Claude Code, Codex and other models like a t...
Guides and comparisons about code tools
Nine new tools that put something deterministic between an agent and what it touches: gateways, policy firewalls, AST breakers, SQL guards and usage ceilings.
Eight local inference projects that fit big models into small memory: a 26B model in 2 GB, MoE weight streaming, a console as a server and sub-1-bit compression
Nine tools for supervising coding agents: phone alerts when an agent blocks, review inboxes, menu-bar contacts, shared scratchpads and team boards.
Nine tools that constrain what an agent can produce and reach: slop-detecting lint rules, declared sandbox tiers, cheaper crawling and signed messaging.
Twenty-five coding tools sorted by what they do: autocomplete, codebase comprehension, testing, or self-hostable models, from CodeGeeX to Codestral.
