Weir
Plant fake API keys, then find out where your agent sent them
Emerged finds new products worth a look, daily — what’s new today
ContextVeil
Lets coding agents read files with secrets while redacting values from the LLM
Agents can keep reading .env and config files they need, while the values you enrolled are swapped for placeholders before anything reaches the model.
ContextVeil sits between a coding agent and its model and replaces chosen secret values with placeholders before text is sent, without blocking file access. A guided setup finds likely candidates in environment variables, .env files, configs and agent credential stores, and stores only references. At runtime it reads current values and does exact replacement. It supports Claude Code, with experimental Codex, Copilot CLI and OpenCode support. It is a local Rust binary, MIT or Apache-2.0, at v1.0.0. It does not catch encoded or transformed values or stop exfiltration.
More like this
T
toolshed
Install, test and keep secrets for MCP servers from a single terminal app
TokenEconomizer
Cuts what Claude Code and Codex spend in a repo you work in daily
BLA
Hardens your shipped builds so AI reverse-engineering agents waste effort
Openmsg
A shared inbox so coding agents from different vendors can message each other
O
Opair
A coding harness that pairs with you instead of working on its own