Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral chec
Detects prompt injection by its effect on a sacrificial canary model, not just pattern matching: untrusted input hits a powerless model first, a behavioral check reads the residue, and it returns block, flag, or pass before your primary model acts. Inbound preflight sensor, not a guarantee.
Maintain this project? Show that it is featured on YunoDB.
[](https://yunodb.com/tools/hermes-labs-ailittle-canary?utm_source=github&utm_medium=badge)<a href="https://yunodb.com/tools/hermes-labs-ailittle-canary?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/hermes-labs-ailittle-canary.svg" alt="Featured on YunoDB" height="20"></a>
Local-first search engine and MCP server for AI agents. One Rust binary indexes code, docs, logs, JSONL/CSV and PDFs for BM25 full-text, vector and hybrid searc
Open-source (Apache-2.0) orchestrator for Claude Code, Codex & 30+ coding agents. Plan, run and supervise agent teams from task to merged PR. Desktop (macOS, Wi
45+ tips for getting the most out of Claude Code, from basics to advanced - includes a custom status line script and Claude Code running itself in a container.