sqz runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 23 Aug 2026.
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
The linked repository no longer exists on GitHub — it was deleted or made private.
This one has been quiet for a while
Quiet is not dead — but it is worth knowing when it wakes up, or when someone else takes it over. We watch the repository and tell you either way.
Alternatives to sqz
same job, measured the same wayPrompt-injection firewall for AI agents — scan untrusted text before LLM calls.
Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM
Context selection and compression for AI agents - recall measured, not claimed.
Deterministic context selection for AI coding agents. Local memory that compounds across sessions.
Scan skills, MCP configs, and agent content for injection and supply-chain risks. Offline, no LLM.
Verified context layer for AI coding agents — prunes, compresses, indexes, remembers. 32 MCP tools.
Audits any website for AI agent readiness and safety, scoring prompt injection risk and llms.txt.
Context optimization for LLM agents: tool registry, result masking, budgeting, compaction.
sqz — questions
Answers built from our own checks of this server.