Guard
MCP serverLocal MCP server giving JS/TS coding agents architecture rules and project context
Runs locally- Open source
- 4 GitHub stars
- Developer tools
Local MCP server giving JS/TS coding agents architecture rules and project context
Runs locallyCatch outdated AI model IDs in code and look up current LLM prices and limits
Runs locallyPrice LLM workloads, size GPUs and audit MCP configs from your coding agent
Runs locallyCheck LLM outputs against your own rules before swapping a model, prompt or provider
Runs locallyHeartbeat and tokens-per-second monitoring for home Ollama, llama.cpp and vLLM servers
Not checked yetChecks JS/TS written by AI for risky patterns, fake npm packages and weakened tests
Runs locallyStops AI coding agents stuck in error loops and tracks token spend across tools
Profiles a local AI host and plans measurable, reversible model-speed tweaks via MCP
Runs locallyChecks OpenAI, Anthropic and Google model IDs for retirement dates before agents use them
Runs locallyLocal MCP server to check VRAM fit, manage models and delegate work to local LLM runtimes
Runs locallyHands-on agent test results for small AI tools, live AI outages and a package name check
Not checked yetGoverned AI-ops for vLLM, Ray Serve, SGLang and TGI: latency RCA, scaling, drain
Runs locallyThe closest alternatives to Stack Guardian are Guard, Stalemodel, AIOps Field Notes, LLM Preflight and Paw Pulse.
Yes. Guard, Stalemodel, AIOps Field Notes have a free or open-source option.