AgentGuard
Runtime guardrails for AI agents: budgets, loops, timeouts, and rates.
pip install agentguard47Tools
AgentGuard is the flagship. The rest of the shelf supports the same job: build, test, and control agent workflows without a fake enterprise wrapper.
Observed package downloads from PyPI, updated hourly. Counts include mirror noise filtered out where the upstream supports it. Downloads are a usage signal, not an adoption proof. A conservative floor is shown when every upstream is unavailable.
12 live from 12 public tools.
Runtime guardrails for AI agents: budgets, loops, timeouts, and rates.
pip install agentguard47Estimate local LLM VRAM needs, GPU layer counts, and CPU offload risk.
Choose a local LLM for your GPU, workload, and speed-quality tradeoff.
Compare GGUF quant levels by size, quality, speed, and GPU fit.
Remove the 5 free runs per tool per day limit. Saved GPU rigs, Hugging Face model import, fit alerts, and benchmark history for local LLM builders.
Describe an AI agent workflow. Get risks, architecture, guardrails, and next steps.
Cursor plugin for scoping AI agent builds, risk, cost, and architecture.
Watch multi-agent AI coordinate live. Skills, handoffs, tools.
Paste a URL. Get summary, sentiment, entities in seconds.
Four AI personas reacting to your live podcast in real time.
Pay-per-call memory for agents. USDC on Base, no accounts.
Look up public Dota 2 profiles, recent matches, ranks, hero performance, and 10-player breakdowns via OpenDota.