Production Ai Python Packages

axonflow

Official Python SDK for AxonFlow — runtime control, MCP policy enforcement, approvals, and audit trails for production AI

kalibr

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

silentwatch-mcp

MCP server for catching cron silent failures in production AI deployments — exit-0-with-empty-output detection, retry storms, action-budget leaks. Works with system cron, systemd timers, OpenClaw cron logs.

openclaw-skill-vetter-mcp

MCP server for security-vetting third-party AI agent extensions before installation — Claude skills, plugins, tool packs. 41 detection rules across prompt-injection, exfiltration, dynamic execution, typosquats. 0-100 risk score.

openclaw-upgrade-orchestrator-mcp

MCP server for safe AI agent runtime upgrades — version-aware regression catalog, pre/post snapshot diff, rollback guides. Read-only advisor: never executes upgrades. Bring your own catalog for non-OpenClaw runtimes.

openclaw-cost-tracker-mcp

MCP server for AI agent token-cost telemetry across Anthropic, OpenAI, Gemini, Ollama — per-agent attribution, anomaly detection, model-routing recs with savings estimates, monthly forecast.

openclaw-health-mcp

MCP server for AI agent deployment health — gateway, CPU/RAM, recent errors, skill registry, upgrades, disk usage. Cross-platform Linux-proc backend; OpenClaw operators get native ~/.openclaw/ parsing.

jamjet

The open-source safety layer for AI agents — block unsafe tool calls, require approval, enforce budgets, audit, replay.

argus-llm

Production-grade LLM observability. G-ARVIS scoring for Groundedness, Accuracy, Reliability, Variance, Inference Cost, and Safety.

llm-cost-reduction

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

llm-cost-optimizer

Stop overpaying to run your agents. Kalibr routes every request to lower-cost model and tool paths without degrading performance.

kite-agent

Production-ready agentic AI framework. High-performance, lightweight, simple. Built-in safety, memory, and 4 reasoning patterns. Ships to production fast.

minotor

Open source software for machine learning production monitoring : maintain control over production models, detect bias, explain your results.

langchain-kalibr

LangChain integration for Kalibr. Route every LangChain LLM call to lower-cost model paths without degrading performance.