llm-ops

Open Source API and AI Gateway supporting REST, GraphQL, TCP, gRPC and MCP (Model Context Protocol)

Give your AI agents structure, guardrails, and full observability — the Agent control plane built on MCP.

CoreMCP: Connect Legacy Databases to AI Agents via Model Context Protocol. Open-source bridge for LLM data analysis.

The Kubernetes operator where AI agents manage their own infrastructure. Self-healing via intent annotations, Ed25519-signed audit, graceful LLM fallback.

Unofficial Go SDK for Langfuse - trace, monitor, and evaluate your LLM applications with async batch processing and specialized observation types

A universal, highly intelligent LLM API proxy gateway. Seamlessly translates heterogeneous AI protocols (OpenAI, Anthropic, Gemini) with built-in multi-account rotation, circuit breaking, and zero-config deployment.

The AI engineering platform for AI teams. Observability, evaluation, and prompt management for LLMs and AI agents. OpenTelemetry native.

Typed LLM operations for Go. Fluent builders over one execution path, with structured-output contracts, retries, cost tracking, and an envelope that keeps model claims separate from measured facts.

🚀 Build with the Langfuse Go SDK to enhance your applications using Langfuse's open-source LLM engineering platform.

Enterprise AI Inference Platform (RAG) showcasing modern DevSecOps, Zero Trust, and IaC practices on Kubernetes

Contract-based accountability runtime for AI agents. Define tasks with required evidence — no proof means not done. MCP server with multi-agent pipelines, independent verification, and append-only audit log.

Distributed real-time AIOps platform for metric ingestion and anomaly detection. Built with Go (CQRS/Event Sourcing), NATS JetStream, and Python (PyTorch/ML).

Aeterna: Universal Process Hot-Relay Orchestrator (UPHR-O). Achieves Zero-Downtime & Zero-Amnesia deployments for AI Agents and Stateful Services via seamless Socket Inheritance and the State Relay Protocol (SRP).