Llm Ops

Open-source LLM app development platform for building AI workflows, RAG pipelines, and agents.

Open-source, real-time infrastructure monitoring with per-second metrics, ML-powered anomaly detection, and zero-config

Free MIT AI gateway unifying 359 providers and 1200+ models behind one endpoint with quota-aware auto-fallback.

Open-source context compression layer for AI agents, cutting tokens 60-95% for JSON and 15-20% for coding.

Kong is a cloud-native API, LLM, and MCP gateway with high performance and extensible plugins.

Dynamic service discovery, configuration management, and service management platform for cloud-native AI applications.

Open-source generative BI engine for AI agents: governed text-to-SQL, semantic layer, and dashboard deployment across 22

Blazing fast AI Gateway routing to 1600+ LLMs with guardrails, retries, and load balancing via one API.

High-performance open-source AI gateway unifying 23+ LLM providers with failover, load balancing, and MCP support.

Open-source LLM platform to extract structured JSON from unstructured documents via API, ETL, or MCP.

Open-source enterprise AI platform with MCP registry, gateway, orchestrator, guardrails, and observability.

Self-hostable workflow orchestrator with declarative YAML, single binary, no database, MCP support.

Open-source observability and policy enforcement for AI agent harnesses, capturing runs and blocking risky tool calls.

High-performance LLM proxy and load balancer with intelligent routing, failover, and model discovery.

Intelligent LLM gateway and VRAM-aware router for Ollama, llama.cpp, and OpenAI with semantic caching and auto-failover.

Self-hosted control plane for OpenClaw and Hermes AI-agent fleets on Docker/Kubernetes with REST, CLI, and MCP.

Local AI load balancer for Ollama and MLX fleets with auto-discovery, smart routing, and OpenAI-compatible API.