Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.

🏕️ Reproducible development environment

Declarative Intent Driven Platform Orchestrator for Internal Developer Platform (IDP).

🕵️‍♂️ Library designed for developers eager to explore the potential of Large Language Models (LLMs) and other generative AI through a clean, effective, and Go-idiomatic approach.

Autoscale LLM (vLLM, SGLang, LMDeploy) inferences on Kubernetes (and others)

Finetune LLMs on K8s by using Runbooks

[deprecated] AI Gateway - core infrastructure stack for building production-ready AI Applications

🐦 A open blazing-fast simple model gateway for rapid development of production GenAI apps

A diverse, simple, and secure all-in-one LLMOps platform

🧯 Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.

Easy and simple AI-first fullstack app builder. Closed-loop WEB and API framework using local LLM, offline/online, RAG and Agentic. Includes simple graph-based orchestration workflow. All compiles and builds a Docker container.

Sister project to OpenLLMetry, but in Go. Open-source observability for your LLM application, based on OpenTelemetry

The reliability layer between your code and LLM providers.

专注在智能运维、自动化运维、Zabbix、Prometheus、Grafana、Nagios、ELK Stack（Elasticsearch、Logstash、Kibana）、Graylog、Ansible、SaltStack、Puppet、Chef、Terraform、Docker、Kubernetes、OpenShift、Jenkins、MySQL、PostgreSQL、MariaDB、Redis、MongoDB、InfluxDB、Ceph、MinIO，RabbitMQ、Kafka、NATS、Apache Pulsar、Nginx、Apache HTTP Server、HAProxy、Traefik、Caddy、OpenStack、OpenLDAP、FreeRDP等多个领域。

Aegis is an LLM-powered AI cluster autonomous operations system, focused on intelligent capabilities such as Fault Diagnosis, Self-healing, Root Cause Analysis, Cluster Inspection, and Alert Optimization.

SDK to integrate Maxim in your Go app.

Honey Hive Go SDK

A self-hosted, open-source (Apache 2.0) proxy for LLM's with prometheus metrics