Starred repositories
A framework for building realtime voice AI agents 🤖🎙️📹
Cloud Native Agentic AI | Discord: https://bit.ly/kagentdiscord
Agent Development Kit Web (adk web) is the built-in developer UI that is integrated with Agent Development Kit for easier agent development and debugging.
Python middleware bridging Google ADK agents with AGUI protocol via Server-Sent Events for real-time agent interactions
The CLI and skills that turn any coding assistant into an expert at creating, evaluating, and deploying AI agents on Google Cloud.
Port of the [official Python SDK](https://github.com/anthropics/claude-agent-sdk-python) to Go
A framework for building, orchestrating and deploying AI agents and multi-agent workflows with support for Go.
Go utilities for Google ADK. It includes LLM clients, storage for sessions and memory, context compaction, artifacts and more!
A Go framework for building production agent systems with graph workflows, tools, memory, A2A, AG-UI, MCP, evaluation, and observability.
High Performance Web Platform Based on Nginx and LuaJIT
A constant throughput, correct latency recording variant of wrk
Benchmarks of approximate nearest neighbor libraries in Python
Minimal templating on steroids.
Cloud provider for KIND clusters
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Build distributed, production-grade, long-running agents.
Fast and easy to use database for traces, which can efficiently handle terabytes of trace spans.
Fast and easy to use database for logs, which can efficiently handle terabytes of logs
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and…
A lightweight, powerful framework for multi-agent workflows in Go
OpenWiki is a CLI that writes and maintains agent documentation for your codebase.
Unofficial Go SDK for Open AI. A lightweight, powerful framework for multi-agent workflows.
An open-source, code-first Go toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.
AI agents in Go — Temporal for durable, crash-resilient execution or run in-process with zero setup. OpenAI, Anthropic, Gemini, Deepseek, Ollama, tools, MCP, A2A, RAG, memory, conversations, AG-UI,…
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.