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…

Get started using Deepgram's Voice Agent with this Next.js demo app

Profile-Based Long-Term Memory for AI Applications. Memobase handles user profiles, memory events, and evolving context — perfect for chatbots, companions, tutors, customer service bots, and all ch…

All-in-one TypeScript Platform for Startups

MemOS (Preview) | Intelligence Begins with Memory

What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers?

Make text LLMs listen and speak

End-to-end stack for WebRTC. SFU media server and SDKs.

Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

Sample application to add voice capabilities to the Agents SDK

Fullstack app framework for web, desktop, and mobile.

Demo of a customer service use case implemented with the OpenAI Agents SDK

MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.

This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.

The most comprehensive authentication framework for TypeScript

Memory for AI Agents in 5 lines of code

The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, self-hosted AI workflows.

Fully Local Manus AI. No APIs, No $200 monthly bills. Enjoy an autonomous agent that thinks, browses the web, and code for the sole cost of electricity.

An AI Hedge Fund Team

A new bootable USB solution.

Collection of leaked system prompts

Memory for AI Agents; SOTA in AI Agent Memory, beating OpenAI Memory in accuracy by 26% - https://mem0.ai/research

ACI.dev is the open source platform that connects your AI agents to 600+ tool integrations with multi-tenant auth, granular permissions, and access through direct function calling or a unified MCP …

Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.

AI-powered multi-agent builder

A TTS model capable of generating ultra-realistic dialogue in one pass.

Model Context Protocol Servers

🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / DeepSeek / Qwen), Knowledge Base (file upload / knowledge managemen…