Awesome AI Agents › Stateful Serverless Frameworks
The DigitalOcean Agent, known as do-agent, is a system monitoring tool designed to collect and send system metrics from DigitalOcean Droplets to DigitalOcean's backend servers. This enables users to visualize resource usage through graphs and set up alerting mechanisms for better infrastructure management. The agent supports a variety of Linux distributions including Ubuntu (from the oldest LTS release still under standard support), Debian (from the oldest supported LTS release), Fedora 27 and later, CentOS 6 and later, and can also be run as a Docker container. While it is optimized for these distributions, it can operate on most Linux systems, though DigitalOcean does not provide official support for unsupported distros or versions. A notable feature for users with SELinux enabled is the requirement to set the `nis_enabled` flag to 1 to allow the agent to communicate over the network for authentication and metric transmission. The installation process is straightforward, with the agent available through DigitalOcean's monitoring checkbox during Droplet creation or via a script that can be run using curl or wget. The project also supports development with requirements including Go 1.11 or later, GNU Make, and Docker, with instructions provided for building and managing dependencies. Users can uninstall the agent using their distribution's package manager. Running the agent as a Docker container is also supported, requiring mounting of the host's `/proc` and `/sys` directories to the container for proper operation. The project encourages community involvement by inviting users to report issues on its GitHub repository. Overall, do-agent is a critical tool for DigitalOcean users to monitor their Droplet performance and maintain system health efficiently.
https://github.com/digitalocean/do-agent
LiteLLM is a Python SDK and proxy server that provides a unified OpenAI-compatible interface to call over 100 large language model APIs from multiple providers, featuring consistent output, retry logic, budget controls, and extensive observability integrations.
Flowise is an open-source drag-and-drop platform that enables users to easily build and deploy customized Large Language Model (LLM) application workflows with a user-friendly interface and flexible deployment options.
Parlant is a Conversation Modeling engine that enables precise, consistent, and reliable control over GenAI-driven conversational agents by enforcing structured behavioral guidelines and adapting dynamically to user interactions.
ToolBench is an open platform for training, serving, and evaluating large language models with advanced tool-use capabilities using a large-scale, richly annotated dataset of real-world APIs.
RivetKit is a stateful serverless framework that enables building scalable, real-time, and collaborative applications deployable across multiple platforms including Rivet, Cloudflare Workers, Bun, and Node.js.
LlamaDeploy is an async-first framework that enables seamless deployment, scaling, and productionization of agentic multi-service workflows built with llama_index, facilitating easy transition from development to cloud-based production environments.
Ragbits is a modular framework providing building blocks for rapid development, deployment, and monitoring of scalable and reliable Generative AI applications with flexible LLM integration and advanced document processing capabilities.
Mirascope is a flexible and user-friendly library that provides a unified interface to work with multiple large language model providers, simplifying AI-driven text generation and information extraction tasks.