Search Results for "asynchronous"
Sort By:
Showing 47 open source projects for "asynchronous"
View related business solutions-
$300 Free Credits to Build on Google CloudPut your $300 in credit toward real workloads, then keep building with free monthly usage for 20+ products. No commitment and no charge until you upgrade.
-
Build Agents and Models on One PlatformGemini Enterprise Agent Platform is Google Cloud's comprehensive platform for developers to build, scale, govern, and optimize agents and models. Choose from Google's most advanced models and third-party models like Anthropic's Claude Model Family.
-
1
AIOGram
Framework for Telegram Bot API written in Python 3.7 with asyncio
aiogram is modern and fully asynchronous framework for Telegram Bot API written in Python with asyncio and aiohttp. It helps you to make your bots faster and simpler. Is a pretty simple and fully asynchronous framework for Telegram Bot API written in Python 3.7 with asyncio and aiohttp. -
2
NoneBot
Asynchronous multi-platform robot framework written in Python
Use NB-CLI to quickly build your own robot. Plug-in development, modular management. Supports multiple platforms and multiple incident response methods. Asynchronous priority development to improve operational efficiency. Simple and clear dependency injection system, built-in dependency functions reduce user code. NoneBot2 is a modern, cross-platform, and extensible Python chatbot framework. It is based on Python's type annotations and asynchronous features, and can provide convenient and flexible support for your needs. ... -
3
TwitchIO
An Async Bot/API wrapper for Twitch made in Python
A fully asynchronous Python IRC, API, EventSub and PubSub library for Twitch. Full asynchronous design. Covers 100% of the Twitch API. IRC Commands extension for creating powerful chatbots. EventSub and PubSub support. Helper extensions for Music/Sounds and Background Tasks. Object-orientated design with stateful objects. TwitchIO is an asynchronous Python wrapper around the Twitch API and IRC, with a powerful command extension for creating Twitch Chat Bots. -
4
RealtimeSTT
A robust, efficient, low-latency speech-to-text library
RealtimeSTT is a Python-based realtime speech-to-text engine emphasizing low latency, wake-word detection, voice activity detection, and automatic speech segmentation. It provides asynchronous callbacks, nanosecond-precision timestamps, and CLI tools, suitable for building voice assistants, meeting transcribers, or live caption systems. -
MongoDB Atlas runs apps anywhereMongoDB Atlas gives you the freedom to build and run modern applications anywhere—across AWS, Azure, and Google Cloud. With global availability in over 115 regions, Atlas lets you deploy close to your users, meet compliance needs, and scale with confidence across any geography.
-
5
OpenAI Python
The official Python library for the OpenAI API
The OpenAI Python library provides convenient access to the OpenAI REST API from any Python 3.7+ application. The library includes type definitions for all request params and response fields, and offers both synchronous and asynchronous clients powered by httpx. -
6
MCP Agent Mail
Asynchronous coordination layer for AI coding agents
MCP Agent Mail is an asynchronous coordination service for teams of AI coding agents working on the same software. It gives each agent a persistent identity, inbox, outbox, searchable history, and threaded Markdown conversations. Agents can send decisions, status updates, images, and attachments without relying on a human to relay context between parallel sessions. -
7
Anthropic SDK Python
Provides convenient access to the Anthropic REST API from any Python 3
...The SDK supports both synchronous and asynchronous usage (via async/await) depending on context. Importantly, it also supports streaming responses via Server-Sent Events (SSE) so that large outputs can be consumed incrementally rather than waiting for the full response. The client offers helper abstractions for tools (function-style “tools”) and streaming utilities for building interactive agents. -
8
AReal
Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible
AReaL is an open source, fully asynchronous reinforcement learning training system. AReal is designed for large reasoning and agentic models. It works with models that perform reasoning over multiple steps, agents interacting with environments. It is developed by the AReaL Team at Ant Group (inclusionAI) and builds upon the ReaLHF project. Release of training details, datasets, and models for reproducibility. -
9
slime LLM
slime is an LLM post-training framework for RL Scaling
...It offers a flexible architecture that connects high-throughput training (e.g., via Megatron-LM) with a customizable data generation pipeline, enabling researchers and engineers to iterate on new RL training paradigms effectively. The framework is designed to support a wide range of training modes, allowing both synchronous and asynchronous RL workflows and programmable rollout interfaces that simplify experimentation with custom environments and reward signals. Because it integrates tightly with SGLang and other training engines, slime can improve scalability and efficiency while providing maintainability and adaptability for developing new models and training algorithms. -
Save Up to 91% on Cloud Compute With Spot VMsRun batch jobs at 60-91% off with Spot VMs. Long-running workloads get automatic discounts with sustained use.
-
10
Gemini-API
Reverse-engineered Python API for Google Gemini web app
Gemini-API is a community-created asynchronous Python wrapper for the web interface of Google’s Gemini models (formerly Bard). It is the result of reverse-engineering the Gemini web app and exposing its functionality through a programmatic API. This enables developers to incorporate Gemini into Python applications, scripts, bots, or tools without relying solely on official SDKs. -
11
Cosmos-RL
Cosmos-RL is a flexible and scalable Reinforcement Learning framework
Cosmos-RL is a scalable reinforcement learning framework designed specifically for physical AI systems such as robotics, autonomous agents, and multimodal models. It provides a distributed training architecture that separates policy learning and environment rollout processes, enabling efficient and asynchronous reinforcement learning at scale. The framework supports multiple parallelism strategies, including tensor, pipeline, and data parallelism, allowing it to leverage large GPU clusters effectively. It is built with compatibility in mind, supporting popular model families such as LLaMA, Qwen, and diffusion-based world models, as well as integration with Hugging Face ecosystems. cosmos-rl also includes support for advanced RL algorithms, low-precision training, and fault-tolerant execution, making it suitable for large-scale production workloads. -
12
Atropos
Language Model Reinforcement Learning Environments frameworks
...Designed as a scalable ecosystem of environment microservices, Atropos allows researchers and developers to collect, evaluate, and manage trajectories (sequences of actions and outcomes) generated by LLMs across a variety of tasks—from static dataset benchmarks to dynamic interactive games and real-world scenario environments. It provides foundational tooling for asynchronous RL loops where environment services communicate with trainers and inference engines, enabling complex workflow orchestration in distributed and parallel setups. This framework facilitates experimentation with RLHF (Reinforcement Learning from Human Feedback), RLAIF, or multi-turn training approaches by abstracting environment logic, scoring, and logging into reusable components. -
13
edge-tts
Use Microsoft Edge's online text-to-speech service from Python
...It also supports generating subtitle files (such as SRT or VTT) alongside the speech, which is handy for video narration, e-learning, or accessibility workflows. From the CLI you can adjust parameters such as speaking rate, volume, and pitch, giving you some control over prosody without diving into SSML. The library is asynchronous under the hood, which makes it efficient for batch jobs or web services that need to synthesize many utterances concurrently. -
14
ComfyUI
The most powerful and modular diffusion model GUI, api and backend
The most powerful and modular diffusion model is GUI and backend. This UI will let you design and execute advanced stable diffusion pipelines using a graph/nodes/flowchart-based interface. We are a team dedicated to iterating and improving ComfyUI, supporting the ComfyUI ecosystem with tools like node manager, node registry, cli, automated testing, and public documentation. Open source AI models will win in the long run against closed models and we are only at the beginning. Our core mission... -
15
Groq Python
The official Python Library for the Groq API
...The SDK handles authentication (via environment variable or parameter), defines proper type-safe request/response data types, and supports both synchronous and asynchronous usage patterns depending on your application needs. This makes it easy to integrate Groq-powered AI capabilities into backend services, data pipelines, research notebooks, or applications written in Python. For those building AI-based tooling, automation scripts, or ML-backed backends, groq-python abstracts away HTTP request plumbing and exposes a clean API, accelerating development and reducing boilerplate. -
16
Meta-World
Collections of robotics environments
...It also offers meta-learning benchmarks (ML1, ML10, ML45) that evaluate few-shot adaptation to new goals or entirely new tasks. The environments adhere to the Gymnasium API, which makes them easy to plug into existing RL pipelines, and they support both synchronous and asynchronous vectorized execution for running many environments in parallel. Installation is done via pip, with official support for Python versions 3.8 through 3.11 on Linux and macOS, and the project is licensed under MIT to encourage broad academic and industry use. -
17
Solace Agent Mesh
An event-driven framework designed to build multi-agent AI systems
...It addresses one of the main challenges in modern AI systems, which is connecting isolated agents, data sources, and enterprise systems into a cohesive and interoperable ecosystem. The framework uses an asynchronous messaging architecture powered by an event broker, enabling agents to communicate reliably without tight coupling, which significantly improves scalability and fault tolerance. It introduces a standardized agent-to-agent communication protocol that allows different agents, regardless of their implementation or location, to exchange tasks, share data, and coordinate workflows efficiently. ... -
18
OAGI Python SDK
Python SDK for the Computer Use model Lux, developed by OpenAGI
...The SDK is designed around “computer use” as a paradigm, where the AI actually navigates interfaces, clicks, types, scrolls, and reads the screen through screenshots instead of only calling APIs. It provides high-level asynchronous agents (like AsyncDefaultAgent and AsyncActor) that encapsulate the loop of capturing screenshots, sending them to Lux, interpreting responses, and executing UI actions with PyAutoGUI. Multiple installation flavors let you choose between a minimal oagi-core package or variants that bundle desktop automation and FastAPI/Socket.IO server capabilities. -
19
DeerFlow
Deep Research framework, combining language models with tools
...“planner,” “searcher,” “coder,” “report generator”) that collaborate in a structured workflow, allowing tasks like literature reviews, data gathering, data analysis, code execution, and final report generation to be largely automated. It supports asynchronous task coordination, modular tool integration, and orchestrates the data flow between agents — making it suitable for large-scale or multi-stage research pipelines. Users can deploy it locally or on server infrastructure, integrate custom tools, and benefit from its flexible configuration. -
20
SimpleLLM
950 line, minimal, extensible LLM inference engine built from scratch
SimpleLLM is a minimal, extensible large language model inference engine implemented in roughly 950 lines of code, built from scratch to serve both as a learning tool and a research platform for novel inference techniques. It provides the core components of an LLM runtime—such as tokenization, batching, and asynchronous execution—without the abstraction overhead of more complex engines, making it easier for developers and researchers to understand and modify. Designed to run efficiently on high-end GPUs like NVIDIA H100 with support for models such as OpenAI/gpt-oss-120b, Simple-LLM implements continuous batching and event-driven inference loops to maximize hardware utilization and throughput. ... -
21
Appfl
Advanced Privacy-Preserving Federated Learning framework
APPFL (Advanced Privacy-Preserving Federated Learning) is a Python framework enabling researchers to easily build and benchmark privacy-aware federated learning solutions. It supports flexible algorithm development, differential privacy, secure communications, and runs efficiently on HPC and multi-GPU setups. -
22
Open SWE
Open source async coding agent that plans, codes, and opens PRs
Open SWE is an open source asynchronous coding agent designed to automate software engineering workflows across entire repositories. Built with LangGraph, it can understand a codebase, generate a structured plan, and execute code changes from start to finish without constant human intervention. It operates in a cloud-based environment where tasks are processed asynchronously, allowing multiple coding jobs to run in parallel in isolated sandboxes. -
23
FullTClash
General proxy performance testing tool based on Clash using Telegram
Back end part useClash project(It can also be called nowmihomo)The relevant code is used as the outing agent. The front end part uses Telegram API as the interactive interface, which needs to be used in conjunction with Telegram, that is, a Telegram robot (bot), FullTClash bot is a Telegram robot (hereinafter referred to as bot) carrying its test tasks. -
24
LlamaDeploy
Deploy your agentic worfklows to production
llama_deploy is an open-source framework designed to simplify the deployment and productionization of agent-based AI workflows built with the LlamaIndex ecosystem. The project provides an asynchronous architecture that allows developers to deploy complex multi-agent workflows as scalable microservices. It enables teams to move from experimental prototypes to production systems with minimal changes to existing LlamaIndex code, making it easier to operationalize AI agents. The system supports orchestrating multiple services, handling communication between agents, and managing workflow execution in distributed environments. ... -
25
Matrix
Multi-Agent daTa geneRation Infra and eXperimentation framework
Matrix is a distributed, large-scale engine for multi-agent synthetic data generation and experiments: it provides the infrastructure to run thousands of “agentic” workflows concurrently (e.g. multiple LLMs interacting, reasoning, generating content, data-processing pipelines) by leveraging distributed computing (like Ray + cluster management). The idea is to treat data generation as a “data-to-data” transformation: each input item defines a task, and the runtime orchestrates asynchronous, peer-to-peer agent workflows, avoiding global synchronization bottlenecks. That design makes Matrix particularly well-suited for large-batch inference, model benchmarking, data curation, augmentation, or generation — whether for language, code, dialogue, or multimodal tasks. It supports both open-source LLMs and proprietary models (via integration with model backends), and works with containerized or sandboxed environments for safe tool execution or external code runs.
