Search Results for "training"
Sort By:
Showing 37 open source projects for "training"
View related business solutions-
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.
-
Full-stack observability with actually useful AI | Grafana CloudBuilt on open standards like Prometheus and OpenTelemetry, Grafana Cloud includes Kubernetes Monitoring, Application Observability, Incident Response, plus the AI-powered Grafana Assistant. Get started with our generous free tier today.
-
1
autoresearch
AI agents autonomously run and improve ML experiments overnight
autoresearch is an experimental framework that enables AI agents to autonomously conduct machine learning research by iteratively modifying and training models. Created by Andrej Karpathy, the project allows an agent to edit the model training code, run short experiments, evaluate results, and repeat the process without human intervention. Each experiment runs for a fixed five-minute training window, enabling rapid iteration and consistent comparison across architectural or hyperparameter changes. ... -
2
OpenClaw-RL
Train any agents simply by 'talking'
...The system incorporates reinforcement learning techniques to refine the agent’s policies for tool use, decision making, and task completion over time. It also explores approaches such as online policy distillation and hindsight feedback signals to strengthen training signals from real interactions. The framework operates asynchronously and does not require external API keys, making it easier to experiment with local agent training workflows. -
3
rLLM
Democratizing Reinforcement Learning for LLMs
...The project is designed to support large-scale language models (including support for big models via integrated training backends), making it relevant for state-of-the-art research and production use. The framework includes tools for defining workflows, specifying objectives or reward functions, and managing training/policy updates across possibly distributed settings. -
4
Agent Reinforcement Trainer
Train multi-step agents for real-world tasks using GRPO
...The framework is designed to integrate easily with Python applications, abstracting much of the RL infrastructure so developers can train agents without deep RL expertise or heavy infrastructure overhead. ART also supports scalable training patterns, observability tools, and integration with hosted platforms like Weights & Biases, and it provides notebooks that demonstrate training on standard benchmarks and tasks. -
Go From AI Idea to AI App FastAccess Gemini 3 and 200+ models. Build chatbots, agents, or custom models with built-in monitoring and scaling.
-
5
AWorld
Build, evaluate and train General Multi-Agent Assistance with ease
...It provides features to help and coordinate across multiple agents. It can also scale their training across environments. -
6
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
CUDA Agent is a research-driven agentic reinforcement learning system designed to automatically generate and optimize high-performance CUDA kernels for GPU workloads. The project addresses the long-standing challenge that efficient CUDA programming typically requires deep hardware expertise by training an autonomous coding agent capable of iterative improvement through execution feedback. Its architecture combines large-scale data synthesis, a skill-augmented CUDA development environment, and long-horizon reinforcement learning to build intrinsic optimization capability rather than relying on simple post-hoc tuning. The system operates in a ReAct-style loop where the agent profiles baseline implementations, writes CUDA code, compiles it in a sandbox, and iteratively refines performance. ... -
7
FinRobot
An Open-Source AI Agent Platform for Financial Analysis using LLMs
...Built with modularity in mind, FinRobot allows users to plug in custom models — from classical algorithms to deep learning architectures — and orchestrate components in pipelines that can run reproducibly across experiments. The framework also tends to include automation layers for deployment, enabling trained models to operate in live or simulated environments with scheduled re-training and risk controls in place. -
8
OpenHarness
Open Agent Harness with a built-in personal agent, Ohmo
OpenHarness is an open-source framework developed to support large-scale machine learning workflows, particularly in the context of training, evaluating, and benchmarking AI models. It provides a structured environment for orchestrating experiments, managing datasets, and standardizing evaluation processes across different models. The project focuses on reproducibility and scalability, allowing researchers and engineers to run consistent experiments while tracking results effectively. ... -
9
AppWorld
World of apps for benchmarking interactive coding agent
AppWorld is a framework developed by Stony Brook University's NLP group to simulate environments for training and evaluating dialogue agents in task-oriented applications. -
$300 in Free Credit Towards Top Cloud ServicesStart your project in minutes. After credits run out, 20+ products include free monthly usage. Only pay when you're ready to scale.
-
10
verl-agent
Designed for training LLM/VLM agents via RL
verl-agent is an open-source reinforcement learning framework designed to train large language model agents and vision-language model agents for complex interactive environments. Built as an extension of the veRL reinforcement learning infrastructure, the project focuses on enabling scalable training for agents that perform multi-step reasoning and decision-making tasks. The framework supports multi-turn interactions between agents and their environments, allowing the system to receive feedback after each step and adjust its strategy accordingly. This step-wise interaction model makes it possible to train agents to operate in long-horizon scenarios where decisions depend on cumulative context and previous outcomes. ... -
11
Agent Lightning
The absolute trainer to light up AI agents
...It’s designed to be compatible with a wide range of agent architectures and frameworks — from LangChain and OpenAI Agent SDKs to AutoGen and custom Python agents — making it broadly applicable across different agent tooling ecosystems. Agent-Lightning introduces a lightweight training pipeline that observes agents’ execution traces, converts them into structured data, and feeds them into training algorithms, enabling users to improve agent behaviors systematically. The project emphasizes minimalist integration, so you can drop this into existing systems without extensive rewrites, focusing instead on iterative performance improvement. -
12
Witsy
Witsy: desktop AI assistant
Witsy is a tool designed to assist in the development and deployment of machine learning models, providing a streamlined workflow for data scientists and engineers. -
13
Habitat-Lab
A modular high-level library to train embodied AI agents
...Configuring and instantiating a diverse set of embodied agents, including commercial robots and humanoids, specifying their sensors and capabilities. Providing algorithms for single and multi-agent training (via imitation or reinforcement learning, or no learning at all as in SensePlanAct pipelines), as well as tools to benchmark their performance on the defined tasks using standard metrics. -
14
Diplomacy Cicero
Code for Cicero, an AI agent that plays the game of Diplomacy
...Configuration is managed via protobuf files to define tasks such as self-play, benchmark agent comparisons, and RL training. The project is now archived and read-only, reflecting that it is no longer actively developed but remains publicly available for research use. -
15
IntentKit
An open and fair framework for everyone to build AI agents
IntentKit is a natural language understanding (NLU) library focused on intent recognition and entity extraction, enabling developers to build conversational AI applications. -
16
Sublayer
A model-agnostic Ruby Generative AI DSL and framework
Sublayer is a platform that enables developers to build and deploy machine learning models with ease, focusing on simplifying the ML lifecycle from development to production. -
17
JAI Workflow
Build programmatically custom agentic workflows, AI Agents, RAG system
JAI-Workflow is a framework for building and managing machine learning workflows, streamlining the process from data ingestion to model deployment. -
18
MiroThinker
MiroThinker is an open source deep research agent
MiroThinker is an open-source deep research AI agent designed to perform complex reasoning, information gathering, and predictive analysis tasks. The system focuses on enabling long-horizon research workflows by allowing the agent to interact repeatedly with external tools, search systems, and data sources while refining its reasoning through iterative steps. Rather than simply generating responses from a single prompt, the agent performs structured multi-step reasoning processes that... -
19
LiteMultiAgent
The Library for LLM-based multi-agent applications
LiteMultiAgent is a lightweight and extensible multi-agent reinforcement learning (MARL) platform designed for rapid experimentation. It allows researchers to design and test coordination, competition, and collaboration scenarios in simulated environments. -
20
AgentForge
Extensible AGI Framework
AgentForge is a framework for creating and deploying AI agents that can perform autonomous decision-making and task execution. It enables developers to define agent behaviors, train models, and integrate AI-powered automation into various applications. -
21
PilottAI
Python framework for building scalable multi-agent systems
pilottai is an AI-based autonomous drone navigation system utilizing reinforcement learning for real-time decision-making. It is designed for simulating and training drones to fly safely through dynamic environments using AI-based controllers. -
22
smolagents
Agents write python code to call tools and orchestrate other agents
This library is the simplest framework out there to build powerful agents. We provide our definition in this page, where you’ll also find tips for when to use them or not (spoilers: you’ll often be better off without agents). smolagents is a lightweight framework for building AI agents using large language models (LLMs). It simplifies the development of AI-driven applications by providing tools to create, train, and deploy language model-based agents. -
23
MetaClaw
Just talk to your agent
MetaClaw is an AI or agent-oriented system that appears to focus on advanced control, coordination, or training of autonomous agents, potentially within reinforcement learning or tool-using environments. The project likely emphasizes meta-level reasoning, where agents are not only executing tasks but also adapting their strategies based on feedback and performance signals. It may incorporate mechanisms for learning from interactions, improving decision-making over time, and generalizing across different domains. ... -
24
Microsoft Learn MCP Server
Official Microsoft Learn MCP Server, powering LLMs and AI agents
Microsoft Learn MCP Server is the official GitHub repository for the Microsoft Learn MCP (Model Context Protocol) Server, a service that implements the Model Context Protocol to provide AI assistants and tools with reliable, real-time access to Microsoft’s official documentation. Rather than relying on training data that may be outdated or incomplete, MCP servers let agents like GitHub Copilot, Claude, or other LLM-based tools search and pull context directly from up-to-date Microsoft Learn content, including Azure, .NET, and other tech docs. By connecting to the MCP endpoint, coding agents can answer questions, retrieve code examples, and offer best practices grounded in authoritative sources without requiring API keys or manual browser searches. ... -
25
RecursiveMAS
Offical Implementation for "Recursive Multi-Agent Systems"
...The system uses a lightweight module called RecursiveLink to transfer and transform latent representations between agents, enabling seamless interaction even across heterogeneous models. It also incorporates an inner–outer loop training approach that optimizes the entire system collectively rather than tuning each agent separately. This design improves efficiency, reduces token usage, and stabilizes learning during iterative reasoning.
