Search Results for "feedback" - Page 3
Sort By:
Showing 152 open source projects for "feedback"
View related business solutions-
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.
-
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
1
Reflexion
Reflexion: Language Agents with Verbal Reinforcement Learning
Reflexion is a research-oriented AI framework that focuses on improving the reasoning and problem-solving capabilities of language model agents through iterative self-reflection and feedback loops. Instead of relying solely on a single-pass response, Reflexion enables agents to evaluate their own outputs, identify errors, and refine their reasoning over multiple iterations, leading to more accurate and reliable results. The framework introduces a mechanism where agents maintain a memory of past attempts and use that memory to guide future decisions, effectively simulating a learning process without requiring traditional model retraining. ... -
2
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... -
3
SteadyDancer
Harmonized and Coherent Human Image Animation
...By differentiating between intentional rhythmic motion and unintentional instability, SteadyDancer applies adaptive filtering that enhances video quality without flattening the core movement dynamics. The system can be used both in preprocessing pipelines for content creators and in live feedback loops for performers, giving dancers and videographers a tool to refine their visual outputs. It supports integration with standard video formats and includes customizable parameters so users can tune stabilization aggressiveness. -
4
Agentic Data Scientist
An end-to-end Data Scientist
Agentic Data Scientist is an experimental AI-driven research framework that orchestrates data science workflows through autonomous agents that can reason, plan, and execute complex analytics tasks. Unlike traditional scripted pipelines, this project lets AI agents break down high-level research goals into sub-tasks such as data acquisition, cleaning, modeling, evaluation, and reporting, with minimal human direction. Each agent is designed to independently call functions, interact with data... -
Enterprise-grade ITSM, for every businessFreshservice is an intuitive, AI-powered platform that helps IT, operations, and business teams deliver exceptional service without the usual complexity. Automate repetitive tasks, resolve issues faster, and provide seamless support across the organization. From managing incidents and assets to driving smarter decisions, Freshservice makes it easy to stay efficient and scale with confidence.
-
5
Atropos
Language Model Reinforcement Learning Environments frameworks
...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. -
6
SWE-agent
SWE-agent takes a GitHub issue and tries to automatically fix it
...On the SWE-bench, the SWE-agent resolves 12.47% of issues, achieving state-of-the-art performance on the full test set. We accomplish our results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, and view, edit, and execute code files. We call this an Agent-Computer Interface (ACI). -
7
PKU Beaver
Constrained Value Alignment via Safe Reinforcement Learning
PKU Beaver is an open-source research project focused on improving the safety alignment of large language models through reinforcement learning from human feedback under explicit safety constraints. The framework introduces techniques that separate helpfulness and harmlessness signals during training, allowing models to optimize for useful responses while minimizing harmful behavior. To support this process, the project provides datasets containing human-labeled examples that encode both performance preferences and safety constraints across multiple dimensions. ... -
8
AgentHandover
AgentHandover observes, learns and teaches agents with skills
...The project supports both focused recording for specific tasks and passive discovery for workflows that appear repeatedly over time. It stores learned knowledge locally and uses feedback from later executions to improve confidence, add decision branches, and demote stale or failing skills. Its main value is helping agents learn how a person actually works, so recurring tasks can be handed off with more context, consistency, and trust. -
9
BlenderMCP
Blender Model Context Protocol Integration
BlenderMCP is a bridge that connects Blender, a 3D modeling and rendering software, with AI systems like Claude through the Model Context Protocol, enabling direct AI-driven interaction with 3D environments. It allows users to control Blender using natural language prompts, effectively turning AI into a co-creator for 3D modeling, scene construction, and asset manipulation. The system establishes a two-way communication channel between Blender and the AI, where commands can be sent and... -
Compliant and Reliable File Transfers Backed by Top Security CertificationsStop relying on non-certified, legacy file transfer tools that creak under the weight of modern security demands. Get full audit trails, advanced access controls and more supported by an award-winning team of experts. Start your free 25-day trial today.
-
10
verl-agent
Designed for training LLM/VLM agents via RL
...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. Developers can configure memory modules that determine how historical information is stored and incorporated into each step of the reasoning process. -
11
RLHF-Reward-Modeling
Recipes to train reward model for RLHF
RLHF-Reward-Modeling is an open-source research framework focused on training reward models used in reinforcement learning from human feedback for large language models. In RLHF pipelines, reward models are responsible for evaluating generated responses and assigning scores that guide the model toward outputs that better match human preferences. The repository provides training recipes and implementations for building reward and preference models using modern machine learning frameworks. ... -
12
PRIME
Scalable RL solution for advanced reasoning of language models
PRIME is an open-source reinforcement learning framework designed to improve the reasoning capabilities of large language models through process-level rewards rather than relying only on final outputs. The system introduces the concept of process reinforcement through implicit rewards, allowing models to receive feedback on intermediate reasoning steps instead of evaluating only the final answer. This approach helps models learn better reasoning strategies and encourages them to generate more reliable multi-step solutions to complex tasks. PRIME provides training pipelines, datasets, and experimental infrastructure that allow researchers to train models with reinforcement learning tailored for reasoning improvement. ... -
13
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
...The benchmark includes multiple environments that simulate realistic scenarios such as web interaction, database querying, and problem solving tasks. These environments require agents to interpret instructions, take actions, and adapt their strategies based on feedback from the environment. AgentBench also includes an evaluation framework that measures success rates, rewards, and task completion performance across different agent implementations. By testing models across diverse scenarios, the benchmark highlights strengths and weaknesses in reasoning, long-term planning, and tool usage. -
14
The Alignment Handbook
Robust recipes to align language models with human and AI preferences
...It provides detailed training recipes that explain how to perform tasks such as supervised fine-tuning, preference modeling, and reinforcement learning from human feedback. The handbook also includes reproducible workflows for training instruction-following models and evaluating alignment quality across different datasets and benchmarks. One of its goals is to bridge the gap between academic research on alignment methods and practical engineering implementation. -
15
CUDA Agent
Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
...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. ... -
16
Agent Reinforcement Trainer
Train multi-step agents for real-world tasks using GRPO
...Instead of just manually crafting prompts or relying on supervised fine-tuning, ART uses techniques like Group Relative Policy Optimization (GRPO) to let agents learn from environmental feedback and reward signals. 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. -
17
Acontext
Context data platform for building observable, self-learning AI agents
...It provides a unified system to store and manage contexts, multimodal messages, artifacts, and task workflows, enabling developers to engineer context effectively for their agent products. The platform observes agent tasks and user feedback in real time, offering robust observability into workflows and helping teams understand how agents perform over time. Acontext also supports agent self-learning by distilling structured skills and experiences from previously completed tasks, which can later be reused or searched to improve future performance. It includes tools to interact with session data, background agents that monitor progress, and a dashboard that visualizes success rates, artifacts, and learned skills. ... -
18
fairseq2
FAIR Sequence Modeling Toolkit 2
...Built from the ground up for scalability, composability, and research flexibility, fairseq2 supports a broad range of language, speech, and multimodal content generation tasks, including instruction fine-tuning, reinforcement learning from human feedback (RLHF), and large-scale multilingual modeling. Unlike the original fairseq—which evolved into a large, monolithic codebase—fairseq2 introduces a clean, plugin-oriented architecture designed for long-term maintainability and rapid experimentation. It supports multi-GPU and multi-node distributed training using DDP, FSDP, and tensor parallelism, capable of scaling up to 70B+ parameter models. ... -
19
Super-Linter
Combination of multiple linters to install as a GitHub Action
...It works best when commits are being pushed early and often to a branch with an open or draft pull request. There is some desire to move this closer to local development for faster feedback on linting errors but this is not yet supported. There is no need to set the GitHub Secret as it is automatically set by GitHub, it only needs to be passed to the action. -
20
MLJAR Studio
Python package for AutoML on Tabular Data with Feature Engineering
...It is a notebook-based development environment with interactive code recipes and a managed Python environment. All running locally on your machine. We are waiting for your feedback. The mljar-supervised is an Automated Machine Learning Python package that works with tabular data. It is designed to save time for a data scientist. It abstracts the common way to preprocess the data, construct the machine learning models, and perform hyper-parameter tuning to find the best model. It is no black box, as you can see exactly how the ML pipeline is constructed (with a detailed Markdown report for each ML model). -
21
AWS IoT Device SDK for Python
SDK for connecting to AWS IoT from a device using Python
...By connecting their devices to AWS IoT, users can securely work with the message broker, rules, and the device shadow (sometimes referred to as a thing shadow) provided by AWS IoT and with other AWS services like AWS Lambda, Amazon Kinesis, Amazon S3, and more. It is a complete rework, built to improve reliability, performance, and security. We invite your feedback! The SDK is built on top of a modified Paho MQTT Python client library. Developers can choose from two types of connections to connect to AWS IoT. For MQTT over TLS (port 8883 and port 443), a valid certificate and a private key are required for authentication. For MQTT over the WebSocket protocol (port 443), a valid AWS Identity and Access Management (IAM) access key ID and secret access key pair are required for authentication. -
22
MedicalGPT
MedicalGPT: Training Your Own Medical GPT Model with ChatGPT Training
MedicalGPT training medical GPT model with ChatGPT training pipeline, implementation of Pretraining, Supervised Finetuning, Reward Modeling and Reinforcement Learning. MedicalGPT trains large medical models, including secondary pre-training, supervised fine-tuning, reward modeling, and reinforcement learning training. -
23
code-act
Official Repo for ICML 2024 paper
code-act is a research framework for building intelligent language-model agents that interact with their environment through executable code actions. The system proposes a unified action representation where language models produce Python code that can be executed directly, allowing the model to interact with external tools and environments in a structured way. By integrating a Python interpreter with the agent architecture, the system enables the agent to execute code, observe the results,... -
24
OpenPiano — Virtual Piano for Windows
Desktop piano playable with a PC keyboard, mouse, or MIDI device.
OpenPiano is a Windows desktop piano application that allows you to play, practice, and record music using your PC keyboard, mouse, or a MIDI device. It supports real-time playback using SoundFonts and provides on-screen piano layouts for visual feedback while playing. OpenPiano is designed to run entirely locally. It does not require accounts, cloud services, or an internet connection for core functionality. Project links: Website: https://www.justagwas.com/projects/openpiano GitHub: https://github.com/Justagwas/openpiano Documentation: https://github.com/Justagwas/openpiano/wiki The application is fully open source. ... -
25
YT Music Downloader
A free and open-source tool to download YouTube videos or playlists as
YT Music Downloader is a free and open-source Python application that allows users to download YouTube videos or full playlists and automatically convert them into high-quality MP3 files. It features a clean and beginner-friendly GUI, works offline, and is packaged with an installer for Windows. Built using pytubefix, moviepy, FFmpeg, and Tkinter.
