Search Results for "feedback" - Page 8
Sort By:
Showing 762 open source projects for "feedback"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
$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
AWS IoT SDK for JavaScript
SDK for connecting to AWS IoT from a device using JavaScript/Node.js
A new AWS IoT Device SDK is now available. It is a complete rework, built to improve reliability, performance, and security. We invite your feedback! The aws-iot-device-sdk.js package allows developers to write JavaScript applications that access the AWS IoT Platform via MQTT or MQTT over the Secure WebSocket Protocol. It can be used in Node.js environments as well as in-browser applications. This package is built on top of mqtt.js and provides three classes: 'device', 'thingShadow' and 'jobs'. ... -
2
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. -
3
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... -
4
Naive UI
A Vue 3 Component Library. Fairly Complete. Theme Customizable
Naive UI is a comprehensive component library built specifically for Vue 3, designed to provide a large set of ready-to-use UI components with strong TypeScript integration and modern performance optimizations. The library includes more than 90 components covering a wide range of interface needs such as forms, data displays, navigation elements, and feedback components, allowing developers to build complex applications efficiently. It is fully written in TypeScript, ensuring type safety and seamless integration with TypeScript-based projects. One of its defining characteristics is its advanced theming system, which allows developers to customize the appearance of components without relying on traditional CSS preprocessors or configuration-heavy setups. ... -
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.
-
5
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. -
6
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. ... -
7
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. ... -
8
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. -
9
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. -
Stop Cyber Threats with VM-Series Next-Gen Firewall on AzureGain integrated visibility across all traffic in a single pass. Deploy Palo Alto Networks VM-Series to determine application identity and content while automating security policy updates via rich APIs.
-
10
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. ... -
11
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. -
12
Interface Design
Design engineering for Claude Code
...The plugin prompts users to confirm a design direction early in the process and then applies those principles consistently — from button sizes to spacing scales and color tokens — so work stays aligned with the established system. It also offers commands to inspect the current design system status, audit inconsistencies, and extract patterns back into a reusable format, making it a live feedback loop for quality UI work. -
13
OCRBase
MD/.JSON Document OCR and structured data extraction API
...The core output is designed for downstream automation, producing structured results like JSON according to user-defined schemas while also providing readable formats like Markdown for human review or indexing. It includes real-time job progress updates via WebSockets, which makes it easier to integrate into UIs, dashboards, or ingestion systems where users need feedback on long-running document processing. -
14
JSCamp InfoJobs
Content and exercises fromJSCamp InfoJobs
...The repo also links to jscamp.dev, where the videos and course materials are hosted, and explains that access is free, with an optional paid certificate that includes extra support like CV review, exercise feedback, and exclusive workshops. Detailed installation requirements are listed (modern browser, VS Code, Live Preview extension, Node.js 20+, Git, Docker, etc. -
15
vue2-elm
Large single page application with 45 pages built on vue2 + vuex
...The project illustrates how to organize a medium-sized SPA, including how to split features into reusable pieces and handle asynchronous data. It places strong emphasis on responsive UI, transitions, and user feedback patterns that feel app-like on mobile devices. Developers can study API consumption patterns and mock data handling to simulate real production constraints. As a learning resource, it gives a practical playground for debugging, performance considerations, and code readability in a real-world scale example -
16
Node.js Testing Best Practices
Beyond the basics of Node.js testing
...It covers API testing, contract testing, and persistence-layer strategies that avoid coupling tests to fragile implementation details. The material explains how to structure tests around process boundaries—HTTP, queues, cron jobs—while keeping fast feedback cycles through selective integration tests and reliable test doubles. It dives into topics like test containers, ephemeral databases, and idempotent fixtures to ensure deterministic runs in CI. Observability is treated as part of testing: logs, metrics, and tracing make failures diagnosable instead of mysterious. By aligning tests with service responsibilities instead of internal modules, the guide helps teams produce suites that reflect real production behavior. -
17
test.vim
Run your tests at the speed of thought
...Output can be shown in splits, quickfix, or dispatched to external runners, and it integrates smoothly with asynchronous job systems for non-blocking runs. You can configure custom strategies to run tests via terminal, tmux panes, Neovim terminals, or background dispatchers. Its design encourages tight feedback loops, making test-driven workflows natural in Vim. -
18
type-challenges
Collection of TypeScript type challenges with online judge
...Problems are arranged from warm-ups to brain-twisters, letting developers build intuition about distributive conditional types, inference in extends, variance, and other corner cases of the type system. The repository includes tests for each puzzle so you get immediate, compiler-driven feedback when your solution is correct. As a result, it doubles as both training material and a living reference for advanced patterns used in real libraries. Many engineers report that solving a handful of these dramatically improves their ability to write safe, expressive APIs with minimal runtime overhead. -
19
Visual Blocks
Visual Blocks for ML is a Google visual programming framework
Visual Blocks is a node-based, in-browser environment for building AI and data-processing workflows with drag-and-drop components. It lets you connect sources, transforms, models, and visualizers into a live graph, so changes propagate instantly and results are observable without writing glue code. Under the hood it leans on web-friendly runtimes (e.g., WebGPU/WebGL/WebNN or TensorFlow.js backends) to execute pipelines locally, which is great for demos, teaching, and privacy-sensitive... -
20
Elixir Code Smells
Catalog of Elixir-specific code smells
...The smells are grouped into two categories: design-related (coarse-grained, harder to detect, affecting architecture/processes) and low-level concerns (fine-grained, often readability and maintainability issues). The catalog evolves with community feedback and contributions, aiming to help developers recognize harmful patterns and apply disciplined refactoring to improve maintainability, testability, and performance in Elixir systems. -
21
DoKit
A platform for the life cycle of pan-front-end product development
...Developers can interactively explore UI layouts, measure layout times, simulate slow networks, or trace touch events—all while the app is running on the device. DoKit aims to shorten feedback loops by surfacing internal state and metrics in situ rather than relying solely on external logging or tooling. Because it’s modular, teams can include only the subsystems relevant to their needs and disable others in production builds. The result is a rich, on-device observability layer that supports debugging performance, layout bug hunts, and UX tuning without deeply invasive instrumentation. -
22
Gradle Lint Plugin
Linter tool for identifying and reporting on patterns of misuse
...The plugin supports custom rules and can even automatically fix certain violations (e.g. unused dependencies) via a fixGradleLint task. Because it hooks into the end of many Gradle tasks, it can catch issues as part of a normal build workflow, making feedback immediate. -
23
BCC (BPF Compiler Collection)
Tools for BPF-based Linux IO analysis, networking, monitoring, etc.
...It is suited for many tasks, including performance analysis and network traffic control. With a BPF-specific frontend, one should be able to write in a language and receive feedback from the compiler on the validity as it pertains to a BPF backend. This toolkit aims to provide a frontend that can only create valid BPF programs while still harnessing its full flexibility. -
24
Opik
Debug, evaluate, and monitor your LLMapps, RAG systems, and agentic AI
Confidently evaluate, test, and monitor LLM applications. Opik is an open-source platform for evaluating, testing, and monitoring LLM applications. Built by Comet. Record, sort, search, and understand each step your LLM app takes to generate a response. Manually annotate, view, and compare LLM responses in a user-friendly table. Log traces during development and in production. Run experiments with different prompts and evaluate against a test set. Choose and run pre-configured evaluation... -
25
Platypus
Create native Mac applications from command line scripts
Platypus is a developer tool that creates native Mac applications from command line scripts such as shell scripts or Python, Perl, Ruby, Tcl, JavaScript, and PHP programs. This is done by wrapping the script in an application bundle along with a slim app binary that runs the script. Platypus makes it easy to share scripts and programs with people who are unfamiliar with the command line interface. Native, user-friendly applications can be created with a few clicks. It is very easy to create...
