Search Results for "human" - Page 3
Sort By:
Showing 363 open source projects for "human"
View related business solutions-
Host LLMs in Production With On-Demand GPUsDeploy your model, get an endpoint, pay only for compute time. No GPU provisioning or infrastructure management required.
-
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
pwa-asset-generator
Automates PWA asset generation and image declaration
...Automatically generates icon and splash screen images, favicons and mstile images. Updates manifest.json and index.html files with the generated images according to Web App Manifest specs and Apple Human Interface guidelines. When you build a PWA with a goal of providing native-like experiences on multiple platforms and stores, you need to meet with the criteria of those platforms and stores with your PWA assets; icon sizes and splash screens. Google's Android platform respects Web App Manifest API specs, and it expects you to provide at least 2 icon sizes in your manifest file. ... -
2
security-audit
A coding-agent skill for multi-phase security audits
...The workflow begins with reconnaissance, then moves into parallel hunting across attack classes such as injection, access control, business logic, cryptography, feature abuse, and chained attacks. Findings are then challenged through separate validation agents to reduce false positives. The skill produces human-readable reports, detailed finding traces, structured JSON output, and independent verification against the actual source code. Overall, it is designed to make AI-assisted security review more systematic, adversarial, and evidence-based. -
3
AgentScope
Build and run agents you can see, understand and trust
...It provides essential abstractions that evolve with advancing LLM capabilities, emphasizing reasoning, tool use, and flexible orchestration rather than rigid prompt constraints. With built-in support for ReAct agents, memory, planning, human-in-the-loop control, and real-time voice interaction, developers can create powerful agents in minutes. AgentScope integrates seamlessly with tools, long-term memory systems, MCP, A2A (Agent-to-Agent) protocols, and observability frameworks. It also supports reinforcement learning workflows for tuning agents and improving performance across complex tasks. ... -
4
verl
Volcano Engine Reinforcement Learning for LLMs
...It ships with reference implementations of popular alignment algorithms and clear examples that make it straightforward to reproduce baselines before customizing. Data pipelines treat human feedback, simulated environments, and synthetic preferences as interchangeable sources, which helps with rapid experimentation. VERL is meant for both research and production hardening: logging, checkpointing, and evaluation suites are built in so you can track learning dynamics and regressions over time. -
$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.
-
5
Habitat-Lab
A modular high-level library to train embodied AI agents
...It is designed to train agents to perform a wide variety of embodied AI tasks in indoor environments, as well as develop agents that can interact with humans in performing these tasks. Allowing users to train agents in a wide variety of single and multi-agent tasks (e.g. navigation, rearrangement, instruction following, question answering, human following), as well as define novel tasks. 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. -
6
Aden Hive
Outcome driven agent development framework that evolves
...Once deployed, agents can capture failure data, evolve automatically to meet their success criteria, and redeploy without constant manual intervention, delivering continual improvement over time. The framework also includes human-in-the-loop nodes, credential management, cost and budget controls, and real-time observability so teams can monitor execution and intervene as needed. Hive is designed for production environments and supports a wide range of large language models, local models, and business system connectivity. -
7
AG-UI
The Agent-User Interaction Protocol
...Instead of treating an AI agent as a black-box chat endpoint, AG-UI defines structured events for messages, tool calls, state changes, lifecycle updates, and user interactions. This makes it easier for developers to build agent-powered apps that stream progress, request human input, update UI state, and coordinate complex workflows. The project is especially useful for teams building copilots, workflow assistants, multi-agent products, or custom AI interfaces. Overall, AG-UI provides a shared communication layer between autonomous systems and the interfaces where people actually use them. -
8
DeepSeek V2
Strong, Economical, and Efficient Mixture-of-Experts Language Model
...The V2 model is expected to support more advanced features like better context window handling, more efficient inference, better performance on challenging tasks, and stronger alignment with human feedback. Because DeepSeek is pushing open-weight competition, this V2 iteration is meant to solidify its position in benchmark rankings and in developer adoption. The code in the repository may include description files, support for tool use or plug-in architectures, and artifacts showing fine-tuning or prompt templates. -
9
OpenHands
Open-source autonomous AI software engineer
...Use AI to tackle the toil in your backlog, so you can focus on what matters: hard problems, creative challenges, and over-engineering your dotfiles We believe agentic technology is too important to be controlled by a few corporations. So we're building all our agents in the open on GitHub, under the MIT license. Our agents can do anything a human developer can: they write code, run commands, and use the web. We're partnering with AI safety experts like Invariant Labs to balance innovation with security. -
99.99% Uptime for MySQL and PostgreSQL DatabasesCloud SQL Enterprise Plus delivers near-zero downtime with 35 days of point-in-time recovery. Supports MySQL, PostgreSQL, and SQL Server.
-
10
video2robot
End-to-end pipeline converting generative videos
video2robot is an end-to-end open-source pipeline that converts generative video or prompt-driven motion content into executable humanoid robot motion sequences, enabling researchers and developers to go from high-level action descriptions or videos to robot-ready motion data. The pipeline supports both prompt-to-video generation using models like Veo/Sora and video upload processing, followed by human pose extraction through a 3D pose model and retargeting of that motion to robot joints using a general motion retargeting system. This workflow allows users to generate robot motion files that specify joint angles, root positions, and orientations that can be deployed on supported robot platforms (e.g., Unitree models). Video2robot includes scripts for each stage of the pipeline (generation, extraction, conversion, visualization) and can run as a CLI or through a basic web UI. -
11
PraisonAI
PraisonAI application combines AutoGen and CrewAI or similar framework
PraisonAI application combines AutoGen and CrewAI or similar frameworks into a low-code solution for building and managing multi-agent LLM systems, focusing on simplicity, customization, and efficient human-agent collaboration. Chat with your ENTIRE Codebase. Praison AI, leveraging both AutoGen and CrewAI or any other agent framework, represents a low-code, centralized framework designed to simplify the creation and orchestration of multi-agent systems for various LLM applications, emphasizing ease of use, customization, and human-agent interaction. -
12
Paperclip
Open-source orchestration for zero-human companies
Paperclip is an open-source tool designed to help AI systems and developer tools access academic research papers through a standardized interface. The project implements a server based on the Model Context Protocol (MCP), a framework that allows large language models and AI agents to connect to external data sources and tools in a consistent way. By acting as a middleware layer, Paperclip aggregates multiple academic databases and exposes them through a single interface, allowing AI... -
13
LangGraph Studio
Desktop app for prototyping and debugging LangGraph applications
LangGraph Studio offers a new way to develop LLM applications by providing a specialized agent IDE that enables visualization, interaction, and debugging of complex agentic applications. With visual graphs and the ability to edit state, you can better understand agent workflows and iterate faster. LangGraph Studio integrates with LangSmith so you can collaborate with teammates to debug failure modes. While in Beta, LangGraph Studio is available for free to all LangSmith users on any plan... -
14
Dendrite
Tools to build web AI agents that can authenticate
Dendrite Python SDK is a toolkit for building web AI agents that can authenticate, interact with, and extract data from any website, facilitating web automation tasks. -
15
HunyuanVideo
HunyuanVideo: A Systematic Framework For Large Video Generation Model
HunyuanVideo is a cutting-edge framework designed for large-scale video generation, leveraging advanced AI techniques to synthesize videos from various inputs. It is implemented in PyTorch, providing pre-trained model weights and inference code for efficient deployment. The framework aims to push the boundaries of video generation quality, incorporating multiple innovative approaches to improve the realism and coherence of the generated content. Release of FP8 model weights to reduce GPU... -
16
ROOT
Analyzing, storing and visualizing big data, scientifically
...It is reliable, performant and well supported, easy to use and obtain, and strives to maximize the quantity and impact of scientific results obtained per unit cost, both of human effort and computing resources. ROOT provides a very efficient storage system for data models, that demonstrated to scale at the Large Hadron Collider experiments: Exabytes of scientific data are written in columnar ROOT format. ROOT comes with histogramming capabilities in an arbitrary number of dimensions, curve fitting, statistical modeling, and minimization, to allow the easy setup of a data analysis system that can query and process the data interactively or in batch mode, as well as a general parallel processing framework, RDataFrame, that can considerably speed up an analysis. -
17
WebMCP
Enabling web apps to get accessed by AI agents
...Unlike backend integrations, WebMCP executes tools within the live web page, preserving shared context between the user, the agent, and the application UI. This approach supports collaborative, human-in-the-loop workflows where users can delegate tasks to agents while maintaining visibility and control. WebMCP reduces developer burden by reusing existing frontend logic instead of requiring separate server-side integrations. Designed to complement protocols like MCP rather than replace them, WebMCP strengthens accessibility, interoperability, and agent reliability across the modern web. -
18
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. -
19
PentAGI
Perform penetration testing tasks
...The platform aims to automate significant portions of the penetration testing lifecycle, including reconnaissance, vulnerability discovery, and exploitation planning, reducing the amount of manual effort required from security professionals. It leverages agent-based architecture and AI reasoning to chain together tools and strategies in a way that mimics experienced human testers. The project is built to be modular and extensible so researchers and red teams can customize behavior or integrate additional tools as needed. By focusing on autonomous decision-making in cybersecurity contexts, PentAGI represents part of the broader trend toward AI-assisted offensive security automation. -
20
Agentic Inbox
A self-hosted email client with an AI agent, running entirely on Cloud
...The system supports full email functionality, including sending, receiving, threading, and attachment management through a modern web interface. Its AI agent can search conversations, summarize messages, and generate replies, while still requiring human approval before sending. The architecture combines durable state management, storage services, and AI inference into a unified workflow. Overall, it serves as a reference implementation for building AI-powered communication tools with full control over data and infrastructure. -
21
DriveLM
Driving with Graph Visual Question Answering
...Instead of treating autonomous driving as a purely sensor-driven pipeline, DriveLM frames it as a reasoning problem where models answer structured questions about the environment to guide decision making. The system includes DriveLM-Data, a dataset built on driving environments such as nuScenes and CARLA, where human-written reasoning steps connect different layers of driving tasks. This design allows models to learn relationships between objects, behaviors, and navigation decisions through graph-structured logic. -
22
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. ... -
23
The LLM Evaluation guidebook
Sharing both practical insights and theoretical knowledge about LLM
...The guidebook teaches developers how to design evaluation pipelines, select appropriate metrics, and interpret model performance results. It discusses multiple evaluation strategies, ranging from automated benchmarks to human evaluation and LLM-based evaluation techniques. The material also highlights the strengths and weaknesses of different evaluation methods, helping practitioners understand when and how to apply them. By organizing evaluation knowledge into structured sections, the project helps engineers and researchers build more reliable and trustworthy AI systems. -
24
LLM-Agent-Paper-List
The paper list of the 86-page SCIS cover paper
...The project also organizes literature into thematic sections that explore different application scenarios, including single-agent systems, collaborative multi-agent environments, and human-agent interaction. By structuring the literature in this way, the repository helps researchers navigate a rapidly growing body of work related to autonomous AI systems built on language models. It is frequently updated to incorporate newly published papers and emerging developments in the field. -
25
Dash Data Agent
Self-learning data agent that grounds its answers in layers of content
Dash is a self-learning data agent built by the Agno AI community that generates grounded answers to English queries over structured data by synthesizing SQL and reasoning based on six layers of context, improving automatically with each run. It sidesteps common limitations of simple text-to-SQL agents by incorporating multiple context layers — including schema structure, human annotations, known query patterns, institutional knowledge from docs, machine-discovered error patterns, and live runtime context — to generate SQL queries that are both technically correct and semantically meaningful. The system then executes those queries against a database and interprets the results, returning human-friendly insights not just raw rows, while learning from errors and successes to reduce repeated mistakes.