Search Results for "task"
Sort By:
94 projects for "task" with 3 filters applied:
-
anny is an all-in-one platform for managing hybrid workplaces and shared resources.Enable your employees to easily book desks, meeting rooms, parking spots, equipment, and more – all in one place. With flexible rules and group permissions, you stay in full control of who can access what.
-
DeskTime is a cloud-based time tracking softwareDeskTime is a high-performance, automated time tracking and workforce management solution for teams and freelancers. It runs silently in the background, logging computer activity from the moment of boot-up to ensure 100% accurate data without the need for manual timers.
-
1
BrowserGym
A Gym environment for web task automation
...One of its main strengths is that it bundles several important benchmarks by default, including MiniWoB, WebArena, VisualWebArena, WorkArena, AssistantBench, WebLINX, and OpenApps. This gives researchers a unified way to compare agent behavior across diverse web environments and task types without stitching together separate evaluation stacks. BrowserGym is also designed to be extensible, and the repository notes that creating new benchmarks mainly involves inheriting its abstract task interface. -
2
Claude Skills
Public repository for Agent Skills
Claude Skills is a public repository that showcases and serves as a collection of skills — modular, reusable packages of instructions, scripts, and resources that Claude and other compatible agents can dynamically discover and load to extend their capabilities on specialized tasks. Rather than relying on handcrafted prompts every time, Skills teach an AI agent procedural knowledge and task-specific workflows so it can apply that expertise reliably, whether the task involves document creation, data analysis, design generation, or technical automation. Each Skill lives in its own directory with a SKILL.md file containing metadata and instructions, and can include supplemental scripts or assets that the agent uses to perform complex operations when relevant. -
3
robosuite
A Modular Simulation Framework and Benchmark for Robot Learning
...Developed by the ARISE Initiative, Robosuite offers a set of standardized benchmarks and customizable environments designed to advance research in robotic manipulation, control, and imitation learning. It emphasizes realistic simulations and ease of use for both single-task and multi-task learning. -
4
AG2
Framework for building and orchestrating multi-agent AI systems
...AG2 focuses on making multi-agent systems more accessible by simplifying how agents are configured, connected, and executed. It includes mechanisms for agent-to-agent interaction, task delegation, and iterative reasoning, which are essential for building advanced AI-driven applications. AG2 is intended for developers experimenting with autonomous systems, research prototypes, or production-grade agent pipelines. AG2 emphasizes flexibility, allowing users to integrate different models and customize behaviors depending on their use case. ... -
Business password and access manager solution for IT security teamsEuropean businesses use Uniqkey to simplify password management, reclaim IT control and reduce password-based cyber risk. All in one super easy-to-use tool.
-
5
Text-to-LoRA (T2L)
Hypernetworks that adapt LLMs for specific benchmark tasks
...Developers and researchers can experiment with how textual task descriptions can generate LoRA weights that modify model behavior in real time. -
6
LLMCompiler
An LLM Compiler for Parallel Function Calling
...Traditional LLM agent systems typically execute tool calls sequentially, which can create latency, higher costs, and reduced reliability when solving multi-step problems. LLMCompiler addresses this limitation by applying principles from classical compilers to analyze a task and construct an execution plan that allows multiple functions to run in parallel whenever possible. The framework builds a dependency graph of required operations, identifying which tasks must run sequentially and which can be executed simultaneously. Its architecture includes components such as a planning module that constructs the task graph, a task dispatcher that manages dependencies, and an executor that performs parallel calls. -
7
Hephaestus
Semi-Structured Agentic Framework. Workflows build themselves
...Developers define high-level phases such as analysis, implementation, and testing, while agents generate specific subtasks within those phases. The system continuously monitors agent behavior and task progression, allowing workflows to evolve as new discoveries are made. For example, if an agent detects a bug or optimization opportunity, it can automatically create a new task and integrate it into the workflow. The framework also includes monitoring mechanisms that track agent trajectories and ensure that tasks remain aligned with overall objectives. -
8
Whisper
Robust Speech Recognition via Large-Scale Weak Supervision
...These tasks are jointly represented as a sequence of tokens to be predicted by the decoder, allowing a single model to replace many stages of a traditional speech-processing pipeline. The multitask training format uses a set of special tokens that serve as task specifiers or classification targets. -
9
Open SWE
Open source async coding agent that plans, codes, and opens PRs
...Open SWE is capable of creating commits and automatically opening pull requests once implementation is complete, effectively closing the loop on development tasks. It also supports interactive feedback during execution, allowing users to guide or adjust the process mid-task. Despite its advanced capabilities, the project has been officially marked as deprecated. -
Teradata VantageCloud Enterprise is a data analytics platform for performing advanced analytics on AWS, Azure, and Google Cloud.VantageCloud is the complete cloud analytics and data platform, delivering harmonized data and Trusted AI for all. Built for performance, flexibility, and openness, VantageCloud enables organizations to unify diverse data sources, run complex analytics, and deploy AI models—all within a single, scalable platform.
-
10
autoMate
AI tool for automating desktop tasks via natural language input
autoMate is an AI-powered local automation tool designed to enable users to control and automate their computers using natural language instructions instead of traditional scripting or rule-based systems. It combines large language models with computer vision techniques to interpret user intent and understand on-screen content, allowing it to interact with graphical interfaces similarly to a human user. autoMate follows an observe-decide-act workflow, where it analyzes the screen, plans... -
11
FinGPT
Open-Source Financial Large Language Models
FinGPT is an open-source, finance-specialized large language model framework that blends the capabilities of general LLMs with real-time financial data feeds, domain-specific knowledge bases, and task-oriented agents to support market analysis, research automation, and decision support. It extends traditional GPT-style models by connecting them to live or historical financial datasets, news APIs, and economic indicators so that outputs are grounded in relevant and recent market conditions rather than generic knowledge alone. The platform typically includes tools for fine-tuning, context engineering, and prompt templating, enabling users to build specialized assistants for tasks like sentiment analysis, earnings summary generation, risk profiling, trading signal interpretation, and document extraction from financial reports. -
12
SGR Agent Core
Schema-Guided Reasoning (SGR) has agentic system design
SGR Agent Core is an open-source framework for building intelligent AI research agents based on a methodology known as Schema-Guided Reasoning (SGR). The framework provides a core library that allows developers to design autonomous agents capable of structured reasoning and complex task execution. Instead of relying solely on free-form prompts, the system organizes reasoning processes around schemas that guide how agents analyze problems, gather information, and generate outputs. This architecture enables agents to follow structured reasoning workflows while still benefiting from the flexibility of large language models. ... -
13
AgentBench
A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)
...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
WanGP
AI video generator optimized for low VRAM and older GPUs use
Wan2GP is an open source AI video generation toolkit designed to make modern generative models accessible on consumer-grade hardware with limited GPU memory. It acts as a unified interface for running multiple video, image, and audio generation models, including Wan-based models as well as other systems like Hunyuan Video, Flux, and Qwen. A key focus of the project is reducing VRAM requirements, enabling some workflows to run on as little as 6 GB while still supporting older Nvidia and... -
15
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... -
16
Learn Claude Code
Bash is all you need, write a claude code with only 16 line code
Learn Claude Code is an educational repository that teaches how modern AI coding agents work by walking learners through a sequence of progressively more complex agent implementations, starting with a minimal Bash-based agent and culminating in agents with explicit planning, subagents, and skills. It emphasizes a hands-on learning path where each version (from v0 to v4) adds conceptual building blocks like the core agent loop, todo planning, task decomposition, and domain knowledge skills, illuminating the patterns behind what makes a true AI agent tick. The goal is to demystify agent architectures like Claude Code by having learners build simplified versions themselves and observe how tools, memory management, planning constraints, and context isolation contribute to reliable agent behavior. ... -
17
Acontext
Context data platform for building observable, self-learning AI agents
Acontext is a cloud-native context data platform designed to support the development and operation of advanced 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. ... -
18
OpenManus
Open-source AI agent framework
OpenManus is an open-source AI agent framework designed to autonomously execute complex, multi-step tasks by combining reasoning, planning, and tool use. It enables developers to build agents that can think, act, and iterate toward goals rather than simply responding to prompts. The platform emphasizes task decomposition, allowing agents to break down objectives into smaller steps and execute them sequentially or recursively. OpenManus supports integration with external tools, APIs, and environments, making it suitable for real-world automation workflows. It is built to be flexible and extensible, enabling customization of agent behaviors, tools, and reasoning strategies. ... -
19
Every Code
Local AI coding agent CLI with multi-agent orchestration tools
Every Code (often referred to simply as Code) is a fast, local AI-powered coding agent designed to run directly in the terminal environment. It is a community-driven fork of the Codex CLI, with a strong emphasis on improving real-world developer ergonomics and workflows. Every Code enhances the traditional coding assistant model by introducing multi-agent orchestration, allowing multiple AI agents to collaborate, compare solutions, and refine outputs in parallel. It supports integration with... -
20
Conversational Health Agents (CHA)
A Personalized LLM-powered Agent Frameworks
CHA, or Conversational Health Agents, is an open-source framework designed to build intelligent healthcare assistants powered by large language models and external data sources. The system enables developers to create personalized AI agents that can interact with users through natural language while performing multi-step reasoning and task execution. It integrates orchestration capabilities that allow the agent to gather information from APIs, knowledge bases, and external services in order to generate more accurate and context-aware responses. The framework supports modular components such as planning, tool execution, and multimodal input processing, which makes it suitable for complex healthcare applications. ... -
21
Ploomber
The fastest way to build data pipelines
...The system integrates with common development environments such as Jupyter Notebook, VS Code, and PyCharm, enabling data scientists to continue working with familiar tools while building scalable workflows. Ploomber automatically manages task dependencies and execution order, allowing complex pipelines with multiple stages to run reliably. The framework can deploy pipelines across different computing environments including Kubernetes, Airflow, AWS Batch, and high-performance computing clusters. It also helps teams maintain reproducibility by tracking changes in code and rerunning only outdated pipeline tasks. -
22
Transfer Learning Repo
Transfer learning / domain adaptation / domain generalization
...The project functions as a large knowledge hub that organizes papers, tutorials, datasets, and software implementations across topics such as domain adaptation, domain generalization, multi-task learning, and few-shot learning. The repository includes surveys and theoretical explanations that help readers understand how transfer learning methods allow models trained in one domain to adapt to new tasks or datasets. In addition to academic references, the project provides practical code implementations of many transfer learning algorithms so that researchers can reproduce experiments or build their own applications. ... -
23
TigerBot
TigerBot: A multi-language multi-task LLM
TigerBot is an open-source family of large language models designed to support multilingual and multi-task natural language processing applications. The project focuses on building high-performance models capable of handling both English and Chinese tasks while maintaining strong reasoning and conversational abilities. TigerBot models are based on modern transformer architectures and are trained on large datasets that cover multiple domains and languages. -
24
4M
4M: Massively Multimodal Masked Modeling
...Training/inference configs and issues discuss things like depth tokenizers, input masks for generation, and CUDA build questions, signaling active research iteration. The design leans into flexibility and steerability, so prompts and masks can shape behavior without bespoke heads per task. In short, 4M provides a unified recipe to pretrain large multimodal models that generalize broadly while remaining practical to fine-tune. -
25
VGGT
[CVPR 2025 Best Paper Award] VGGT
VGGT is a transformer-based framework aimed at unifying classic visual geometry tasks—such as depth estimation, camera pose recovery, point tracking, and correspondence—under a single model. Rather than training separate networks per task, it shares an encoder and leverages geometric heads/decoders to infer structure and motion from images or short clips. The design emphasizes consistent geometric reasoning: outputs from one head (e.g., correspondences or tracks) reinforce others (e.g., pose or depth), making the system more robust to challenging viewpoints and textures. ...
