XAgent supports autonomous complex task solving with a large language model agent.
Open source
24 alternativesmicrosoft/JARVIS
JARVIS connects large language models with machine learning models and tools from the ML community.
About microsoft/JARVIS
microsoft/JARVIS is an open-source research system that uses a large language model as a controller to work with expert models from Hugging Face Hub. It plans user requests into tasks, selects models based on their descriptions, executes them, and combines the outputs into a response.
Use requires an OpenAI key and a Hugging Face token. The default configuration lists Ubuntu 16.04 LTS, 24GB or more VRAM, and over 284GB disk space. A lite configuration avoids local model deployment but is limited to models running on Hugging Face Inference Endpoints.
Key features
- Plans user requests into solvable subtasks using LLM controller
- Selects Hugging Face expert models based on descriptions
- Invokes selected models and returns results for integration
- Generates combined response from multiple model outputs
- Provides CLI mode and server mode with task APIs
- Supports Azure OpenAI service and GPT-4 model
Best for: Researchers and developers studying or building LLM-controlled workflows across multiple Hugging Face models.
Good for
- Open-source code with related EasyTool and TaskBench code and datasets
- Offers CLI mode, server mode, and web APIs for tasks and results
- Lite configuration allows use without deploying models locally
Watch out for
- Default configuration requires 24GB+ VRAM and 284GB+ disk space
- Lite configuration is limited to stable Hugging Face Inference Endpoints models
- Requires user-supplied OpenAI key and Hugging Face token
microsoft/JARVIS at a glance
- Website
- github.com/microsoft/JARVIS
- Category
- AI & Machine Learning › AI Agents & Automation
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
microsoft/JARVIS alternatives
Tools and sites you could use instead, ranked by how closely they match.
This repository provides code for building agents controlled by large language models.
Open source
24 alternatives
ThinkGPT provides agent techniques intended to extend the capabilities of large language models.
Open source
24 alternatives
Use L2MAC, an automatic computer framework built around large language models.
Open source
24 alternatives
SymbolicAI explores a neurosymbolic approach to large language models.
Open source
24 alternatives
BabyCommandAGI explores combining command-line interfaces with language model agents for task execution.
Open source
24 alternativesPopular in AI Agents & Automation
Well-known listings from the same topic.
Simsim.aiMaya AI.smartmaya.aiMakeformsmakeforms.ioAgent Skillsagentskills.ioGenFuse AIgenfuseai.comBeambeam.ai
microsoft/JARVIS FAQ
What credentials are needed to run JARVIS?
A personal OpenAI key and Hugging Face token, set in the config file or as OPENAI_API_KEY and HUGGINGFACE_ACCESS_TOKEN environment variables.
What are the system requirements?
The default configuration lists Ubuntu 16.04 LTS, 24GB or more VRAM, and over 284GB disk space. The lite configuration lists Ubuntu 16.04 LTS with no local model deployment required.
How does JARVIS process a request?
Through four stages: task planning, model selection, task execution, and response generation.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.