Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
DeepSWE is an innovative and fully open-source coding agent that utilizes the Qwen3-32B foundation model, trained solely through reinforcement learning (RL) without any supervised fine-tuning or reliance on proprietary model distillation. Created with rLLM, which is Agentica’s open-source RL framework for language-based agents, DeepSWE operates as a functional agent within a simulated development environment facilitated by the R2E-Gym framework. This allows it to leverage a variety of tools, including a file editor, search capabilities, shell execution, and submission features, enabling the agent to efficiently navigate codebases, modify multiple files, compile code, run tests, and iteratively create patches or complete complex engineering tasks. Beyond simple code generation, DeepSWE showcases advanced emergent behaviors; when faced with bugs or new feature requests, it thoughtfully reasons through edge cases, searches for existing tests within the codebase, suggests patches, develops additional tests to prevent regressions, and adapts its cognitive approach based on the task at hand. This flexibility and capability make DeepSWE a powerful tool in the realm of software development.
Description
Frontier AI labs use Patronus AI to train models and agents on realistic, multi-step work. The company designs reinforcement learning environments modeled on everyday digital tasks, from writing and shipping code to operating websites, resolving customer support requests, and completing financial workflows. Every environment combines replicas of real software with task definitions and reward signals, and it introduces the friction agents meet in practice, including slow responses, changing interfaces, and interruptions. Alongside these environments, Patronus AI researches Digital World Models: AI models that learn how software environments respond to an agent’s actions, making it possible to create new training environments automatically and keep them challenging as model capabilities grow. Labs apply this work across post-training, benchmarking, and evaluation.
API Access
Has API
No
API Access
Has API
Yes
Integrations
Together AI
No
Pricing Details
Free
Free Trial
No
Free Version
Yes
Pricing Details
Custom pricing based on project scope. Contact Patronus AI to discuss.
Free Trial
No
Free Version
No
Deployment
Web-Based
No
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
Yes
Mac
Yes
Linux
Yes
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
Yes
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Agentica Project
Founded
2025
Country
United States
Website
agentica-project.com
Vendor Details
Company Name
Patronus AI
Founded
2023
Country
United States
Website
www.patronus.ai/
Product Features
Product Features
Artificial Intelligence
Chatbot
No
For Healthcare
No
For Sales
No
For eCommerce
No
Image Recognition
No
Machine Learning
Yes
Multi-Language
No
Natural Language Processing
Yes
Predictive Analytics
No
Process/Workflow Automation
No
Rules-Based Automation
No
Virtual Personal Assistant (VPA)
No