Apr 3, 12:24 PM

Augment Code Launches SWE-bench Verified Agent with 200,000 Token Context for Automating Large Codebase Tasks

Augment Code has launched the Augment SWE-bench Verified Agent, a new open-source AI tool designed for software engineering tasks. This AI agent is capable of handling large codebases with over 1,000 files and can automate the coding process from issue identification to pull request creation in a matter of minutes. It features a 200,000 token context, persistent memory, and deep integrations with MCP servers. The agent combines technologies from Claude Sonnet 3.7 and OpenAI O1, marking a significant advancement in agentic AI for developers.

#Augment Code #OpenAI O1

Written with ChatGPT (GPT-4o mini).

Sources

Vlad Ruso PhD@vlruso
2 years ago
Augment Code Launches SWE-bench Verified Agent: A Breakthrough in Open-Source AI for Software Engineering #OpenSourceAI #SoftwareEngineering #AIAgent #SWEbench #TechInnovation https://t.co/odv0mdclSt https://t.co/yWddvwska3
Marktechpost AI Research News ⚡@Marktechpost
2 years ago
Augment Code Released Augment SWE-bench Verified Agent: An Open-Source Agent Combining Claude Sonnet 3.7 and OpenAI O1 to Excel in Complex Software Engineering Tasks Augment Code has announced the launch of their Augment SWE-bench Verified Agent, a development in agentic AI https://t.co/gV4S6IC7Iz
Sumanth@Sumanth_077
2 years ago
AI Agent built for developers working with large codebases! Augment Agent can go from issue to PR in minutes It comes with a 200K context, persistent memory, and deep tool integrations and MCP servers. https://t.co/I98IDoesnt

Additional media

Image #1 for story augment-code-launches-swe-bench-verified-agent-200000-token-context-automating-e19eb519