Open SWE: An Open-Source Framework for Internal Coding Agents

kept by eddie mar 18

LangChain releases Open SWE, an open-source framework for building internal coding agents that mirrors patterns from Stripe, Ramp, and Coinbase production deployments.

Your harness, your memory
Agent harnesses are deeply tied to agent memory, and using a closed one cedes control of memory to a third party, creating vendor lock-in that open harnesses avoid.
also on Deep Agents, LangChain, #ai-agents, #open-source, #developer-tools
Give your agent its own computer
LangSmith Sandboxes give each AI agent its own hardware-isolated microVM with filesystem, shell, and package manager, enabling secure code execution without risking host infrastructure.
also on Langsmith, LangChain, #ai-agents, #software-engineering, #developer-tools
How to really stop your agents from making the same mistakes (via @garrytan)
LangChain's LangSmith testing platform uses trajectory evals and trace-to-dataset pipelines to prevent AI agents from repeating mistakes, despite its high valuation and funding.
also on Langsmith, LangChain, #ai-agents, #software-engineering, #developer-tools
Agents Should Be More Opinionated
Building opinionated agents that limit user choices and optimize for specific tasks produces far more reliable outcomes than flexible, general-purpose designs.
also on LangGraph, LangChain, #ai-agents, #ai-coding, #software-engineering, #developer-tools
The Harness Is the Company - by Shrivu Shankar
SaaS businesses will evolve into AI-driven 'harnesses'—systems of infrastructure, context, and agents—that invert human roles from operators to taste-holders within the organization.
also on LangGraph, #ai-agents, #ai-coding, #software-engineering, #developer-tools