Robin and Open SWE: What Happens Between an Issue and a Pull Request?
LangChain’s open-source coding agent shows why sandboxes, validation, and human review matter as much as generated code.
7 posts with this tag
LangChain’s open-source coding agent shows why sandboxes, validation, and human review matter as much as generated code.
Hermes Agent can lock a curated skill against agent edits. The interesting part is where that protection ends.
OpenAI plans to acquire Pierre Computer, the team behind Diffs and Trees. What does better code review need as coding agents work in parallel?
DeepSeek’s research prototype separates messages, mandates and execution. Its architecture is worth studying, including the limits of its permission model.
Lightpanda removes page rendering while retaining JavaScript and the DOM. Its architecture makes a useful case for matching browser infrastructure to an agent’s actual task.
Microduck makes robotics easier to inspect and retrain. Its software shows why robot security must cover networks, updates, AI inputs and physical motion.
Between 2011 and 2014 we developed a Cloud Platform with DLP capabilities, now in 2020 it is Open Source . It was a very cool technology at that…