"SWE-chat: Coding Agent Interactions From Real Users in the Wild" This paper proposes a real-world coding-agent dataset. It tracks 6K sessions from actual developers, with prompts, tool calls, and line-level human vs. agent authorship. Main result is that agent autonomy is
CODE
-
Clawsweeper integrates codex review with automerge loops
By
–
Integrated codex review into clawsweeper. I'm using a very similar system prompt so this gets you the same as /review, and clawsweeper has automerge, loops until it stops finding new issues. https://
github.com/openclaw/claws
weeper
… -
Cursor SDK transforms agent runtime into programmable infrastructure
By
–
Cursor is making a platform play. Right now they're an IDE. By releasing the SDK, they're turning their agent runtime into programmable infrastructure that runs headlessly in CI/CD pipelines, internal tools, and even third-party products. Every agent spun up through the SDK burns… https://t.co/mzuAjJJSCi
— Chubby♨️ (@kimmonismus) 29 avril 2026Cursor is making a platform play. Right now they're an IDE. By releasing the SDK, they're turning their agent runtime into programmable infrastructure that runs headlessly in CI/CD pipelines, internal tools, and even third-party products. Every agent spun up through the SDK burns
-
YOLO Edge Deployment with Ultralytics and Metis Partnership
By
–
Our AI friends over at @Ultralytics has put up a new partner page covering YOLO on Metis, which we really want you to take a deep dive into: https://
eu1.hubs.ly/H0tYFwB0 Essential stuff if you're deploying YOLO at the edge:
• One-command export from Ultralytics straight to .axm
• -
AI Agents Successfully Reproduce Social Science Research Results
By
–
Paper: https://
elliottash.com/wp-content/upl
oads/2026/04/Kohler-Zollikofer-Einsiedler-Hoyle-Ash-Read-Paper-Write-Code-Agentic-Reproduction-Social-Science-Results.pdf
… Check out http://
AlphaSignal.ai to get a daily summary of top models, repos, and papers in AI. Read by 280,000+ devs. -
AI Agents Successfully Rebuild 48 Academic Papers Without Source Code
By
–
AI agents rebuilt 48 papers without seeing the code or the paper. Most academic papers are supposed to be self-contained. Turns out, AI can now test that claim. Researchers built an agentic pipeline that reads a paper's methods section, looks at the raw data, and rewrites
-
Vibe Coding Evolves: The Era of Vibe Codexers Begins
By
–
vibe coding is over
we are all vibe codexers now -
Cursor SDK Enables AI Agents for Automated Code Development
By
–
Customers like Rippling, Notion, C3 AI, and Faire are using the Cursor SDK to build custom background agents, take bugs from ticket to merge-ready PR, and maintain self-healing codebases. Learn more:
-
Cursor SDK Enables Local and Cloud Agent Deployment
By
–
With the Cursor SDK, you can run agents locally or deploy them in our cloud.
-
Open-source AI agent starter projects for developers
By
–
We've open-sourced a few starter projects for you to build on: a coding agent CLI, a prototyping tool, and an agent-powered kanban board. Use Cursor to customize them for your use case: