Using Local Coding Agents

Upgrading agentic coding capabilities with the new Devstral models

Harness engineering: leveraging Codex in an agent-first world

By Ryan Lopopolo, Member of the Technical Staff

Tiny Agents: an MCP-powered agent in 50 lines of code

Personal Copilot: Train Your Own Coding Assistant

How to Combine Claude Code and Codex for Maximum Coding Power

Get the most out of each coding model to have a very powerful coding setup The post How to Combine Claude Code and Codex for Maximum Coding Power appeared first on Towards Data Science .

Components of A Coding Agent

How coding agents use tools, memory, and repo context to make LLMs work better in practice

Codex is Open Sourcing AI models

Tiny Agents in Python: a MCP-powered agent in ~70 lines of code

Training CodeParrot 🦜 from Scratch

Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages

arXiv:2606. 10933v1 Announce Type: new Abstract: LLM-based coding agents are usually evaluated in familiar software settings: mainstream languages, common libraries, and public repositories.

Detecting AI Coding Agents in Open Source: A Validated Multi-Method Census of 180 Million Repositories

Generative AI coding agents are entering the open-source supply chain, yet their diverse and often invisible traces leave their prevalence poorly understood. We introduce a multi-layered detection framework that integrates configuration-file scanning, commit-message analysis, author-identity matching, and bot-signature lookup across World of Code (180M+ Git repositories), classifying agent traces into four behavioral types.

Addendum to o3 and o4-mini system card: Codex

Codex is a cloud-based coding agent. Codex is powered by codex-1, a version of OpenAI o3 optimized for software engineering.