Codex independently navigates your codebase, implements and tests code changes, and proposes pull requests for you to review. It’s powered by codex-1, a version of OpenAI o3 optimized for software engineering.
AGENTS
-
Codex AI software engineering agent launches in ChatGPT
By
–
We’re launching a research preview of Codex: a cloud-based software engineering agent that can work on many tasks in parallel. Rolling out to Pro, Enterprise, and Team users in ChatGPT starting today.
-
Shared State Enables Data Exchange Between AI Agents
By
–
Shared state Shared state enables data exchange between agents, especially useful for passing data across branches or non-adjacent steps in a flow.
-
Human-in-the-Loop Workflow Checkpoints Enable Seamless AI Execution
By
–
Truly human-in-the-loop Why "truly"? Execution is paused while waiting for human input, but it does not block the running thread. Each checkpoint is saved, enabling the workflow to resume from that point, even after an application restart. This concept of checkpoints makes
-
Multi-Agent Communication Systems: Supervisor and Worker Architecture
By
–
Agent-to-agent communication We support multimodal communication between different agents. For example, a Supervisor agent can formulate and delegate tasks to multiple Worker agents. The outputs from the Worker agents are fed back to the Supervisor. In every turn, agents
-
Agentflow V2 vs n8n Make Zapier: Key Differences
By
–
We launched Agentflow V2 yesterday. One of the most asked questions: What is the difference between Agentflow and automation platforms like n8n, Make, or Zapier?
-
OpenAI Codex Agent Shows Net-Positive Coding Gains, Future Bright
By
–
I've tried OpenAI's Codex, the autonomous SWE agent integrated into ChatGPT. -> While certainly not producing one-shot perfect PRs, it's already a net-positive. And the gain will only improve with better coder models! I think that in the next era of coding, most will be done
-
DeepAgent Evaluates All LLMs in Single Line Prompt
By
–
In a single line prompt, DeepAgent evaluates all LLMs and creates this website:
— Abacus.AI (@abacusai) 16 mai 2025
•Generated an image for each LLM
•Created a chart that compares and contrasts top LLMs across cost, performance, and context pic.twitter.com/0fwC6bhEGOIn a single line prompt, DeepAgent evaluates all LLMs and creates this website: •Generated an image for each LLM
•Created a chart that compares and contrasts top LLMs across cost, performance, and context -
Cloud-based software engineering agent handling parallel tasks efficiently
By
–
"A cloud-based software engineering agent that can work on many tasks in parallel" Codex, it's a better name than ChatGPT
-
OpenAI Launches Codex: AI Agent for Parallel Software Engineering Tasks
By
–
Coding is about to change forever. We’re launching a research preview of Codex, a cloud-based software engineering agent that can work on many tasks in parallel. Codex is powered by codex-1, a version of OpenAI o3 optimized for software engineering.