no, it does not spawn a new Node process per input. Codex() starts a local Codex app-server process and the SDK talks to it over stdio/JSON-RPC for threads and turns.
TOOLS
-
Resume restores persisted conversation history but not live processes
By
–
Resume restores the persisted thread: conversation/run history plus thread settings/config that are saved with it. It does not resurrect live tool/process state. So if Codex changed files, those filesystem changes are still there. But open shell processes, transient handles,
-
Become a pro user and explore Hugging Face’s new blog for exciting updates!
By
–
You have to be a pro user and then https://
huggingface.co/blog/new! -
Codex now supports Amazon Bedrock with GPT-5.4 and GPT-5.5
By
–
PSA: Codex now works with Amazon Bedrock! To configure, set: model_provider = "amazon-bedrock" and Codex can run local CLI, desktop, and IDE workflows against OpenAI models on Bedrock, using AWS-native auth/IAM. Both GPT-5.4 and GPT-5.5 are supported. Big unlock for teams
-
Codex Python SDK Released for Embedding in Python Apps
By
–
We just released the Codex Python SDK You can now embed Codex directly into your Python apps and workflows! > Start threads
> Run turns > Stream progress > Resume sessions
> Pass images > Control sandbox access All whilst reusing your existing Codex auth. pip install -
Abacus AI Supercomputer: Build Cloud Services & Host LLMs with a Single Prompt
By
–
🚨 INTRODUCING THE ABACUS AI SUPERCOMPUTER
— Abacus.AI (@abacusai) 1 juin 2026
– literally build ANY cloud service with a prompt
– host open-source LLMs & always-on agents
– bring your own Codex, Claude or Anti-gravity
– multi-agent architectures with Opus 4.8 and GPT 5.5
– run 3D games or any other server at… pic.twitter.com/Rs8lA4G0vaINTRODUCING THE ABACUS AI SUPERCOMPUTER – Literally build ANY cloud service with a prompt
– Host open-source LLMs & always-on agents
– Bring your own Codex, Claude or Anti-gravity
– Multi-agent architectures with Opus 4.8 and GPT 5.5
– Run 3D games or any other server at -
ActiveGraph agents have automatic first-class tracing, not bolted on
By
–
if you build any agent on activegraph, the trace is automatic and first-class, not bolted on
-
Parallel experiment building coding agent on ActiveGraph AI with event log trace
By
–
a parallel experiment building a coding agent on top of @activegraphai
. you can see everything flattened down to a single event log trace -
Tools should be called from code, not from within LLM API
By
–
slowly we're all realizing that tools should be called from code, not from within the llm api
-
Anthropic restrictive, Codex is far better for code review and allows sub.
By
–
Hmmm Anthropic is very restrictive, claude -p no longer works so no. Codex is far better at code review tho and allows using the sub!