4 posts tagged with "responses-api"

Codex CLI brings an agent into the terminal, but teams often want that agent to use more than one model source. OGX gives Codex one OpenAI-compatible connection to local models, hosted models, and secured deployments.

With ogx connect codex, you can launch Codex against the models exposed by a running OGX server without hand-editing your normal Codex configuration. OGX discovers the available models, writes a temporary Codex session home, forwards auth and provider data when needed, and starts Codex with a session that points at OGX.

This post walks through the command, the generated Codex profile, and a local-first path with Ollama and vLLM. The result is a small but useful workflow: Codex gets a familiar Responses API endpoint, and teams keep model access, auth, and provider choice in OGX instead of hard-coding those details into every developer tool.

AI agents that call tools, search documents, and reason over multiple turns are powerful, but they also need boundaries. A model that can execute a web search or query your internal knowledge base should not be free to produce harmful content along the way.

OGX implements guardrails as a first-class feature of the Responses API. Unlike bolt-on moderation that checks content after the fact, OGX validates content at two critical points inside the agentic loop: before inference starts and while user-visible text and reasoning output streams. This post explains exactly how that works, why the design choices matter, and how to use it in practice.

The Responses API is rapidly emerging as one of the most influential interfaces for building AI agents. It handles multi-step reasoning, tool orchestration, and conversational state in a single interaction, which is a big improvement over the manual orchestration loops that developers had to build on top of chat completion APIs. OGX's implementation of the Responses API brings these capabilities to the open source world, where you can choose your own models and run on your own infrastructure.

This post covers why the Responses API matters, what OGX's implementation enables, and how it connects to the broader move toward open agent standards like Open Responses.

What if your AI agent could improve itself? Most agent tutorials show a single loop — user asks a question, the agent calls some tools, returns an answer. But what happens when you need to systematically improve your agent's behavior over time?

In this post, we build a ResearchAgent that answers questions from an internal engineering knowledge base — and gets better at it automatically. The agent uses the Responses API agentic loop with file_search and client-side tools to research questions, and it owns its own system prompt. Every N calls, it benchmarks itself by using a different model to judge the results, and rewrites its own prompt via the Prompts API.

This is literally self-referential: a OGX agent evaluating and improving itself using the Responses API, Prompts API, and Vector Stores as its toolkit.