diff --git a/.story_kit/work/1_backlog/344_story_chatgpt_agent_backend_via_openai_api.md b/.story_kit/work/1_backlog/344_story_chatgpt_agent_backend_via_openai_api.md
new file mode 100644
index 0000000..d173225
--- /dev/null
+++ b/.story_kit/work/1_backlog/344_story_chatgpt_agent_backend_via_openai_api.md
@@ -0,0 +1,24 @@
+---
+name: "ChatGPT agent backend via OpenAI API"
+---
+
+# Story 344: ChatGPT agent backend via OpenAI API
+
+## User Story
+
+As a project owner, I want to run agents using ChatGPT (GPT-4o, o3, etc.) via the OpenAI API, so that I can use OpenAI models for coding tasks alongside Claude.
+
+## Acceptance Criteria
+
+- [ ] Implement OpenAiRuntime using the AgentRuntime trait from refactor 343
+- [ ] Supports GPT-4o and o3 models via the OpenAI chat completions API
+- [ ] Manages a conversation loop: send prompt + tool definitions, execute tool calls, continue until done
+- [ ] Tool definitions map to the same tools agents currently use (file read/write, bash, grep, etc.)
+- [ ] Configurable in project.toml: runtime = 'openai', model = 'gpt-4o'
+- [ ] OPENAI_API_KEY passed via environment variable
+- [ ] Token usage tracked and logged to token_usage.jsonl
+- [ ] Agent output streams to the same event system (web UI, bot notifications)
+
+## Out of Scope
+
+- TBD