diff --git a/.storkit/work/5_done/345_story_gemini_agent_backend_via_google_ai_api.md b/.storkit/work/5_done/345_story_gemini_agent_backend_via_google_ai_api.md
new file mode 100644
index 0000000..8c1d2fd
--- /dev/null
+++ b/.storkit/work/5_done/345_story_gemini_agent_backend_via_google_ai_api.md
@@ -0,0 +1,25 @@
+---
+name: "Gemini agent backend via Google AI API"
+---
+
+# Story 345: Gemini agent backend via Google AI API
+
+## User Story
+
+As a project owner, I want to run agents using Gemini (2.5 Pro, etc.) via the Google AI API, so that I can use Google models for coding tasks alongside Claude and ChatGPT.
+
+## Acceptance Criteria
+
+- [ ] Implement GeminiRuntime using the AgentRuntime trait from refactor 343
+- [ ] Supports Gemini 2.5 Pro and other Gemini models via the Google AI generativeai API
+- [ ] Manages a conversation loop: send prompt + tool definitions, execute tool calls, continue until done
+- [ ] Agents connect to storkit's MCP server for all tool operations — no custom file/bash tools needed
+- [ ] MCP tool definitions are converted to Gemini function calling format
+- [ ] Configurable in project.toml: runtime = 'gemini', model = 'gemini-2.5-pro'
+- [ ] GOOGLE_AI_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