# ref/ect

## Docs

- [Data types](https://docs.starlight-search.com/api-reference/data-types.md): Reference for all data types returned by ReflectClient methods.
- [Reference overview](https://docs.starlight-search.com/api-reference/introduction.md): SDK exports and how the reference is organized.
- [ReflectClient](https://docs.starlight-search.com/api-reference/reflect-client.md): Complete method reference for the Reflect Python client.
- [For AI Agents](https://docs.starlight-search.com/for-agents.md): How AI agents consume Reflect: plain-text docs, installable skills, and the MCP server.
- [Deep Agents](https://docs.starlight-search.com/guides/examples/deepagents-exa.md): The context manager pattern: use reflect.trace() as a with-block to instrument multi-step tool-using agents.
- [Interactive Feedback CLI](https://docs.starlight-search.com/guides/examples/interactive-feedback-cli.md): The building-block pattern: call augment_with_memories and create_trace_and_wait directly, then review interactively.
- [OpenAI Agents](https://docs.starlight-search.com/guides/examples/openai-agents.md): The decorator pattern: wrap an async agent function with @reflect_trace for automatic memory retrieval and trace submission.
- [MCP Server](https://docs.starlight-search.com/guides/mcp.md): Connect Reflect memory tools to Cursor, Claude Code, Windsurf, and any MCP-compatible client.
- [Memories](https://docs.starlight-search.com/guides/memories.md): What memories are, how they're created, how to retrieve them, and best practices for getting the most out of memory-augmented agents.
- [Roadmap](https://docs.starlight-search.com/guides/roadmap.md): Upcoming priorities for the StarlightSearch Reflect SDK.
- [Skills](https://docs.starlight-search.com/guides/skills.md): Project-level skills auto-generated from your reviewed Reflect traces. (Looking to integrate Reflect? See For AI Agents.)
- [Traces and reviews](https://docs.starlight-search.com/guides/traces-and-reviews.md): What traces and reviews are, how to record them using the three SDK patterns, and how reviews drive the learning loop.
- [Introduction](https://docs.starlight-search.com/index.md): Python client for the Reflect learning API.
- [Installation](https://docs.starlight-search.com/installation.md): Install the Reflect SDK for Python.
- [Quickstart](https://docs.starlight-search.com/quickstart.md): Create a client, query memories, record a trace, and submit a review.

## OpenAPI Specs

- [openapi](https://docs.starlight-search.com/api-reference/openapi.json)

## Optional

- [Console](https://reflect.starlight-search.com)