# Memic

> Memory for your AI applications. Ingest documents, search, chat, and manage prompts with a single API key.

## Docs

- [Authentication](https://docs.memic.ai/api-reference/authentication.md): Every Memic API call is authenticated with a single API key bound to one environment.
- [Chat with documents](https://docs.memic.ai/api-reference/endpoints/chat-with-documents.md): Grounded question-answering over the indexed documents in your environment. Returns an answer plus structured citations back to the source files.
- [Confirm file upload](https://docs.memic.ai/api-reference/endpoints/confirm-file-upload.md): Signal that the file has been uploaded to the presigned URL returned by `/files/init`. Memic queues the file for chunking, embedding, and indexing.
- [Delete file](https://docs.memic.ai/api-reference/endpoints/delete-file.md): Delete a file along with its associated chunks, embeddings, and vectors. This operation is irreversible.
- [Get API key context](https://docs.memic.ai/api-reference/endpoints/get-api-key-context.md): Returns the organization, project, and environment resolved from your API key. Useful for confirming which environment a key is bound to before making other calls.
- [Get file status](https://docs.memic.ai/api-reference/endpoints/get-file-status.md): Return the processing status of a file. Poll this endpoint until `status` is `ready` before issuing search or chat queries that expect the file's content.
- [Get prompt](https://docs.memic.ai/api-reference/endpoints/get-prompt.md): Fetch the currently-live version of a managed prompt by name. Prompt names are scoped to the environment resolved from your API key.
- [Initialize file upload](https://docs.memic.ai/api-reference/endpoints/initialize-file-upload.md): Start a file upload by requesting a presigned URL. PUT the file contents directly to the returned URL, then call `POST /files/{file_id}/confirm` to trigger processing.
- [List files](https://docs.memic.ai/api-reference/endpoints/list-files.md): Return a paginated list of files in the environment. Use the `page` and `page_size` query parameters to iterate.
- [List projects](https://docs.memic.ai/api-reference/endpoints/list-projects.md): Returns all projects in your organization.
- [Unified search](https://docs.memic.ai/api-reference/endpoints/unified-search.md): Runs unified search across both unstructured documents and structured connector-backed data in your environment. Memic classifies the incoming query and intelligently routes it — natural-language questions are answered by semantic search over indexed documents, while structured queries (filters, agg…
- [Errors](https://docs.memic.ai/api-reference/errors.md): HTTP status codes, error response format, and how to handle failures.
- [API Reference](https://docs.memic.ai/api-reference/introduction.md): The Memic public API — 10 endpoints, one API key, zero IDs in the URL.
- [Pagination](https://docs.memic.ai/api-reference/pagination.md): How list endpoints paginate and how to iterate through all pages.
- [Rate limits](https://docs.memic.ai/api-reference/rate-limits.md): How Memic rate-limits requests and how to handle 429 responses.
- [Versioning](https://docs.memic.ai/api-reference/versioning.md): How the Memic API is versioned and what happens when we ship a breaking change.
- [Core concepts](https://docs.memic.ai/core-concepts.md): Organizations, projects, environments, folders — and how a single API key resolves all of them.
- [Chat over your documents](https://docs.memic.ai/guides/chat.md): Grounded question-answering with citations back to source files.
- [Environments & tenancy](https://docs.memic.ai/guides/environments.md): How to use environments to isolate staging vs prod and per-customer data.
- [Ingesting documents](https://docs.memic.ai/guides/ingestion.md): Upload files, batch imports, metadata, and file processing lifecycle.
- [Production checklist](https://docs.memic.ai/guides/production-checklist.md): What to verify before taking your Memic integration live.
- [Managed prompts](https://docs.memic.ai/guides/prompts.md): Version, edit, and roll out prompts from the dashboard without redeploying code.
- [Unified search](https://docs.memic.ai/guides/search.md): One endpoint across unstructured documents and structured connector data — Memic routes the query for you.
- [What is Memic?](https://docs.memic.ai/introduction.md): A unified context layer for AI agents — structured and unstructured, behind a single API.
- [Quickstart (cURL)](https://docs.memic.ai/quickstart-curl.md): Hit the Memic REST API directly from the command line — no SDK required.
- [Quickstart (Python)](https://docs.memic.ai/quickstart-python.md): Install, authenticate, upload a file, and search — in five minutes.
- [Build a chatbot with memory](https://docs.memic.ai/recipes/chatbot-with-memory.md): A complete, copy-paste chatbot over your own documents with citations.
- [Multi-tenant RAG for SaaS](https://docs.memic.ai/recipes/multi-tenant-rag.md): A complete pattern for embedding RAG into a SaaS product with customer-facing chat.
- [Per-customer isolation with environments](https://docs.memic.ai/recipes/per-customer-isolation.md): Multi-tenant pattern: one environment per customer, one API key per environment.
- [Python SDK — Installation](https://docs.memic.ai/sdks/python/installation.md): Install the memic Python package and make your first call.
- [Python SDK — Reference](https://docs.memic.ai/sdks/python/reference.md): Every method and parameter in the memic Python SDK.

## OpenAPI Specs

- [openapi](https://docs.memic.ai/api-reference/openapi.json)

## Optional

- [GitHub](https://github.com/memic-ai)