# XTrace Memory

> Hosted memory for AI agents. Send conversation turns, get back searchable facts.

## Docs

- [Archive group](https://docs.xtrace.ai/api-reference/groups/archive-group.md): Soft-delete: flips `status` to `archived`. The group row is retained so memory rows tagged with this id remain searchable; new ingests reject the id with `422 group_archived`. Restore by `PATCH`ing `status` back to `active`. Idempotent.
- [Create group](https://docs.xtrace.ai/api-reference/groups/create-group.md): Register a new group on the org. Returns the persisted row including the server-generated `id`.
- [Get group](https://docs.xtrace.ai/api-reference/groups/get-group.md)
- [List groups](https://docs.xtrace.ai/api-reference/groups/list-groups.md): List groups for the calling org. Active-only by default.
- [Update group](https://docs.xtrace.ai/api-reference/groups/update-group.md): Patch `name`, `prompt`, and/or `status`. Changing `prompt` does not retroactively re-tag memory rows that were tagged under the previous prompt.
- [Agentic memory search](https://docs.xtrace.ai/api-reference/memories/agentic-memory-search.md): Agentic search over the memory pool.
- [Delete memory](https://docs.xtrace.ai/api-reference/memories/delete-memory.md): Hard-delete a memory — fact, artifact, or episode.
- [Get memory](https://docs.xtrace.ai/api-reference/memories/get-memory.md): Get one memory by id. Works for facts, artifacts, episodes. Always returns the full representation — artifacts include ``details.full_content``.
- [Get revision chain](https://docs.xtrace.ai/api-reference/memories/get-revision-chain.md): Return the revision chain for a memory.
- [Ingest memories](https://docs.xtrace.ai/api-reference/memories/ingest-memories.md): Async ingest. Returns ``202 + job_id`` by default; the extraction runs in the background and the caller polls ``GET /v1/memories/jobs/{job_id}``.
- [List memories](https://docs.xtrace.ai/api-reference/memories/list-memories.md): List memories with flat-equality filters and cursor pagination.
- [Poll ingest job](https://docs.xtrace.ai/api-reference/memories/poll-ingest-job.md): Return the current state of an ingest job.
- [Get usage](https://docs.xtrace.ai/api-reference/usage/get-usage.md): Aggregate the org's memory MONTHLY rollup rows for the current calendar month, plus DAILY rows if requested, plus an inline Qdrant storage snapshot.
- [Authentication](https://docs.xtrace.ai/guides/authentication.md): How API keys and org headers work — and how to wire them into the SDK.
- [Groups](https://docs.xtrace.ai/guides/groups.md): Share memory across users. Register a group, tag memories to it at ingest, and let every member search them.
- [Ingesting memories](https://docs.xtrace.ai/guides/ingesting-memories.md): Send conversation turns, get back extracted facts. Async by default, with a sync escape hatch.
- [Quickstart](https://docs.xtrace.ai/guides/quickstart.md): Install the SDK, ingest a conversation turn, and search it back — in under five minutes.
- [Searching memories](https://docs.xtrace.ai/guides/searching-memories.md): Vector search scoped by what you pass — a user's own memories, shared groups, or both.
- [TypeScript SDK](https://docs.xtrace.ai/guides/typescript-sdk.md): Reference for the @xtraceai/memory package — every class, method, type, and error.
- [Introduction](https://docs.xtrace.ai/introduction.md): Hosted memory for AI agents. Send conversation turns, get back searchable facts.
- [CLI quickstart](https://docs.xtrace.ai/x-vec/cli.md): Set up the xtrace CLI and run the init workflow — create an execution context, configure embeddings, and go from an empty knowledge base to search results in four commands.
- [CLI command reference](https://docs.xtrace.ai/x-vec/cli-reference.md): Full usage details for every xtrace CLI command — shared commands, knowledge base admin, and x-vec data commands.
- [Configuration](https://docs.xtrace.ai/x-vec/configuration.md): Configure the x-vec SDK via environment variables or constructor parameters — cryptography backends, key providers, DataLoader/Retriever options, and AWS KMS.
- [Embedding models](https://docs.xtrace.ai/x-vec/embedding-models.md): Convert text into binary vectors for encrypted storage and search using Ollama, Sentence Transformers, OpenAI, or your own float vectors.
- [Installation](https://docs.xtrace.ai/x-vec/installation.md): Install the x-vec Python SDK and optional extras for local embeddings and the CLI.
- [XTrace Vector DB — Encrypted vector search](https://docs.xtrace.ai/x-vec/introduction.md): Semantic search with the privacy guarantees of keeping your data on your own machine. Content is AES-encrypted and embedding vectors are homomorphically encrypted before they ever leave your laptop.
- [LLM inference](https://docs.xtrace.ai/x-vec/llm-inference.md): Run an LLM over retrieved context for RAG pipelines — with OpenAI, Anthropic, private TEE inference via Redpill, or fully local Ollama.
- [Managed service](https://docs.xtrace.ai/x-vec/managed-service.md): XTraceIntegration is the single entry point for the XTrace API — security model, connecting, loading, querying, metadata search, chunk operations, and execution context management.
- [Metadata filtering](https://docs.xtrace.ai/x-vec/metadata-filtering.md): Filter encrypted search by plaintext metadata tags — field schema, supported operators, query examples, and the privacy trade-offs.
- [Quickstart](https://docs.xtrace.ai/x-vec/quickstart.md): A complete end-to-end walkthrough of the x-vec Python SDK — create an execution context, encrypt and store documents, and run an encrypted search.

## OpenAPI Specs

- [openapi.public](https://api.staging.xtrace.ai/openapi.public.json)
- [openapi](https://docs.xtrace.ai/api-reference/openapi.json)