Give your AI memory in one parameter

Backboard has introduced a single-parameter memory system for LLMs, replacing the typical multi-step pipeline of embedding extraction, vector storage, and similarity search. By setting `memory` to `"Auto"`, the assistant automatically extracts, stores, and recalls user facts across conversations without any additional engineering. The feature supports per-turn control with options for read-only or off modes, as well as a higher-accuracy `memory_pro` variant.

By default, an LLM forgets you the moment a conversation ends. Start a new chat and it has no idea who you are, what you told it last week, or what you prefer. For a real product, that is a dealbreaker. Users expect the app to remember. The standard fix is a memory pipeline you build yourself. Extract the important facts from each conversation. Turn them into embeddings. Store the vectors in a database. On every new message, run a similarity search, pull the relevant facts, and inject them into the prompt. That is a meaningful chunk of engineering, and you maintain it forever. Backboard collapses that into one parameter: memory . Set it to "Auto" and your assistant remembers. Memory is stored on the assistant, so pass the same assistant id and memory="Auto" . Facts the user shares in one conversation are recalled in the next. pip install backboard-sdk python import asyncio from backboard import BackboardClient async def main : client = BackboardClient api key="YOUR API KEY" Conversation 1: tell it something await client.send message "My name is Sarah. I work at Google as a software engineer.", assistant id="your-assistant-id", memory="Auto", Conversation 2: new thread, same assistant, it remembers reply = await client.send message "What do you remember about me?", assistant id="your-assistant-id", memory="Auto", print reply.content name, employer, and role asyncio.run main js const send = body = fetch "https://app.backboard.io/api/threads/messages", { method: "POST", headers: { "X-API-Key": "YOUR API KEY", "Content-Type": "application/json", }, body: JSON.stringify body , } .then r = r.json ; await send { content: "My name is Sarah. I work at Google as a software engineer.", assistant id: "your-assistant-id", memory: "Auto", } ; const reply = await send { content: "What do you remember about me?", assistant id: "your-assistant-id", memory: "Auto", } ; console.log reply.content ; Save: memory="Auto" extracts and stores facts curl -X POST "https://app.backboard.io/api/threads/messages" \ -H "X-API-Key: YOUR API KEY" \ -H "Content-Type: application/json" \ -d '{"content": "My name is Sarah. I work at Google as a software engineer.", "assistant id": "your-assistant-id", "memory": "Auto"}' Recall: same assistant, new conversation curl -X POST "https://app.backboard.io/api/threads/messages" \ -H "X-API-Key: YOUR API KEY" \ -H "Content-Type: application/json" \ -d '{"content": "What do you remember about me?", "assistant id": "your-assistant-id", "memory": "Auto"}' No embedding step. No vector database. No retrieval code. One parameter, and the assistant extracts the facts, stores them, and recalls them when they are relevant. "Auto" actually does Behind that single value, Backboard runs the full loop: It works across every thread under the same assistant, which is exactly the behavior you want: the user is remembered no matter which conversation they are in. memory is a per-turn parameter. Pass it on each call where you want memory active. Pick one value: | Parameter | Value | Saves? | Retrieves? | Use it when | |---|---|---|---|---| memory | "Auto" | Yes | Yes | The recommended default for most apps | memory | "Readonly" | No | Yes | Recall facts without writing new ones | memory | "off" | No | No | One-off requests that should not be remembered | memory pro | "Auto" | Yes | Yes | You need higher-accuracy recall and accept higher cost | memory pro | "Readonly" | No | Yes | High-accuracy recall only | memory and memory pro cannot be used together in the same message. Use memory for everyday recall and memory pro when accuracy matters more than cost. Higher-accuracy retrieval response = await client.send message "What were my project deadlines?", assistant id="your-assistant-id", memory pro="Auto", "Auto" covers most apps. When you need to manage memory directly, the assistant exposes full CRUD: list, add, search, update, and delete. You own the data and can export it whenever you want. Add a fact yourself await client.add memory assistant id, content="User prefers dark mode in all applications", Semantic search over what the assistant knows results = await client.search memories assistant id, query="user interface preferences", limit=5, for m in results "memories" : print m "content" Persistent memory is usually a project: an extraction pipeline, a vector store, retrieval code, and ongoing upkeep. Backboard makes it a parameter. Set memory="Auto" , reuse the assistant, and your AI remembers your users across every conversation. When you need precision or control, switch to memory pro or manage memories directly. No database required. Grab a key and try it: app.backboard.io https://app.backboard.io Memory docs: docs.backboard.io/concepts/memory https://docs.backboard.io/concepts/memory