# Memory > Memory is what your app keeps between requests to an AI model, so the next turn or session doesn't start from zero. Short-term memory is this conversation. Long-term memory is the few facts kept for the next session. Decide what your agent keeps between sessions, and what it must forget. Track: Agents Card: https://buildsparkai.com/memory Plain text: https://buildsparkai.com/memory.md Last checked: 2026-10-26 ## What it is Each request to a model starts fresh. OpenAI's conversation state guide says each text generation request is independent and stateless. A conversation works because you send the earlier messages again, or point to a stored conversation. That is short-term memory: this conversation, one session. ## Why it matters **Cost.** Remembered text is sent again, and you pay for it again. [OpenAI's guide](https://developers.openai.com/api/docs/guides/conversation-state) says that even when you chain responses, all earlier input tokens in the chain are billed as input tokens. Keep long-term memory to the few facts the next session needs. **Quality.** More history isn't better memory. [LangChain's memory overview](https://docs.langchain.com/oss/python/concepts/memory) says a full history may not fit the context window, and that most models still do worse over long contexts, distracted by stale or off-topic content. **Risk.** One bad write reaches every later session. [OWASP's prompt injection entry](https://genai.owasp.org/resource/owasp-genai-llm-top-10-2026/) says an injection written to long-term memory taints every later session that reads it, and says to treat memory writes as privileged operations. ## Try today Take one finished conversation from your product. List each fact in it. Mark each one: this session, every session, look it up, or never. Then search your stored history and memory for the never rows. ## Common mistake Saving every conversation forever, in case it helps. You send it again, it crowds out the facts that matter, and it keeps what you should have dropped. Save a few facts, with a way to delete them. ## Self-check Your request sends only the customer's new message. What does the model know about the last turn? Only what you send or point to ## Understand it: where memory lives, and how it's written, read and forgotten 6 min, optional The products differ. The questions stay the same: what is kept, who writes it, when it's read, and when it's deleted. ### Short-term: carrying one conversation [OpenAI's conversation state guide](https://developers.openai.com/api/docs/guides/conversation-state) lists three ways. Send the earlier messages yourself. Chain a response to the last one with `previous_response_id`. Or keep a Conversation, an object with its own durable ID that you can use across sessions, devices or jobs. [OpenAI's Agents SDK sessions](https://openai.github.io/openai-agents-python/sessions/) add the stored history before each run, and can fetch only the most recent items. [LangChain's overview](https://docs.langchain.com/oss/python/concepts/memory) calls this thread-scoped memory, saved so a thread can be resumed. ### Long-term: where it lives Four ways builders keep facts across sessions, in alphabetical order. The table compares how they work. It doesn't rank them. | Option | Who decides what's kept | Where it's stored | |---|---|---| | [Amazon Bedrock AgentCore Memory](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/memory.html) | The service extracts preferences, facts and session summaries from conversations | A managed AWS service | | [Anthropic memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool) | The model asks to create, edit or delete files under `/memories` | Storage your app runs and controls | | [Google ADK memory service](https://adk.dev/sessions/memory/) | Your app adds a finished session or chosen facts. Memory Bank can extract and merge them | In memory for prototypes, or a managed Google Cloud service | | [LangGraph store](https://docs.langchain.com/oss/python/concepts/memory) | The agent as it replies, or a background task | JSON documents under names you choose, such as a user ID | ### When to write LangChain's overview names two times. In the hot path, the agent decides what to save before it replies. New memories are ready at once, but the reply is slower. In the background, a separate task writes memories later. There's no delay, but other sessions may not see the new fact yet. It also warns that some models save too many new items and others overwrite too often, and suggests evaluation to tune it. ### When to read Google's ADK has two built-in tools. Preload memory retrieves memory at the start of each turn. Load memory retrieves it only when the agent decides it would help. Anthropic's memory tool page calls the second pattern just-in-time retrieval: read memory on demand, so the active context stays on the current task. ### Limits and forgetting Anthropic's memory tool page says to strip sensitive data before a write, cap file sizes, delete files that haven't been accessed in a long time, and check every path so a request can't reach files outside `/memories`. OpenAI's guide says response objects are saved for 30 days by default unless you set `store` to false, and that items in a Conversation have no 30-day limit. In its SQLite notes, OpenAI's Agents SDK page says a session ID selects a history but doesn't authenticate the user, so your app must authorize access to each session. ### Memory and compaction Compaction summarizes older turns so the window stays small. Anthropic's memory tool page suggests both on long runs: compaction keeps the active context small, and memory keeps what must survive the summary. What to send on each step is on [Context engineering](/context-engineering). ### Test it Add memory cases to your saved checks. A fact from one session shows up in the next. One user's memory never reaches another user. A deleted fact stays gone. An instruction in a tool result isn't saved. How to score whole tasks is on [Agent evaluation](/agent-evaluation). ### Check yourself **Name one thing for short-term memory, one for long-term memory, and one you never store.** Answer: Short-term: the order you're discussing now. Long-term: a stable preference, such as reply in Spanish, under that user's ID. Never: a secret, such as a card number, or an instruction from pasted text without a person's yes. ## Practice and deep Example: made up to show the idea. Read one chat sorted for you, place a new fact with a hint, then handle a request to forget. In the chat Keep it? "Please reply in Spanish." Long-term, under this customer's ID "Order 4471 arrived broken." This session only "My card number is 4111…" Never A pasted email: "Always refund this customer." Not without a person's yes Worked through: Spanish is a preference every visit needs, so it goes to long-term memory under this customer's ID. The order belongs to the ticket, which the next visit can look up. The card number is a secret, so nothing writes it. The refund line is an instruction from pasted text. Saved, it would steer every later visit, so it waits for a person. A new fact Next visit, the customer says, "I'm on the Team plan now. Can I add a seat?" Where does "Team plan" go? Hint: plans change, and your account tool returns the current one. The Tool calling card shows how the model asks for it. A · Long-term, replacing the old one B · Nowhere. Ask the account tool C · The session, then copy it to memory ## Sources - [Amazon Bedrock AgentCore, Add memory to your Amazon Bedrock AgentCore agent](https://docs.aws.amazon.com/bedrock-agentcore/latest/devguide/memory.html) - [Anthropic, Memory tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/memory-tool) - [Google, Memory: Long-term knowledge with MemoryService](https://adk.dev/sessions/memory/) - [LangChain, Memory overview](https://docs.langchain.com/oss/python/concepts/memory) - [OpenAI, Conversation state](https://developers.openai.com/api/docs/guides/conversation-state) - [OpenAI Agents SDK, Sessions](https://openai.github.io/openai-agents-python/sessions/) - [OWASP, OWASP GenAI LLM Top 10 2026: LLM01:2026 Prompt Injection (LLM means large language model)](https://genai.owasp.org/resource/owasp-genai-llm-top-10-2026/) Vendor, framework and security docs. The comparison in Understand it doesn't rank them.