Agent Memory
Ajan Belleği
D3
In this entry, agent memory means application-managed information retained or retrieved from previous interactions so an agent can use it in later work.
Review status: 2026-12-04
Technical explanation
A useful distinction is scope: short-term memory can preserve state within one conversation or thread, while long-term memory can store and retrieve information across conversations.
Conceptual boundaries
This entry concerns how an application retains and reuses information, not computer RAM capacity. Retained history need not all be supplied to the current model call: the context window limits how much can be supplied at once.
Provider-neutral example
Illustrative: after a user corrects a preferred report date format, an application stores that preference by account and retrieves it before drafting a later report.
Limitations
Remembered material can be stale, incomplete, wrongly attributed, unavailable, or inappropriate to reuse. Persistence does not make it true, authorized, or suitable for the next request.
Related concepts
Atomic claims and evidence
1.1LangChain Docs: Short-term memory
- Source
- LangChain Docs: Short-term memory
- Source role
- Authoritative source
- Exact locator
- Overview
- Supported claim
- LangChain defines agent memory as a system that remembers information about previous interactions and says short-term memory can retain those interactions within one thread or conversation.
- Last verification
- Review due
- Scope limitation
- This is LangChain documentation terminology; it is not a universal storage architecture or a guarantee of recall accuracy.
2.1LangChain Docs: Short-term memory
- Source
- LangChain Docs: Short-term memory
- Source role
- Authoritative source
- Exact locator
- Overview: short-term and long-term memory
- Supported claim
- LangChain distinguishes thread-level short-term memory from long-term memory that stores and recalls user-specific or application-level data across threads and sessions.
- Last verification
- Review due
- Scope limitation
- The distinction describes a common design scope; it does not prescribe a database, retention period, or privacy policy.
3.1LangChain Docs: Short-term memory
- Source
- LangChain Docs: Short-term memory
- Source role
- Authoritative source
- Exact locator
- Overview: context-window limits and removing stale information
- Supported claim
- LangChain says a full conversation history may not fit an LLM context window and that applications can remove or forget stale information because context windows are limited.
- Last verification
- Review due
- Scope limitation
- This is LangChain’s documented design consideration, not a claim that forgetting is always correct or that an application’s retained memory is accurate.