# US 2026/0311006 A1 · Compounding memory for computer-based agents including accessing long-term memory

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0311006 A1
- Document ID: US20260311006A1
- Status: Published application
- Kind: A1
- Application number: 19/255,449
- Filed: 2025-06-30
- Published: 2026-10-08
- Earliest claimed: 2025-04-03
- Assignees: Palantir Technologies Inc.
- Applicants: Palantir Technologies Inc.
- Inventors: Mazin Abdulmahmood; Palvinder Sander
- Web page: https://patentgrep.com/patent/US20260311006A1

## CPC

- G06N 5/043: Distributed expert systems; Blackboards
- G06F 9/5016: {the resource being the memory}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method may provide an agent service that utilizes a plurality of agents to process one or more computational tasks, wherein an agent is configured to: receive a request to perform a computational task, establish a memory bank of the agent by implementing a short-term memory of the memory bank, accessing a long-term memory store that is accessible to the plurality of agents, determining, based on the computational task and by a large language model (“LLM”), at least a portion of the long-term memory store to implement in the memory bank; and implementing a long-term memory including the determined portion of the long-term memory store, determine a tool to perform a portion of the computational task based on the memory bank including information for performing the portion of the computational task, process the portion of the computational task using the tool, and update the short-term memory.

## Claims

### Claim 1

A method implemented by one or more processors executing program instructions, the method comprising:
providing an agent service that utilizes a plurality of agents to process one or more computational tasks, wherein an agent of the plurality of agents is configured to:
receive a request to perform a computational task;
establish a memory bank of the agent, wherein establishing the memory bank includes:
implementing a short-term memory of the memory bank of the agent;
accessing a long-term memory store that is accessible to the plurality of agents;
determining, based on the computational task and by a large language model (“LLM”), at least a portion of the long-term memory store to implement in the memory bank of the agent; and
implementing a long-term memory of the memory bank of the agent, wherein the long-term memory includes the determined portion of the long-term memory store;
determine a tool to perform a portion of the computational task based on the memory bank of the agent, wherein the tool includes information for performing the portion of the computational task;
process the portion of the computational task using the tool; and
update the short-term memory of the memory bank based on the processing of the portion of the computational task.

### Claim 2 (depends on 1)

The method of claim 1, wherein implementing the short-term memory comprises generating or accessing one or more short-term memory files.

### Claim 3 (depends on 2)

The method of claim 2, wherein the long-term memory store is accessed via a long-term memory store service.

### Claim 4 (depends on 3)

The method of claim 3, wherein the agent is further configured to:
receive an indication of one or more memory settings of the memory bank, wherein determining at least the portion of the long-term memory store is further based on the one or more memory settings.

### Claim 5 (depends on 3)

The method of claim 3, wherein the one or more memory settings include at least one of: a memory mode of the memory bank, or one or more custom instructions.

### Claim 6 (depends on 5)

The method of claim 5, wherein the agent is further configured to:
receive an indication of a compaction mode of the memory bank, wherein implementing the short-term memory of the memory bank is based on the compaction mode.

### Claim 7 (depends on 6)

The method of claim 6, wherein implementing the long-term memory comprises copying one or more long-term memory files, or portions of one or more long-term memory files, from the long-term memory store.

### Claim 8 (depends on 7)

The method of claim 7, wherein the long-term memory store comprises a plurality of long-term memory files accessible to the plurality of agents.

### Claim 9 (depends on 8)

The method of claim 8, wherein the portion of the long-term memory store comprises at least one of: a portion of a long-term memory file, a long-term memory file, a plurality of long-term memory files, or portions of a plurality of long-term memory files.

### Claim 10 (depends on 9)

The method of claim 9, wherein the agent is further configured to:
determine a second tool to perform a second portion of the computational task based on the memory bank including the updated short-term memory, wherein the second tool includes information for performing the second portion of the computational task;
process the second portion of the computational task using the second tool; and
optionally, further update the short-term memory of the memory bank based on the processing of the second portion of the computational task.

### Claim 11 (depends on 10)

The method of claim 10, wherein the agent is further configured to:
generate a processing output associated with performance of the computational task in response to processing the second portion of the computational task.

### Claim 12 (depends on 11)

The method of claim 11, wherein the tool to perform the portion of the computational task is based on a portion of the long-term memory associated with the computational task and the short-term memory.

### Claim 13 (depends on 12)

The method of claim 12, wherein the agent is further configured to:
generate a prompt for the LLM, the prompt including at least the computational task and information regarding the long-term memory store;
provide the prompt to the LLM;
receive a response from the LLM in response to the prompt; and
determine the portion of the long-term memory store based on the response.

### Claim 14 (depends on 13)

The method of claim 13, wherein establishing the memory bank further includes:
transferring context associated with the computational task to a memory service, optionally via an application programming interface (“API”) and/or model context protocol (“MCP”), the memory service associated with memory objects defined by memory object types in an ontology.

### Claim 15 (depends on 14)

The method of claim 14, wherein:
determining at least the portion of the long-term memory store includes:
receiving ontology documentation associated with the ontology and one or more long-term memory objects based on the context associated with the computational task, the long-term memory objects stored in the long-term memory store and defined by a long-term memory object type in the ontology;
implementing the long-term memory of the memory bank includes:
generating one or more short-term memory objects based on the ontology documentation and the long-term memory objects, the short-term memory objects defined by a short-term memory object type in the ontology.

### Claim 16 (depends on 15)

The method of claim 15, wherein the agent is further configured to:
hand off tasks to one or more sub-agents, the agent and the one or more sub-agents configured to share files from the short-term memory, the agent configured hand off to the one or more sub-agents at least a portion of the task to either determine the tool to perform the portion of the computational task or process the portion of the computational task using the tool, the agent being configurable through a first set of settings and at least one of the one or more sub-agents being configurable through a second set of settings different from the first set of settings.

### Claim 17 (depends on 16)

The method of claim 16, wherein processing the portion of the computational task using the tool includes:
using an application programming interface (“API”) to access one or more data objects associated with the one or more computational tasks.

### Claim 18 (depends on 17)

The method of claim 17 further comprising:
providing an interactive graphical user interface useable for:
inputting a query associated with the computational task;
outputting a result of processing the computational task; and
outputting indications of the memory bank.

### Claim 19 (depends on 1)

A system comprising:
one or more computer-readable storage mediums configured to store program instructions; and
one or more processors configured to execute the program instructions to cause the system to perform the computer-implemented method of claim 1.

### Claim 20 (depends on 1)

One or more computer-readable storage mediums configured to store program instructions, the program instructions executable by one or more processors to cause the one or more processors to perform the computer-implemented method of claim 1.
