# Shared Selective Persistent Memory for Agentic LLM Systems

DevFeed: [Shared Selective Persistent Memory for Agentic LLM Systems](<https://devfeed.tech/articles/shared-selective-persistent-memory-for-agentic-llm-systems-30891.md>)

Original publisher: [Read original article](<https://machinelearning.apple.com/research/shared-selective-persistent-memory>)

Published: 2026-09-16T00:00:00Z

Content type: article

Language: en

Sources: [Apple Machine Learning Research](<https://devfeed.tech/sources/apple-machine-learning-research.md>)

Topics: [Large Language Model](<https://devfeed.tech/topics/llm.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Framework](<https://devfeed.tech/topics/framework.md>), [Code](<https://devfeed.tech/topics/code.md>), [configuration](<https://devfeed.tech/topics/configuration.md>), [Access Control](<https://devfeed.tech/topics/access-control.md>), [Git](<https://devfeed.tech/topics/git.md>), [Model Context Protocol (MCP)](<https://devfeed.tech/topics/model-context-protocol-mcp.md>), [CSV](<https://devfeed.tech/topics/csv.md>), [SQL](<https://devfeed.tech/topics/sql.md>), [Grafana](<https://devfeed.tech/topics/grafana.md>)

Tags: [access-control](<https://devfeed.tech/tags/access-control.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [code](<https://devfeed.tech/tags/code.md>), [configuration](<https://devfeed.tech/tags/configuration.md>), [csv](<https://devfeed.tech/tags/csv.md>), [dashboards](<https://devfeed.tech/tags/dashboards.md>), [git](<https://devfeed.tech/tags/git.md>), [llm](<https://devfeed.tech/tags/llm.md>), [mcp](<https://devfeed.tech/tags/mcp.md>), [memory](<https://devfeed.tech/tags/memory.md>), [platform](<https://devfeed.tech/tags/platform.md>), [replication](<https://devfeed.tech/tags/replication.md>), [sql](<https://devfeed.tech/tags/sql.md>)

## AI overview

This research introduces shared selective persistent memory for agentic LLM systems. The architecture retains reusable task specifications, data schemas, tool configurations, and output constraints while discarding session-specific reasoning traces. Shared workspaces support role-based collaborative reuse, and experiments report higher task completion than no memory or full-history persistence, along with zero-token data refresh and lower token costs.

## Source excerpt

Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive. Naively persisting entire conversation histories is both token-inefficient and counterproductive--irrelevant context degrades generation quality. We introduce shared selective persistent memory, a memory architecture for agentic systems that identifies and retains four categories of reusable context--task specifications, data...