---
type: "post"
slug: "warp-agent-memory"
title: "Warp Agent Memory"
description: "Warp's Agent Memory keeps durable facts and decisions on the server and shares them across harnesses, so what one agent learned is available to Claude Code, Codex or a teammate next."
retrieval_nugget: "Warp's Agent Memory keeps durable facts and decisions on the server and shares them across harnesses, so what one agent learned is available to Claude Code, Codex or a teammate next."
published_at: "2026-09-01"
updated_at: "2026-09-12"
record_date: "2026-08-25"
date_kind: "discovered_at"
topics: ["agent-memory","agents","ai","memory"]
entities: ["Warp"]
source_url: "https://docs.warp.dev/agents/agent-memory"
source_title: "Agent Memory (Research Preview)"
source_domain: "docs.warp.dev"
source_terms: ["Warp","Memory","page","Preview","Copy"]
summary_word_count: 188
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:warp-agent-memory"
status: "published"
source_urls: ["https://docs.warp.dev/agents/agent-memory"]
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:273e6aa71f6bcd89170a6bcc805e0093269d4c0bcdf19978e4dc41887fa08ac6","reviewed_at":"2026-09-12T10:00:00Z","source_evidence_count":1,"verified_claim_count":2,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":2,"implication_count":1,"watch_condition_count":1,"related_record_count":3}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Warp documented Agent Memory, a research-preview persistent memory system that lives on Warp rather than inside a single agent.","observed_facts":[{"text":"Agent Memory is shared across supported harnesses including the built-in Warp Agent, Claude Code and Codex.","source_urls":["https://docs.warp.dev/agents/agent-memory"]},{"text":"Memory creation and retrieval run asynchronously in the background, and the feature is enabled per team for design partners.","source_urls":["https://docs.warp.dev/agents/agent-memory"]}],"mechanism":"agents read from and write to it as they run, so durable facts, decisions and outcomes from one conversation are available to the next regardless of which harness, machine or teammate triggers the work","why_now":"It is shared across every supported harness — the built-in Warp Agent, Claude Code, Codex and others as they are added","implications":["It makes the memory a shared team asset rather than a per-tool convenience, and it also relocates the governance question: whatever is written becomes visible to the next harness that reads it, including one a different person started."],"evidence_boundary":"This is research-preview documentation gated to design partners: it describes behaviour without published retention, scoping or redaction rules for what agents write.","watch_conditions":["The condition to watch is whether memory writes become reviewable before they are shared, because a cross-harness memory that accepts whatever one agent concluded propagates its mistakes just as efficiently as its facts."],"related_records":[{"url":"https://newruntime.com/posts/portable-agent-session-test","relation":"Prior coverage of portability as the real lock-in test."},{"url":"https://newruntime.com/patterns/company-memory-needs-write-loops","relation":"Existing pattern on write loops for durable company memory."},{"url":"https://newruntime.com/topics/agent-memory","relation":"Topic hub for where agent memory lives."}]}
routes: {"html":"https://newruntime.com/posts/warp-agent-memory/","markdown":"https://newruntime.com/posts/warp-agent-memory.md","json":"https://newruntime.com/posts/warp-agent-memory.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# Warp Agent Memory

## Retrieval answer

Warp's Agent Memory keeps durable facts and decisions on the server and shares them across harnesses, so what one agent learned is available to Claude Code, Codex or a teammate next.

Warp documented Agent Memory, a research-preview persistent memory system that lives on Warp rather than inside a single agent. It is shared across every supported harness — the built-in Warp Agent, Claude Code, Codex and others as they are added — and agents read from and write to it as they run, so durable facts, decisions and outcomes from one conversation are available to the next regardless of which harness, machine or teammate triggers the work. Creation and retrieval run asynchronously in the background, and access is enabled per team for design partners from a waitlist.

Putting memory outside the harness is the interesting choice. It makes the memory a shared team asset rather than a per-tool convenience, and it also relocates the governance question: whatever is written becomes visible to the next harness that reads it, including one a different person started.

That is exactly the property tested by [the agent lock-in test being a full session export](https://newruntime.com/posts/portable-agent-session-test/), and it is the write-loop argument recorded as a pattern in [company memory needing write loops](https://newruntime.com/patterns/company-memory-needs-write-loops/). The [agent memory hub](https://newruntime.com/topics/agent-memory/) tracks where that state is allowed to live.

This is research-preview documentation gated to design partners: it describes behaviour without published retention, scoping or redaction rules for what agents write. The condition to watch is whether memory writes become reviewable before they are shared, because a cross-harness memory that accepts whatever one agent concluded propagates its mistakes just as efficiently as its facts.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Agent Memory](https://newruntime.com/topics/agent-memory.md): Explore the agent-memory topic hub.
- topic hub: [Agents](https://newruntime.com/topics/agents.md): Explore the agents topic hub.
- topic hub: [Ai](https://newruntime.com/topics/ai.md): Explore the ai topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)