xmemory

xmemcli command-line client and the agent skill.

How xmemory works, how to define schema-based memory, and where to start integrating it into agentic workflows.

MCP integration guide.

Complete guide to XMD v1 objects, fields, enums, defaults, primary keys, relations, descriptions, validation, and schema design.

Toloka evaluated xmemory with 11 models in about 20k graded runs. Lessons from past runs raised scores, including on tasks not used to write them, and xmemory's compact answers cut the bill by 26%.

Posts on schema-first memory and agent reliability.

TypeSafe’s Jev identified nearly all invented values in an extraction cascade while improving accuracy by 81% between fast/cheap and slow/expensive extractors, re-running 38% of records.

xmemory and Temporal are partnering to bring reliable execution and shared, structured state to developers building long running agents.

Subscription plans, usage quotas, deployment options, security, and contact information.

How xmemory compares with other agent memory products and with the architectural patterns teams reach for instead. Short, evidence-linked pages, one per alternative, with an XMD schema showing the equivalent in xmemory.

Cognee turns documents into a knowledge graph and answers over it; its custom graph models are the nearest thing to a schema among memory tools. xmemory owns the schema at the instance and resolves every natural-language write against stored state, so memory behaves as state rather than as a corpus.

Letta is an agent runtime whose memory is a git-backed filesystem of Markdown the agent edits itself, consolidated by background "dreaming" subagents. xmemory is a memory engine with a schema the instance owns, so facts are records resolved on write and queried as state, from any runtime.

Mem0 stores extracted facts as ranked text, while xmemory runs user-defined memory schemas, supporting both Mem0-style fact capture and structured state as workflows evolve.

xmemory's mission, team, company background, offices, and contact information.

Interactive demo of the natural-language write/read memory loop.

xmemory lets users define extraction, storage, and updates using schemas as a programming language, executed alongside evolving workflows.

xmemory Inc. describes how it collects, uses, stores, shares, and protects user information through its website, console, APIs, OAuth flows, and related services.

GitHubRepository owner

Toloka and xmemory collaborate to evaluate how memory impacts AI agent performance. The Toloka Arena platform allows users to benchmark their AI models directly. This initiative explores whether memory integration enhances AI capabilities in practical applications.

Oct 2026toloka.aiNews article

xmemory emerges from stealth with a £3 million pre-seed funding round to develop infrastructure for AI workflows. Fly Ventures leads the investment, supporting the company’s focus on building a dedicated memory layer for AI systems. The funding will accelerate product development and technical innovation in AI memory solutions.

Mar 2026uktechnews.infoNews article

xmemory, a London-based AI startup, secures £3m pre-seed funding to build a write-time memory layer. The company targets improvements in AI reliability and governance through its precision-focused technology. The funding supports early-stage development of hardware or software solutions for AI systems.

Mar 2026Startupmag.co.ukNews article