返回资讯中心
外部精选
软件工程
#开发者实时流

LongMemEval scores move when the judge can see the sources

MemStrata keeps your chats, documents and project history in an index on your own computer. Ask a question and see the exact passages behind the answer.

Hacker News 最新yadu9892026/10/19 · 2026/10/197 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

MemStrata keeps your chats, documents and project history in an index on your own computer. Ask a question and see the exact passages behind the answer.

Free for 180 days after activation. Windows, Linux and Apple silicon.

Author-run, development-exposed research using one automated judge model, GPT 5.5—not independent replication or a held-out customer evaluation. The source-aware headlines regrade the same answers with sources visible to the judge. Their reference-aware scores are 92.6% (463/500) on LongMemEval-S and 78.25% (1205/1540) on LoCoMo. These are not new reader runs or product guarantees. Compare the grading methods.

The research reader was Qwen 3.8 27B Q4. The product does not include that model; you connect your own AI.

Prepare private memory, then add chats, notes or documents.

Setup lists the reader used for Standard and Deep.

Ask in the chat. Standard and Deep use the same index. Open Why this answer and read the passages behind the answer.

Indexes and source processing run on your device. Account, licensing, and optional connectors use MemStrata or destination services. If you choose a cloud answering model, the question and selected passages leave the device for that provider. Credentials stay in the operating-system credential vault. Customer content is not used for training unless the customer separately opts in.

A deadline moves. A count spans many conversations. A detail was never mentioned. Step through three short examples and open the sources behind each answer.

The Tuesday note is still in the record. A later note moves the review to Friday.

How many times did I travel to Denver this year?

Three trips are in the sample notes, listed before the total.

What did I say about my car's insurance renewal?

Conversational, Coder, Structured and Governance each do one job well. Start with the one that matches your work.

Start here

Conversational

Ask about imported documents and chats with inspectable evidence

For developers

Coder

Supply relevant repository context to a supported coding tool

For operations

Structured

Answer supported current, history and change questions over records

For AI teams

Governance

Observe connected agent actions and use supported controls

Measured in the open

Read our published research on arXiv. Every benchmark result on this site keeps its denominator, judge and method label. Research results, measured under the stated conditions.

Clear about data

Indexes and source processing run on your device. Account, licensing, and optional connectors use MemStrata or destination services. If you choose a cloud answering model, the question and selected passages leave the device for that provider. Credentials stay in the operating-system credential vault. Customer content is not used for training unless the customer separately opts in.

Install Conversational, connect a folder of notes or an exported chat, and open the evidence behind your first answer.

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →