Built on palace-rsAn open foundation.
An open foundation.
An inspectable memory.
The MIT-licensed local engine powers retrieval. Palace Server adds the shared team layer and PostgreSQL-backed deployment.
A concrete retrieval resultMeasured recall.
Measured recall.
With the context attached.
On the LongMemEval s_cleaned evaluation, the exchange-pair configuration retrieves a relevant session within the first five results for 98.7% of evaluated questions. No LLM and no GPU are involved at any stage.
98.7%RECALL @ 5
470QUESTIONS
MITCORE LICENSE
What this number meanspalace-rs engine benchmark; exchange pairs with the default
minilm-l6-v2-q8 model; recall_any at session granularity. The 30 abstention questions are excluded, as is standard. It measures retrieval by the engine inside Palace Server.| Configuration | Recall @ 1 | Recall @ 5 | Recall @ 10 |
|---|---|---|---|
| Exchange pairs, as Palace stores conversations | 91.5% | 98.7% | 99.6% |
| One drawer per session | 89.8% | 98.1% | 99.1% |
Source: the palace-rs README. Review the method and reproduce it ↗
Local for an individual.
Shared for a team.
palace-rs runs locally with SQLite and provides the memory tools, free for any solo developer. Palace Server is the commercial, self-hosted team service: shared memory, organization access controls, audit records, and PostgreSQL storage.
Put your knowledge to workGive your next session
Give your next session
a head start.
Start your team trial
60 days · 10 seats · No credit card