@witcheer: someone in the community worked on a real benchmark of seven self-hostable memory providers for Hermes Agent, each fed …
Summary
A community member benchmarked seven self-hostable memory providers for Hermes Agent, testing each with 71,060 conversation turns and 3,750 questions about changing facts; full results and GitHub repo are in the thread.
View Cached Full Text
Cached at: 08/10/26, 03:25 AM
someone in the community worked on a real benchmark of seven self-hostable memory providers for Hermes Agent, each fed the same 71,060 conversation turns and quizzed with 3,750 questions about facts that change over time.
I am personally using Hermes Agent built-in memory paired with Obsidian, which works wonderfully, but I know a lot of you are using a third party memory provider.
full thread with github repo:
Similar Articles
@KSimback: https://x.com/KSimback/status/2058262328496554021
A comprehensive guide to memory systems for Hermes Agent, explaining the three-layer memory architecture and comparing various memory tools and providers.
@smykx: last month i wrote a blog on memory internals of hermes-agent by @NousResearch link in replies
The author shares a blog post detailing the memory internals of the Hermes-Agent framework developed by Nous Research.
Question: how should Hermes agents handle persistent memory across sessions?
A community discussion about how Hermes agents should handle persistent memory across sessions, exploring an external memory layer (8mem) and comparing memory-aware vs generic outputs.
@witcheer: a Hermes community builder shipped Synapse, a very cool addition to your agent the pitch in one line: memory that forge…
Synapse is an open-source, self-hosted synthetic hippocampus for AI agents, using a temporal knowledge graph (Graphiti + FalkorDB) with salience scoring and Ebbinghaus forgetting curve to manage memory decay and consolidation, integrated as a Hermes agent memory provider.
@mr_r0b0t: hermesbench v0.1 — a benchmark purpose-built for Hermes Agent tool-calling Runs real Hermes Agent subprocess in an isol…
hermesbench v0.1 is a new benchmark for evaluating local models on Hermes Agent tool-calling, featuring real agent harness, deterministic verifiers, and hardware telemetry. It includes 43 tasks across 11 categories and is designed to measure how well models use the Hermes Agent.