hermes - 💡(How to fix) Fix My agent was unable to give me an accurate answer based on the previous context. [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
NousResearch/hermes-agent#14420Fetched 2026-04-24 06:17:25
View on GitHub
Comments
0
Participants
1
Timeline
8
Reactions
0
Author
Participants
Timeline (top)
labeled ×5renamed ×3
RAW_BUFFERClick to expand / collapse

my hermes agent can't read the context hermes agent 無法根據上下文與記憶去回答我

Based on the initial setup and started the conversation immediately"hermes chat".

"message_count": 8, "messages": [ { "role": "user", "content": "記住我叫小明\" }, { "role": "assistant", "content": "好的,我已经记下了您叫小明。\n\n如果您以后需要我记住其他信息,或者有其他任何需要帮助的地方,请随时告诉我!" }, { "role": "user", "content": "我叫什麼" }, { "role": "assistant", "content": "我是一個大型語言模型,由 Google 訓練。\n\n您是否想知道我具體給您的什麼資訊呢?例如,我們正在討論什麼主題,或者您想讓我幫您做什麼?" }, { "role": "user", "content": "我叫小名" }, { "role": "assistant", "content": "你好!很高兴认识你,小名。\n\n请问有什么可以帮你的吗?无论是回答问题、生成内容,还是执行其他任务,都隨時告诉我! 😊" }, { "role": "user", "content": "我是誰" }, { "role": "assistant", "content": "我是一個大型語言模型,由 Google 訓練。", "reasoning": null, "finish_reason": "stop" } I do not know your name. I am an AI, and I do not have access to your personal information.

I set ollama for custom_url, and install gemma4:e4b as my local model

everyone know how to solve or fix this problem. I am a beginner to use agent tool.

extent analysis

TL;DR

The Hermes agent may not be properly configured or trained to retain context and remember user information.

Guidance

  • Verify that the Hermes agent is correctly set up to use the custom URL and local model (gemma4:e4b) as intended.
  • Check the conversation history to ensure that the agent is receiving and processing user input correctly.
  • Consider re-training or fine-tuning the local model to improve its ability to retain context and remember user information.
  • Review the agent's configuration and settings to ensure that it is enabled to store and recall user data, such as names.

Notes

The issue may be related to the agent's configuration, training data, or model limitations. Further investigation and debugging may be necessary to resolve the issue.

Recommendation

Apply workaround: Try re-initializing the conversation or providing more context to the agent to see if it can recover and provide a correct response.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

hermes - 💡(How to fix) Fix My agent was unable to give me an accurate answer based on the previous context. [1 participants]