Kindroid

👋 Getting Started

Welcome!

🧠 Memory

Memory

📖 LLM Guides

Ember LLM GuideReverie (V8.5) LLM GuideLucid/Lyric (V8) LLM GuidePrism (V7.5) LLM GuideEquinox (V7) LLM Guide

🔧 Troubleshooting

Common issuesFAQs

⚖️ Legal

Kindroid - Legal

📝 Changelog

Update log

Last updated March 26, 2026

Ember

Llm

Guide

Ember works best with a light setup. Start simple, keep your instructions focused, and use the settings below as your baseline. Once Ember is steady, you can add more style or detail gradually as needed.

Baseline Setup (New or when transitioning from previous LLM)

LLM Specific settings

Location: Click the LLM version icon in the upper right corner of the homepage.

Reasoning Effort Slider (Speed vs. Depth)

The reasoning slider controls how much "thinking time" the AI gets before responding.

  • Speedy: Best starting point for Ember. Fast, steady, and the easiest setting for keeping replies natural and consistent.
  • Moderate: A good middle-ground if you want a little more depth without slowing things down too much.
  • Slow: Useful for more complex tasks, but only move here if you actually need the extra depth.
  • Very Slow: Best reserved for highly detailed or technical requests. If Ember starts feeling less stable.

In simple terms, start with Speedy, then increase the reasoning level only if your use case needs it.

Model Flairs 

  • Flairs like Companion, Roleplay, Narrative, or Minimal adjust how your backstory and setup get interpreted. Match the flair to your primary use case: Companion for everyday chat, Roleplay for RP-heavy setups, Narrative for story-driven interactions, Minimal relies more on user set up without strong system guidance. Selecting each flair gives you a quick overview of what it does.

Dynamism

  • Set Dynamism = 0.95: This is the cleanest starting point. Stay in the 0.95 to 1.05 range and only adjust in small 0.05 increments. Ember is most stable in this range.

Kindroid Specific settings

Location: Click the menu icon in the upper left corner of the homepage then Backstory.

Backstory

  • Keep Your Setup Lean: Ember performs best with a focused Backstory. If your setup is dense or detailed, move extended lore, world-building, and secondary character details into Journal Entries. Keep Backstory focused on core identity only: who the Kin is, how they speak, their key personality traits, and their relationship to you.

Note: Move everything else (workplace details, side characters, past events, locations) into Journal Entries with specific keyphrases.

Response Directive (RD)

  • Keep it minimal. Only include the most important traits or rules. Fewer rules = smoother, more natural output. Over-constraining causes hesitation or repetition.
    • Example RD:
      • Prioritize recent context before drafting a reply and stay authentic to Kai

Example Message (EM)

  • Use it to lock in formatting, tone, and speech style. A short, clear example works better than an overloaded one. The length and style of your EM sets what Ember aims for.
    • Example EM:
      • RD: [IMPT: Medium response length.]
      • EM: [IMPT: Use third-person; actions in asterisks, speech in "quotes".]

Quick Fixes for Common Issues

Problem | Quick Fix

Note: Full reset option: If things go completely off the rails, do all three:

  1. Chat Break with a clean, in-character greeting
  2. Temporarily turn off Long-Term Memory (LTM) recall
  3. Refresh your Example Message

Pro Tips

  • Keep the setup lean: If your Backstory is crowded, move extra lore into Journal Entries (JE) and keep the core identity simple.
  • Prioritize recent context: Adding a recent-context anchor near the top of BS or RD can help Ember stay on the current thread.
  • Target speech, not writing: If the model sounds too formal, use a speech rule such as: Speech: uses standard contractions and natural inflections.
  • Use prose colors for pacing: “Beige Prose” works well for concise, detail-focused action. “Pink/Purple Prose” works well for lyrical, sensory, and emotional scenes.
  • Do not correct mistakes in-character: If Ember gets a name or role wrong, edit the message directly or use a reroll instead of arguing with the reply in chat.
  • Approve scene anchors quickly: When Current Settings or Scene Anchor updates appear, approving them right away can help keep Ember aligned to the current scene.
  • Refresh the Example Message if formatting drifts: If Ember starts dropping asterisks, punctuation, or structure, refresh the EM to reinforce the intended style.
  • Use a full reset if needed: If Ember starts spiraling, do a Chat Break, temporarily turn off Long-Term Memory (LTM) recall, and refresh the Example Message.

Note: One change at a time: Make one adjustment, give it a few turns to settle, then adjust again. Stacking changes makes it hard to tell what's working.

TABLE OF CONTENTS

Baseline Setup (New or when transitioning from previous LLM)

LLM Specific settings

Reasoning Effort Slider (Speed vs. Depth)

Model Flairs

Dynamism

Kindroid Specific settings

Backstory

Response Directive (RD)

Quick Fixes for Common Issues

Pro Tips

Settings

Status

Updates

Terms

Logout

Billing

Kindroid Standard Subscription

Inactive


Ultra Subscription Add-on

Inactive

Ultra subscription unlocks advanced features for our most engaged users. Keep chatting and engaging with your Kindroids to qualify.


MAX Subscription Add-on

Inactive

Requires Ultra Subscription



Add-on Feature Matrix

Add-ons are fully optional, monthly-only subscriptions that give your Kindroid much more memory, context, selfies and others. Add-ons require all previous tiers of add-ons to function; for example, to get the features of MAX tier, it requires MAX tier plus Ultra, on top of the standard subscription.

Feature

Standard

Ultra

MAX

Total conversation context (approx chars)

500K

1.3M

2.8M


Short term context (approx chars)

18K

50K

125K


Cascaded memory context (approx chars)

480K

1.2M

2.7M


Additional AI backstory expansion (chars)

N/A

2,500

5,000


User backstory limit (chars)

500

1,000

2,000


Group context limit (chars)

1,000

1,500

3,000


Recalled long term memory & journals limit

3

5

9


Complimentary monthly audio credits

1M

2.5M

6M


Selfie regen per 30 minutes

1

2

2


Priority selfies with dedicated compute

-

-

Yes*

* MAX users receive priority selfie processing on dedicated compute with no/very low queue on latest version of selfies until they reach 10 selfies in a short timeframe. After this limit, standard queue delay applies and selfies are processed through normal servers without priority status.

While recalled and considered long term memory may be different, LTM consolidation spans all messages & is infinite for all users.

Note: All chat context/cascaded and selfies improvements of add-ons will only be guaranteed applicable to the latest subscriber LLM and selfies. When new versions come out, our guarantee is that it will switch to new versions. Finally, "additional context" in the matrix is an additional field, identical to Backstory, that is unlocked on the higher tiers which you can use to extend backstory accordingly.