Status
SteamPeaks
ChartsSalesUpcomingPatchesNewsCalculator
New on SteamEvery app, DLC and depot the minute Steam creates itAppsEvery app on Steam, newest change firstPackagesSubs and bundles, and what each containsDepotsDepots, manifests and install sizesTagsSteam's user tags and the games under themDevelopers & publishersCompanies and their cataloguesTechnologiesEngines, SDKs and anti-cheat found in the filesChange historyEvery PICS changelist as it lands
SignalsNineteen readings of the whole catalogueCompareAny games side by sideRecordsAll-time peaks and the days they were setReportsWeekly and monthly write-upsAlerts & newsroomWatch a game, get told when it movesSteam statusIs Steam up, right nowWeb API explorerTry the endpoints in the browser
NewsSteam's own announcements and the sales calendarCalculatorWhat a Steam account is worth, and its pile of shame
/
Sign in
/
SteamPeaks
The ultimate resource for Steam data.
ExploreChartsSalesSales and festsUpcomingPatchesNewsRecordsTrendingSignals
DatabaseAppsPackagesDepotsTagsDevelopersTechnologiesChange history
ToolsCalculatorCompareSearchAlertsSteam statusAPI
SiteMethodologyFAQDiscordSupportSign in via Steam
Not affiliated with Valve or Steam. Game names and artwork belong to their owners. All times UTC.
PrivacyCookiesFair useStatus
AI Pals EngineNewsDevlog #4: AI Pals That Remember You + Changelog
Community

Devlog #4: AI Pals That Remember You + Changelog

AI Pals Engine · published 15 Mar 2026, 15:50 UTC

All newsPlayers around this dateRead on Steam

Happy Sunday! ☀️

The latest update introduced the automatic mode for GPU layers. This is also planned for the chat format, which should make things a lot easier (as promised in the Early Access description).

If you run into issues with automatic mode, let me know, it will likely become the default in later versions. Also I'm curious: How are the new Qwen3.5 models performing in non-English languages? I was positively surprised how they performed in my image interpretation tests.

This devlog is about the memory functionality, which is a bit of a complex topic and the access to it a little hidden, so let's look at how it works.


🧠AI That Remembers

Imagine talking to an AI Pal that remembers details about you. Not just within a single conversation, but across long chats, roleplays or documents. That’s the idea behind the memory system.

The Context Window Problem

If you've used AI and AI Pals Engine, you know the context window: the maximum amount of text a model can process at once.

A few years ago, getting 4096 tokens in a local model was already impressive. Today we have much larger contexts, but they still have limits and roleplay world descriptions, documents and long conversations can exceed them (and of course your hardware).

Instead of trying to fit everything into the context, the memory functionality uses a different approach.

Memory as Search

The system works similarly to the web search tool we look at in this Devlog, but instead of searching the internet, it searches a local memory database.

Example

User question:

"What was the name of the city my character came from again?"

Due to semantic search the system can retrieve relevant entries, even if the original text looked like:

"Elira was born in the coastal city of Vaelthorne."

Why This Matters

The AI Model itself is static and can't add information on the fly. Using the memory approach allows the AI to access information that goes far beyond the model's context window. Without memory systems, long-running interactions eventually lose important details.

Practical benefits:

  • Conversations stay coherent over time – even very long chats won't lose key information or earlier decisions.

  • World lore and documents stay accessible – roleplay settings, guides, manuals or research notes can all be referenced during chat.

  • Remembers important details – characters, story events, personal preferences or ongoing projects can come up again later.

  • Large documents become usable in chat – instead of pasting them repeatedly, the AI can retrieve relevant sections when needed.

  • Your own knowledge base – you can build a personal database of information the AI can search and use as a general reference.

  • Less repetition – you don’t have to keep re-explaining the same context or background information.

✅ Can I Use Memory in AI Pals Engine?

Yes, you can enable Memory in the Char's Config. Your input will then be compared with entries in the database using embedding similarity.

At the moment:

  • Each Widget uses a shared memory (Char-independent)

  • The chatview/testview has memory per Char

You can access the memory view in the sidepanel, where you can:

  • Paste in text

  • Load documents

  • Manipulate current memory entries

You can also store conversations that are removed when the context becomes too long, this is configurable in the Char's Config.

When memory is enabled, the {{memory}} token is automatically replaced with actual memory entries.

Example

This Char's memory includes the entire American Bible Standard Edition, which is a little less than one million tokens of text.

For the test we'll add additionally: the secret word is 'Curiosity'

👉 Out of 5578 text chunks, it still is able to retrieve the right information to phrase the correct answer to "What is the secret?"

🔍 How Could We Further Improve the Memory Functionality?

The current system uses similarity-based comparison, which means you might not always get the most relevant entries, just like how web search doesn't always return perfect results. So, there's always room to improve lookup accuracy.

Even more importantly: it would be powerful to build functionality on top of memory entries. Imagine an AI that:

  • Continuously transforms new memory entries into meaningful insights

  • Compresses information so you can inject more (or all) information

  • Learns about your RP history or personal patterns

  • Analyzes your behavior

Right now, you can experiment with this manually:

  • Multi-select messages → copy → transform via AI → re-enter into memory

Enable “Auto-load the last conversation” in the widget settings to ensure the conversation grows long enough for messages to be transferred to memory.

❗As with any of the features, Memory will become more integrated over time and easier to use. Let me know if you think it's worth adding an automatic layer, maybe using a fast, lightweight model to handle tasks like summarization or compression automatically!


🌅What's on the Horizon for AI Pals Engine?

  • Speech-To-Text Wake Word

  • Better Audio integration

  • More of the following: Help pages, Internationalization, Fixes, QoL Improvements

📝Changelog V0.8.18.0

Summarized from smaller updates deployed since the last Post:

✨ New Features

  • Presets - GPU Auto Mode: Auto GPU Layer Selection + MoE Speed Optimizations (when enabled)

  • Presets: Basic Device Support (GPU selection)

  • Extended Model Support: Added Qwen35 and other hybrid model support

  • Char Config: Available Dynamic Tokens Overview

  • Char Config: ST Card Exporter/Importer

🔧 Improvements

  • Char Config: Increased text limits

  • Char Config: Aiprepend/Userappend now parse dynamic tokens

  • Char Overview: "Load in Widget" now temp-loads and starts a fresh conversation (instead of just selecting it in the widget settings)

  • TTS: Better handling of non-English-only sentences

  • Memory: Multiselect + enhanced info & usability

  • Help: Group Chat and the Memory pages have been improved

🐞 Fixes

  • Fixed Widget Temporary Char dependency loading

  • Fixed duplicate key error on context overflow and chat memory enabled

More from AI Pals Engine

Other announcements

All news
In-game event11 Aug 2026Update V0.10.0: Moving to Runtime V2 + Changelog 🛠️Hey everyone! 👋 The publictest version has been updated to V0.10.0 . This is a major structural change. Runtime V2 completely replaces the old one. In the past, a lot of Python "glue code" was necessary between AI Pals Engine and the inference engine (llama.cpp). This layer was a necessity then, but it's becoming more and more redundant as the inference engine evolves. The goal of Runtime V2 w…Community3 Apr 2026Google Gemma 4 & Devlog #5: State/Mic Check, Workshop and Bundles + ChangelogHappy Easter in advance 🐰! Yesterday, Google gifted us Gemma 4 in multiple variants and experimental support has been added to the Steam publictest version and other editions since then (see inapp Recommended Models ). Model Parameter Size Context Window Gemma 4 E2B 2.3B effective (5.1B w/ embeddings) 128K Gemma 4 E4B 4.5B effective (8B w/ embeddings) 128K Gemma 4 31B 31B dense model 256K Gemm…Community25 Feb 2026Model News + Changelog: Qwen 3.5AI Pals Engine allows you to hook in any model through a custom endpoint, but for convenience, it aims to support as many local models as possible natively . If you notice a model isn’t working smoothly or a new model release isn’t getting the spotlight it deserves, head over to the Community Hub to let us know. Please also let me know if you would like to receive more information about model r…