Atraium 0.3.1 Preview 1

Atraium 0.3.1 Preview 1

Atraium 0.3.1 Preview 1 is a major experience release. It modernizes the conversation, workspace, navigation, settings, and administration surfaces; turns Model Providers into a first-class workflow; adds persisted Light, Dark, and System themes; improves long-conversation reliability; and expands reasoning and token-usage support across providers.

Recommended target

• Windows desktop: recommended preview experience
• Android: not included in this release unless listed in the attached assets
• Web: not currently supported

Highlights

A redesigned conversation experience

The main chat surface has been rebuilt around a cleaner, more focused conversation canvas.

• Assistant and user turns use a flatter, more readable visual hierarchy.
• On wide layouts, the assistant response appears first, followed by reasoning and tool activity so live work remains near the bottom of long turns.
• On compact and mobile layouts, process information remains before the response for easier conversational scanning.
• Reasoning has a dedicated disclosure instead of being mixed into the visible response.
• Tool activity uses a structured timeline with clearer running, completed, failed, and attention states.
• Activity now fills the complete assistant-turn width.
• Message actions, attachments, code, Markdown, and generated artifacts have more consistent spacing and responsive behavior.
• The composer has been simplified and remains anchored to the conversation column.
• Empty, loading, error, and retry states have been standardized across chat surfaces.

More reliable long conversations

Long and virtualized conversations now open and navigate more predictably.

• A conversation initially renders its latest message window instead of visibly opening near the start and animating through the thread.
• Initial bottom positioning waits for the rendered layout to settle.
• Late content growth from images, Markdown, code blocks, and enhanced content is followed while bottom anchoring is active.
• Jump to latest now uses immediate, verified, retry-safe positioning rather than fragile smooth scrolling.
• Prepending older messages preserves the reader’s scroll position.
• A Chromium regression test covers layout growth after the initial anchor begins.

Better attachments

Attachment presentation has been rebuilt for both the composer and message history.

• Long filenames truncate safely without pushing remove, Preview, Download, or Copy controls outside the card.
• Full attachment names remain available through accessible tooltips.
• Compact cards reserve space for their actions and stay contained at narrow widths.
• Image previews, file metadata, and attachment actions use consistent responsive layouts.
• Workspace attachments have a dedicated browser for reviewing files associated with the active workspace.

Modernized workspace surfaces

Room and Workspace interaction now uses a more coherent shell.

• The conversation header, Workspace picker, and surface navigation have been redesigned.
• Workspace Tasks, Notes, Tools, Artifacts, and Attachments use consistent headers and inspector surfaces.
• Notes and Tasks have clearer empty states, filtering, editing, and action placement.
• Workspace context can use a persistent inspector on wide layouts and an overlay surface on compact layouts.
• The message canvas no longer competes with unnecessary nested outer cards.

New application navigation

The left navigation has been completely reworked.

• The compact rail shows a bounded set of pinned and recent rooms instead of an unbounded avatar column.
• The active room remains visible in the compact rail.
• A +N affordance exposes additional rooms.
• Expanded navigation includes room search, grouped rooms, and a flatter Manage section.
• Room selection uses native keyboard-accessible buttons, with pin and overflow actions kept separate.
• Desktop expanded and mini states are preserved.
• Mobile uses the same hierarchy in a temporary drawer.
• Windows title-bar and lower-edge insets are accounted for so the final navigation item remains visible.
• Model providers now has its own direct navigation destination.

Persisted Light, Dark, and System themes

Atraium now includes a complete appearance preference stored in UserPreferences.

• Choose System, Light, or Dark from Setup & Settings.
• Existing and new profiles default to System.
• Theme changes apply immediately and persist across restarts.
• System mode follows live Windows appearance changes.
• A desktop title-bar action provides a quick Light/Dark toggle.
• MudBlazor palettes and Atraium’s own semantic design tokens switch together.
• Chat, dialogs, navigation, attachments, inputs, code, diagnostics, file drop, image preview, and administration surfaces have dark-mode-aware colors.

Administration and settings parity

The remaining administration pages now follow the same modern design language.

Modernized surfaces include:

• Setup & Settings
• Guided Configuration
• Advanced Settings
• Model Providers
• Provider Profile Setup
• Backup & Restore
• Plugins
• MCP Servers

Common improvements include:

• consistent semantic page headers;
• pinned Back, navigation, Add, Upload, and Save actions;
• compact sticky headers on small windows;
• wider administration canvases on desktop;
• responsive and container-aware layouts;
• flatter cards and clearer section hierarchy;
• standardized loading and empty states;
• improved destructive-action placement;
• full Light and Dark theme support.

Guided Configuration also has a clearer step list, improved active-step status, container-driven responsive behavior, and a sticky Previous/Next/Save footer.

Model Providers as a first-class experience

Model Providers has been redesigned to make configuring, validating, routing, and switching models substantially faster.

Live capability routing

A new Live routing dashboard shows what currently powers every model capability:

• Chat
• Utility
• Embeddings and memory
• Image generation
• Realtime
• Text-to-speech
• Speech-to-text

Each capability shows its active profile and only compatible alternatives. Selecting another profile persists the route immediately for future requests.

Provider inventory and focused editor

The former nested profile accordion has been replaced with:

• a searchable provider inventory;
• stable profile selection;
• one focused editor at a time;
• visible provider, model target, routing usage, credential readiness, and health;
• advanced tuning that remains available without dominating the inventory.

Long provider and model names are contained and ellipsized rather than overflowing routing cards or editor columns.

Faster provider creation

The Add provider menu now includes starting templates for:

• OpenAI-compatible endpoints
• Anthropic Claude
• Google Gemini

Templates populate suitable endpoint, model, API mode, and pacing defaults while keeping every field editable.

Adapter-backed connection verification

The focused editor now includes Test connection.

• Verification uses the same shared OpenAI, Anthropic, and Gemini client construction as the assistant runtime.
• It performs a minimal non-streaming request with a short timeout.
• It sends no room, workspace, or conversation content.
• Credentials are never displayed in the result.
• Changing the endpoint, model, deployment, API mode, or credential invalidates a previous result so stale health is never shown.

Results are normalized into actionable states such as:

• Connected
• Endpoint required or invalid
• Model target required
• Credential required or rejected
• Model target not found
• Rate limited
• Timed out
• Provider unreachable
• Unexpected verification failure

A connection test is a real provider request and may incur a negligible provider charge.

Switch Chat models from the conversation

The room command bar now includes a Chat provider quick switcher.

• Switch the active Workspace Chat profile without leaving the conversation.
• Return to the inherited global Chat route when desired.
• Open Manage providers… directly from the switcher.
• A model change starts a fresh conversation target to avoid mixing incompatible provider context.

Model Providers is also directly accessible from the application navigation instead of requiring a trip through Settings.

Tagged reasoning from open-weight and non-OpenAI models

Atraium now recognizes reasoning emitted in these tags, case-insensitively:

<think>...</think>
<thinking>...</thinking>
<thought>...</thought>

• Tagged reasoning is removed from normal assistant Markdown.
• Extracted content appears in the existing reasoning disclosure.
• Tags split across streaming chunks are supported.
• Multiple and unclosed reasoning blocks are handled safely.
• Ordinary less-than text is not mistaken for a reasoning tag.
• Native provider reasoning and tagged reasoning can coexist.
• Reasoning is persisted in the assistant metadata envelope and survives history reloads.
• Older stored messages containing tags are separated when loaded.

This support applies across OpenAI Responses, OpenAI-compatible Chat Completions, Anthropic, Gemini, and other IChatClient-based providers.

Complete provider token-usage capture

Token usage is now captured and stored consistently across supported Chat paths.

• OpenAI Responses: input, cached input, output, and total tokens.
• OpenAI-compatible Chat Completions: streaming usage is requested with stream_options.include_usage and read from the final update.
• Anthropic: usage is collected from the provider’s Microsoft.Extensions.AI usage content, including multi-call tool workflows.
• Google Gemini: prompt, cached prompt, candidate, thought/reasoning, and total tokens.
• Duplicate usage objects are ignored.
• Usage reported before an interrupted ...

Atraium 0.2.3 Preview 1

Atraium 0.2.3 Preview 1

Atraium 0.2.3 Preview 1 introduces reusable Model Provider Profiles, granular Room and Workspace tool routing, safer Chat Completions context handling, and more capable Workspace actions for the assistant.

Recommended target

• Windows desktop: recommended preview experience
• Android: not included in this release unless listed in the attached assets
• Web: not currently supported

Highlights

Reusable Model Provider Profiles

Provider configuration is now centralized in reusable Model Provider Profiles. Configure a provider target once, then assign it wherever it is needed.

• Create, edit, filter, and delete reusable provider profiles from Settings -> Model providers.
• Store provider, endpoint, API mode, model, deployment, token limits, pacing, pricing, image settings, and credentials in one profile.
• API keys remain in secure platform storage and are not shown again after saving.
• Assign compatible profiles independently to Chat, Utility, Embeddings, Image generation, Realtime, Text-to-speech, and Speech-to-text.
• Advanced LLM settings now choose capability profiles instead of duplicating endpoints, keys, and model settings.
• Guided configuration now begins with provider-profile setup, followed by capability assignment.
• Existing per-capability settings remain supported as a compatibility fallback while you move to profiles.
• Open-weight models can be connected through a compatible OpenAI-style endpoint, including Qwen 3.5, Qwen 3.6, and KAT-Coder V2.5 variants where the serving stack supports the required API behavior.

Room and Workspace Chat profile overrides

Room and Workspace overrides now select a full Chat provider profile instead of overriding only a model or deployment name.

• A Room can override the global Chat profile.
• A Workspace can override its Room profile.
• Effective precedence is:

Workspace Chat profile -> Room Chat profile -> Global Chat profile

• A selected profile applies the complete Chat target: provider, endpoint, credentials, API mode, model, deployment, token limits, reasoning effort, sampling, pacing, and pricing.
• Atraium safely refreshes the affected Chat runtime at the next request boundary.

Flexible reasoning and sampling controls

Provider profiles better support modern reasoning models.

• Temperature and Top P are optional and clearable.
• Clearing either field omits that parameter from provider requests instead of sending a default value.
• This avoids unsupported-parameter failures from models that reject sampling options.
• Reasoning effort is now an autocomplete field with standard suggestions:

minimal
low
medium
high
xhigh

• Custom provider-specific reasoning values remain supported.

Fine-grained direct and gateway tool routing

Room and Workspace tool controls now separate availability from route.

• Configure sources and individual tools with inherited, enabled, or disabled availability.
• Route enabled tools through the Gateway or expose them Directly to the active model.
• Room policy establishes the baseline; Workspace policy can refine it.
• Direct routes are supported for Responses, Anthropic, and Semantic Kernel Chat Completions paths.
• Direct tools are registered correctly in the Semantic Kernel, including wrapped local tools such as the Text tools.
• Up to 24 catalog tools can be exposed directly; any overflow remains gateway-accessible.

Coding-agent compatible tool surface

Atraium now exposes a compact Coding tool source for models trained on common coding-agent conventions.

• Direct core tools are:

Read
Write
Edit
Glob
Grep
Bash
apply_patch

• The surface follows familiar Claude Code, Codex, OpenClaw, Cline, and Roo Code concepts while preserving Atraium's specialist tools.
• Common gateway aliases are accepted, including read_file, read_files, write_to_file, replace_in_file, search_files, execute_command, exec, shell_command, and apply_diff.
• Bash accepts one normal command. Its optional cwd is no longer required for ordinary project work: Atraium infers a safe working directory from accessible file or project paths and prefers a detected repository or solution root.
• apply_patch accepts the standard *** Begin Patch envelope with add, update, delete, and move operations.
• Read, Glob, and Grep provide lightweight discovery; Edit is preferred for exact targeted changes; Write is reserved for complete file replacement.
• The Coding source is direct by default when enabled, but Room and Workspace policy can disable it or route it through the gateway.
• Existing Text_*, structured configuration, Roslyn, Visual Studio, and document tools remain available for advanced or specialized work.

Assistant direct-tool access requests

The assistant can request direct access to an eligible catalog tool, but it cannot grant access to itself.

• Requests are stored as durable pending proposals scoped to the Room or active Workspace.
• Review proposals in Workspace -> Tools & access.
• Approve a request to apply the scoped Direct route, or dismiss it without changing access.
• Requests include the tool, source, scope, and assistant rationale.

Faster, organized Workspace Tools

The Workspace Tools surface is more responsive for large catalogs.

• The tool catalog loads lazily when Tools is opened and remains cached while moving between Workspace surfaces.
• Tool groups stay organized by source or category.
• Source-level policy controls remain immediately available.
• Individual tool controls are rendered only after expanding Fine-tune this category.
• Expanded category lists use virtualization to avoid building hundreds of routing controls at once.
• Search and an explicit catalog refresh action are available from the Tools surface.

More ergonomic Workspace actions

Assistant Workspace actions now avoid unnecessary round trips.

• Create tasks that are already complete with isComplete: true.
• Reuse IDs returned by Workspace create, update, and list operations directly.
• Update a task's title, description, priority, due date, and completion state in one operation.
• Delete tasks and notes when the user explicitly asks to remove them.
• Room and Workspace writes now use short-lived database contexts and bounded concurrency retries, reducing conflicts with simultaneous assistant or chat updates.

Chat Completions context caching control

Chat Completions profiles now include an advanced Chat Completions context caching option.

• Default: off. Atraium keeps the root system message stable and inserts current-turn context only into a cloned provider request immediately before the latest user message. This preserves prompt-cache reuse.
• Optional: on. Enable Update system message with current-turn context to re-render the single pinned root system message in place each turn. Enable this for Chat Completions models that accept a system message only in the first position, including affected open-weight or quantized server builds.
• The root system message remains protected from history compaction.
• The Responses API route retains its existing request-local context behavior.

Settings and navigation refinements

• Settings, Model Providers, and guided setup components now use corrected scoped-CSS isolation patterns for MudBlazor content.
• Model Providers Back navigation now returns through Atraium's shared navigation stack and no longer loops between Settings and Model Providers.
• Room and Workspace configuration use the new Chat profile selector rather than legacy model-name fields.
• Chat composer, message stream, and responsive Room layouts include additional mobile quality-of-life refinements.

What to try

1. Open Settings -> Model providers and create a reusable Chat profile.
2. Assign it as the global Chat profile, then optionally select a different profile from Room or Workspace configuration.
3. Open Workspace -> Tools & access, confirm the Coding source is enabled, then ask the assistant to inspect a project with Read, Glob, or Grep and make a small exact change with Edit.
4. Ask the assistant to run a project command through Bash without specifying cwd when the command includes an accessible project path.
5. Set a small, suitable non-Coding category to Direct, or ask the assistant to request the direct tool it needs and approve or dismiss the proposal from the Tools surface.
6. Create a Chat Completions profile and leave context caching off for stable prompt caching. Enable it for an open-weight model or server that requires the system message to remain first, such as affected KAT-Coder V2.5 GGUF configurations.
7. Ask the assistant to record completed work using a task created with isComplete: true.

Important limitations

• This is preview software and may contain breaking issues.
• Direct model-tool exposure is limited to 24 catalog tools. Additional enabled tools remain available through the gateway.
• Model availability, feature support, quotas, regions, and parameter support vary by provider, account, endpoint, and model.
• OpenAI-compatible providers can differ in their support for API modes, tool calling, reasoning parameters, prompt caching, system-message ordering, and chat templates.
• Tool behavior depends heavily on the selected model and its tool-calling quality.
• Provider-side usage, billing, and policy controls remain authoritative.
• Support is best-effort.

Downloads

This preview release includes:

• Atraium-0.2.3-preview.1-win-x64-setup.exe
• Atraium-0.2.3-preview.1-win-x64-portable.zip
• Atraium-0.2.3-preview.1-SHA256SUMS.txt

Verification

...

Atraium 0.2.2 Preview 1

Atraium 0.2.2 Preview 1

Atraium 0.2.2 Preview 1 improves the reliability, traceability, and control of provider-powered work. It adds a dedicated usage ledger and analytics experience, stronger recovery from temporary provider failures, and more capable Workspace controls.

Recommended target

• Windows desktop: recommended preview experience
• Android: not included in this release unless listed in the attached assets
• Web: not currently supported

Highlights

Provider usage and cost visibility

Atraium now records provider activity in a dedicated usage ledger instead of attaching usage only to individual chat messages.

• Review usage in each Workspace from the new Usage surface.
• Open Usage analytics for a Room- and Workspace-wide view across Atraium.
• See reported input, cached input, uncached input, output, and total token counts where the provider supplies them.
• Review measured work for supported non-token operations, such as images, embeddings, speech, realtime sessions, and computer-use activity.
• See completed requests and retained provider-failure details in one place.
• Inspect the effective target, configured model, and configured deployment recorded for new requests.
• Filter analytics by time period, Room, Workspace, provider, effective target, configured model, deployment, operation, outcome, and message link.

Cost estimates are available when a supported model pricing profile has been configured. Atraium keeps each transaction's pricing snapshot so later pricing changes do not rewrite historical estimates.

Interactive analytics

The new root-level Usage analytics page makes longer-term usage easier to understand.

• Explore token trends over the selected time range.
• Review provider and model breakdowns.
• Use Room-level usage distribution and drill into Workspace distribution.
• Browse large ledgers through virtualized, server-paged transaction lists.
• Keep currencies separate: Atraium does not add amounts from different currencies together.

More resilient provider requests

Temporary provider limits and interruptions are handled more safely.

• Atraium retries temporary provider failures, including many 429 Too Many Requests responses, using bounded back-off.
• Configure request-per-minute pacing for Chat and Utility models to help respect provider quotas, including free-tier limits.
• Temporary waits are surfaced as assistant status instead of appearing as a silent stop.
• Failed tool and computer-use steps now leave recoverable results, reducing the risk of an incomplete tool chain blocking the next message.
• Provider failures are recorded in usage history to aid troubleshooting.

Refined Workspace controls

Workspaces now provide clearer ownership and customization.

• Edit a Workspace's name, brief, and personality instructions from Workspace settings.
• Reset Workspace instructions to the selected template when needed.
• Workspace personality instructions apply to the next message without reopening the Room.
• Workspace list handling has been improved to prevent duplicate entries after creation.

What to try

1. Open a Room and choose a Workspace.
2. Send a few messages, use tools, or generate supported content.
3. Open the Workspace Usage surface to inspect the current Workspace ledger.
4. Open Usage analytics from the main navigation.
5. Filter by provider, configured model, deployment, or time range.
6. If your provider has a strict quota, set the appropriate requests-per-minute value in advanced model settings.

Important limitations

• This is preview software and may contain breaking issues.
• Provider-reported usage and charges are authoritative. Atraium can only record the information exposed by a provider.
• Some capabilities record known local measurements rather than provider-reported billable units.
• Cost estimates require a configured pricing profile and may differ from provider invoices, taxes, regional pricing, discounts, or account-level agreements.
• Existing historical usage may not include the newer configured-model and deployment snapshots.
• Provider availability, model access, regions, quotas, and feature support can vary by account.
• Tool behaviour depends heavily on the selected model.
• Support is best-effort.

Downloads

This preview release includes:

• Atraium-0.2.2-preview.1-win-x64-setup.exe
• Atraium-0.2.2-preview.1-win-x64-portable.zip
• Atraium-0.2.2-preview.1-SHA256SUMS.txt

Verification

Verify the SHA-256 checksum of the downloaded installer or archive against the attached checksum file.

Token usage, costs, and credentials

You are solely responsible for all usage and charges from the providers, endpoints, plugins, MCP servers, and infrastructure you configure.

Atraium does not include provider credentials, model credits, or token allowance. It does not enforce your provider budget, control provider pricing, or issue refunds for provider charges.

Tool-rich workflows can involve multiple model calls, long context, searches, embeddings, images, speech, retries, and continued work. Configure provider-side limits and monitor your provider dashboard.

Read Token usage and provider billing before using paid credentials.

Feedback

Use GitHub Issues for reproducible bugs and structured feedback. Use Discussions for broader questions and workflow ideas.

Do not publish API keys, tokens, private endpoint URLs, confidential prompts, source code, or sensitive files.

Atraium 0.2.1 Preview 1

Atraium 0.2.1 Preview 1

Atraium 0.2.1 Preview 1 expands your model choices. In addition to OpenAI-compatible services, Atraium now supports Anthropic Claude and Google Gemini across supported features.

Recommended target

• Windows desktop: recommended preview experience
• Android: not included in this release unless listed in the attached assets
• Web: not currently supported

Highlights

More model providers

Choose the provider that best suits each part of your workflow.

• Continue using OpenAI-compatible models and endpoints.
• Use Anthropic Claude for Chat and Utility work.
• Use Google Gemini for Chat, Utility, memory, images, voice, and live interactions.
• Keep existing OpenAI-compatible settings: no migration is required.

Mix providers by feature

You are no longer limited to one model provider for the entire app.

For example, you can use:

Chat and Utility       → Anthropic Claude
Memory and search      → Google Gemini
Image generation       → Google Gemini
Realtime and voice     → Google Gemini

You can also keep OpenAI-compatible services for any supported feature. Each feature can have its own provider, model, endpoint, and API key.

Guided configuration improvements

The guided setup now makes provider choices clear from the start.

• Choose a provider for Chat and Utility.
• Select providers separately for Embeddings, Images, Realtime, Speech-to-text, and Text-to-speech.
• See only the choices that are available for the feature you are configuring.
• Use provider-specific API keys without replacing keys already configured for other services.
• Start with suggested models, including Claude 4.8 and Gemini 3.5 Flash.

Capability overview

Feature	Available providers
Chat and Utility	OpenAI compatible, Anthropic Claude, Google Gemini
Memory and semantic search	OpenAI compatible, Google Gemini
Image generation	OpenAI compatible, Google Gemini
Realtime and voice	OpenAI compatible, Google Gemini

Anthropic Claude is currently available for Chat and Utility. Atraium does not present Claude as an option for features that Anthropic does not provide.

What to try

1. Open Settings or Guided configuration.
2. Configure an Anthropic or Google AI API key.
3. Choose a provider and model for Chat and Utility.
4. Optionally choose different providers for memory, images, realtime, and voice.
5. Start a new conversation and try your selected Chat model.

Important limitations

• This is preview software and may contain breaking issues.
• Provider availability, model access, regions, quotas, and feature support can vary by account.
• OpenAI-compatible providers can differ in route and feature support.
• Tool behaviour depends heavily on the selected model.
• Cost controls are incomplete; monitor every configured provider account.
• Powerful local workflows should be tested with non-critical files first.
• Support is best-effort.

Downloads

This preview release includes:

• Atraium-0.2.1-preview.1-win-x64-setup.exe
• Atraium-0.2.1-preview.1-win-x64-portable.zip
• Atraium-0.2.1-preview.1-SHA256SUMS.txt

Verification

Verify the SHA-256 checksum of the downloaded installer or archive against the attached checksum file.

Token usage, costs, and credentials

You are solely responsible for all usage and charges from the providers, endpoints, plugins, MCP servers, and infrastructure you configure.

Atraium does not include provider credentials, model credits, or token allowance. It does not enforce your provider budget, control provider pricing, or issue refunds for provider charges.

Using more than one provider can create charges across multiple accounts. Chat, memory, images, voice, realtime sessions, and tool-rich workflows may all be billed separately by the configured provider.

Read Token usage and provider billing before using paid credentials.

Feedback

Use GitHub Issues for reproducible bugs and structured feedback. Use Discussions for broader questions and workflow ideas.

Do not publish API keys, tokens, private endpoint URLs, confidential prompts, source code, or sensitive files.

Atraium 0.2.0 Preview 1

Atraium 0.2.0 Preview 1

Atraium 0.2.0 Preview 1 introduces Workspaces: a clearer way to organize active work, conversations, notes, tasks, source material, and generated files inside each Room.

Recommended target

• Windows desktop: recommended preview experience
• Android: not included in this release unless listed in the attached assets
• Web: not currently supported

Highlights

Workspaces for focused work

A Room can now contain focused Workspaces for separate streams of work. Each Workspace keeps its own conversation, notes, task list, source material, generated files, and tool preferences while remaining part of the same Room.

• Create focused areas for research, planning, writing, or implementation work.
• Switch between Workspace conversations without losing the larger Room context.
• Use the Room overview to see activity, open work, notes, and generated files at a glance.
• Keep Room-wide actions and Workspace-specific actions clearly separated.

Notes, tasks, and artifacts in one place

Workspaces now provide dedicated places to capture and revisit work.

• Add shared notes for decisions, findings, drafts, and reference material.
• Track open tasks and follow-up actions alongside the relevant conversation.
• Review generated documents and source files from the Artifacts view.
• Newly generated documents, workbooks, presentations, and PDFs are kept with the conversation so they remain available after reopening Atraium.

A more polished Room experience

Room navigation and workspace controls have been refined for a cleaner, more focused experience.

• Room actions are grouped with the Room header.
• Conversation controls are kept close to the composer where they are most useful.
• Mobile layouts now prioritize the active content view and use more compact Room controls.
• Workspace cards, lists, and panels have improved spacing and readability.

Improved Windows desktop experience

The Windows app now feels more integrated with the desktop.

• Atraium can extend naturally into the window frame while keeping familiar window controls.
• The title-bar area supports both window dragging and quick access to common actions.
• Window resizing and everyday typing remain responsive.

Better image previewing

Image previews now provide more reliable zooming and panning.

• Use the toolbar, mouse wheel, or touch gestures to zoom.
• Drag to inspect details, then use Reset view to return to the original framing.
• Images retain their correct proportions while zooming.

What to try

• Create a Room and add separate Workspaces for different goals.
• Capture a note or task while working through a conversation.
• Generate a document, workbook, presentation, or PDF and download it after restarting Atraium.
• Open an image attachment and try zooming, panning, and resetting the preview.
• Resize the Windows app and explore the updated Room navigation.

Important limitations

• This is preview software and may contain breaking issues.
• OpenAI-compatible providers can differ in route and feature support.
• Tool behaviour depends heavily on the selected model.
• Cost controls are incomplete; monitor your provider account.
• Powerful local workflows should be tested with non-critical files first.
• Support is best-effort.

Downloads

This preview release includes:

• Atraium-0.2.0-preview.1-win-x64-setup.exe
• Atraium-0.2.0-preview.1-win-x64-portable.zip
• Atraium-0.2.0-preview.1-SHA256SUMS.txt

Verification

Verify the SHA-256 checksum of the downloaded installer or archive against the attached checksum file.

Token usage, costs, and credentials

You are solely responsible for all usage and charges from the providers, endpoints, plugins, MCP servers, and infrastructure you configure.

Atraium does not include provider credentials, model credits, or token allowance. It does not enforce your provider budget, control provider pricing, or issue refunds for provider charges.

Tool-rich workflows can involve multiple model calls, long context, searches, embeddings, images, retries, and continued work. Configure provider-side limits and monitor your provider dashboard.

Read Token usage and provider billing before using paid credentials.

Feedback

Use GitHub Issues for reproducible bugs and structured feedback. Use Discussions for broader questions and workflow ideas.

Do not publish API keys, tokens, private endpoint URLs, confidential prompts, source code, or sensitive files.

Atraium 0.1.0 Preview 1

Atraium 0.1.0 Preview 1

This is the first external preview of Atraium, a local-first bring-your-own-model workspace for configurable assistants and tool-backed workflows.

Recommended target

• Windows desktop: recommended preview experience
• Android: not included in this release unless listed in the attached assets
• Web: not currently supported

What to try

• configure Chat, Utility, and Search / Grounding;
• create a room with a focused personality or system prompt;
• perform a source-grounded research task;
• work with a disposable local workspace;
• create a document, workbook, presentation, or image where configured;
• report unclear setup steps and reproducible failures.

Important limitations

• This is preview software and may contain breaking issues.
• OpenAI-compatible providers can differ in route and feature support.
• Tool behaviour depends heavily on the selected model.
• Cost controls are incomplete; monitor your provider account.
• Powerful local workflows should be tested with non-critical files first.
• Support is best-effort.

Downloads

This preview release includes:

• Atraium-0.1.0-preview.1-win-x64-setup.exe
• Atraium-0.1.0-preview.1-win-x64-portable.zip
• Atraium-0.1.0-preview.1-SHA256SUMS.txt

Verification

Verify the SHA-256 checksum of the downloaded installer or archive against the attached checksum file.

Token usage, costs, and credentials

You are solely responsible for all usage and charges from the providers, endpoints, plugins, MCP servers, and infrastructure you configure.

Atraium does not include provider credentials, model credits, or token allowance. It does not enforce your provider budget, control provider pricing, or issue refunds for provider charges.

Tool-rich workflows can involve multiple model calls, long context, searches, embeddings, images, retries, and continued work. Configure provider-side limits and monitor your provider dashboard.

Read Token usage and provider billing before using paid credentials.

Feedback

Use GitHub Issues for reproducible bugs and structured feedback. Use Discussions for broader questions and workflow ideas.

Do not publish API keys, tokens, private endpoint URLs, confidential prompts, source code, or sensitive files.