v3.0.0

OpenMindAI v3.0.0 Release Notes

Release line: v3.0.0
Status: Release candidate until the signed production installer and updater artifacts pass the final release pipeline.

OpenMindAI v3.0.0 is the largest workflow-focused update since v2.0.0.
The release moves OpenMindAI beyond local chat and model management into a local AI workstation that can actively work with real projects, files, terminal commands, Git repositories, and connected services while keeping explicit permission and validation boundaries.

Between v2.0.0 and the v3.0.0 source line, the repository contains hundreds of changes across the desktop UI, Rust backend, local AI runtimes, project system, connected apps, media capabilities, CI, security, installer, updater, and release infrastructure.

---

Highlights

Project Work is now a first-class workspace

Projects are no longer limited to instructions, attached files, and linked chats.

Each Project now includes:

• Overview tab for project instructions, linked chats, and reference/context files.
• Work tab for active local development work.
• Attached local filesystem browsing.
• Local file editor.
• Local terminal controls.
• Direct handoff to a linked Project Agent conversation.
• Explicit Full PC + Terminal permission boundary.
• Live project/workspace context refresh after changes.

This turns a Project into a practical local workspace instead of a passive context container.

---

Open Folder as Project

A real local folder can now be opened directly as an OpenMindAI Project.

The flow can:

• Select an existing folder.
• Create the Project automatically.
• Attach the folder as the Project workspace.
• Create a linked Project Agent chat.
• Link the Project and conversation durably.
• Open the Project directly in the Work area.
• Roll back incomplete Project/chat state if setup fails before the relationship is committed.
• Keep filesystem access scoped to the attached folder unless broader terminal access is explicitly approved.

This creates the foundation for working on existing applications, repositories, research code, websites, scripts, or other local projects directly inside OpenMindAI.

---

Local Project Agent

v3.0.0 introduces the new autonomous Project Agent workflow.

The agent can work against an attached local project and can:

• Inspect files and directories.
• Read project source code.
• Create files.
• Edit existing files.
• Rename files.
• Delete files when required.
• Use recent Project conversation context.
• Refresh its workspace view after modifications.
• Reason over tool failures.
• Repair failed changes.
• Re-run validation.
• Report the final result and validation evidence.

The agent uses the local OpenMindAI model/runtime rather than requiring a paid cloud coding API.

---

Agent Edit → Terminal → Detect → Fix → Retest Loop

The Project Agent now supports a real iterative development loop:

1. Inspect the workspace.
2. Plan the required change.
3. Edit project files.
4. Run an applicable command.
5. Detect non-zero exits or command timeouts.
6. Feed the failure back into the next reasoning step.
7. Repair the implementation.
8. Re-run tests, lint, build, or another applicable validation.
9. Complete only after valid evidence is available.

Important reliability improvements include:

• Non-zero terminal exits are treated as real failures.
• Command timeouts are treated as failures.
• Successful recovery resets the consecutive-failure counter.
• Duplicate exact-action protection prevents infinite repetition.
• Agent execution has a bounded safety budget.
• Transient local-model failures can be retried.
• Running agent work can be cancelled.
• Validation cannot be silently bypassed for projects with recognizable build/test manifests.

---

Stronger Validation Rules

v3.0.0 makes completion evidence stricter.

After a workspace-changing action:

• Previous validation is considered stale.
• The workspace must be validated again.
• Mutating terminal commands also invalidate previous validation.
• Successful validation commands are tracked as completion evidence.
• Chained terminal commands cannot hide an earlier failure.
• A Project with a recognized build/test manifest cannot simply claim that validation is unnecessary.
• If no meaningful automated validation exists, the agent may record a concrete reason for skipping it.

Recognized project validation targets include common ecosystems such as:

• Node.js / JavaScript / TypeScript
• Rust
• Python
• Go
• Maven / Java
• Gradle
• PHP / Composer
• Ruby
• .NET projects and solutions

---

Live Workspace Context

The local agent no longer works from a stale snapshot after making changes.

v3.0.0 refreshes Project workspace context after:

• Direct filesystem changes.
• Successful terminal actions.
• Other operations that may modify the attached project.

This makes the next agent step reason over the current state of the project rather than the state that existed before the edit or command.

---

Terminal Safety and Permission Boundary

Terminal access remains intentionally permission-gated.

Without explicit broader permission, OpenMindAI keeps Project Agent work scoped to the attached workspace.

When Full PC + Terminal access is enabled, the agent can use non-interactive local shell commands while still following safety restrictions.

The terminal workflow avoids:

• Interactive editors.
• Password prompts.
• sudo requests.
• Commands that indefinitely wait for user input.
• Interactive pagers.
• Unsafe root-level destructive commands.

Cross-platform terminal guidance is implemented for:

• Windows: non-interactive PowerShell.
• Linux: /bin/sh -lc.
• macOS: /bin/sh -lc.

---

Git-Aware Project Work

Project Agent can inspect Git state when terminal permission is available.

New Git-aware capabilities include:

• Structured Git status inspection.
• Structured Git diff inspection.
• Safer Git execution configuration.
• External diff helpers disabled during inspection.
• Textconv disabled during inspection.
• fsmonitor disabled during inspection.
• Recursive submodule behavior restricted during inspection.

Potentially mutating Git operations such as commits, resets, cleans, branch changes, installs, or arbitrary commands remain behind the terminal permission boundary and the user's task instruction.

---

Connected Apps

v3.0.0 adds a major Connected Apps architecture.

Connected services are treated as internal assistant tools rather than a separate raw API console.

Users configure connections in:

Settings → Apps

Then they can ask for the desired result naturally from Chat or Project Work.

Supported app families include:

Google Workspace

• Gmail
• Google Drive
• Google Calendar
• Google Contacts

GitHub

• Repositories
• Repository files
• Issues
• Pull requests
• GitHub Actions
• Releases

Microsoft 365

• Outlook
• OneDrive
• Calendar
• Contacts

Additional integrations

• Slack
• Notion
• Dropbox
• MCP servers

Connected-app actions are selected internally by the assistant instead of exposing provider/action JSON to the user.

---

Connected-App Safety

The new connected-service backend includes additional controls for remote data and mutations.

Implemented protections include:

• OAuth/client configuration isolated to Settings.
• Tokens and connection secrets kept out of chat history.
• OS credential-store integration for sensitive credentials.
• Explicit backend approval for mutating remote actions.
• Provider-level permission checks.
• Connected tool output treated as untrusted external data.
• Input guards for provider parameters.
• Path and repository validation.
• Fail-closed mutation classification.
• Narrow explicit confirmation phrases before remote writes.
• Pending approval state with bounded lifetime.
• Duplicate approval protection.

This allows natural-language connected-service workflows without treating external tool output as trusted instructions.

---

Chat and Conversation Improvements

The chat backend received substantial persistence and workflow hardening.

Improvements include:

• Better conversation/model association.
• Stronger message mutation handling.
• Branch cleanup when earlier user turns are removed.
• Improved streaming-state handling.
• Better interrupted-message recovery after reopening the database.
• Project/profile context separation.
• Active model persistence.
• Better multimodal attachment handling.
• Improved internal tool routing support.
• Project context synchronization before connected-agent operations.
• Improved regeneration handling for connected-app conversations.

---

Project Data Integrity Improvements

The Project system received database and relationship hardening.

Changes include:

• Stronger Project CRUD validation.
• Safer Project/conversation linking.
• Single-project ownership enforcement for a conversation.
• Migration support for the updated relationship model.
• Bounded Project context.
• Unicode-safe context limits.
• Better tracking of local project resources.
• Workspace metadata synchronized into agent context.

---

Local Media Runtime Expansion

v3.0.0 significantly expands local multimodal infrastructure.

New or expanded backend areas include:

• Local diffusion runtime.
• Image-generation runtime preparation.
• Hardware-aware media preflight checks.
• Voice runtime.
• Speech/audio runtime.
• Video-related local runtime validation.
• Vision batch processing.
• PDF/OCR support.
• Multimodal input handling.
• Model package validation for multi-file model packages.

The goal remains local-first: OpenMi...

v2.0.0

OpenMindAI v2.0.0 Release

OpenMindAI v2.0.0 is a major update focused on making the app feel more complete, smooth, and ChatGPT-like while staying local-first. This release adds full model management, internal model routing, media generation entry points, Tools, Projects, better setup flow, improved UI responsiveness, and a fresh Windows installer.

What’s New

Model System

• Added full model catalog support.
• Models now show with OpenMindAI personal model names.
• Downloaded models show as Verified instead of Download.
• Added pause, cancel, progress, and download speed for model downloads.
• Added model delete flow with confirmation warning.
• Recommended model badge now depends on system configuration.
• Model selector popup now shows only personal OpenMindAI model names.
• Fixed duplicate model display issues.

Internal Model Routing

• Added automatic internal model routing based on user input.
• Routing is hidden from the user, similar to ChatGPT.
• Chat automatically chooses the best local model for tasks like chat, code, image, video, voice, and file-related work.

Image, Video, Voice Generation

• Added Generate image option.
• Added Generate video option.
• Added Generate voice option.
• If required model is missing, the app shows Model Download Required in red.
• Image generation now creates a local preview artifact when the image model is available.
• Video and voice generation now show clear local runtime connector messages.

Tools Section

• Enabled the left sidebar Tools section.
• Added functional tool workspace.
• Added tool actions for diagnostics, files, models, library, and chat workflows.

Projects Section

• Enabled the Projects section.
• Added project creation, editing, deletion, and chat linking.
• Added project instructions.
• Added local file attachment support.
• Text/code files are ingested into hidden project context.
• Binary/large files are tracked locally with status.
• Project chats automatically use hidden project instructions and file context.

Setup / Installer

• Setup flow now shows all available OpenMindAI personal models.
• Users can download models during setup.
• Recommended badges are based on system configuration.
• Runtime install can be cancelled/retried.
• New Windows installer generated for v2.0.0.

UI / UX Improvements

• Fixed responsive menu issues.
• Improved chat starting position.
• Improved composer and model popup behavior.
• Added user message edit/copy actions.
• Added sidebar version display.
• Changed Local Active to System Active with green status dot.
• Added footer copyright:
  Copyright 2026 Md Shahanur Islam Shagor. All rights reserved.

Release Files

• OpenMindAI_2.0.0_x64-setup.exe
• SHA256SUMS.txt
• OpenMindAI-Setup.bat
• OpenMindAI-Setup.command
• openmindai-setup.sh
• openmindai.marker

SHA256

c7711d8a69fffd9cf2434950283a1038d2b0c8956528c65d864bf92ad3608577  OpenMindAI_2.0.0_x64-setup.exe

v1.0.1

OpenMindAI v1.0.1 🚀
The first stable release of OpenMindAI is here.

OpenMindAI is a local-first, offline AI desktop application designed to run AI directly on your own computer using your CPU, RAM, GPU, and VRAM — without requiring a paid AI API or cloud account for core AI chat.

✨ Highlights
Local AI chat powered by an open-weight model
Works offline after the initial setup
Automatic hardware detection
GPU acceleration with supported hardware
CPU fallback when GPU acceleration is unavailable
Automatic AI runtime setup
Automatic model download and verification
Resumable model downloads
Real-time streaming AI responses
Stop generation at any time
Local persistent chat history
SQLite-based local database
Custom local AI storage location
Local profile/database setup
Automatic restoration of previous conversations
Built-in system health and setup architecture
Application and model update support
Portable/local storage architecture
🤖 AI Model
OpenMindAI v1.0.1 uses:

Qwen3 4B — Q4_K_M

The model runs locally through llama.cpp.

AI model files are downloaded during initial setup and are not bundled inside the application installer.

🔒 Local & Offline by Design
After the first-time setup is complete, core OpenMindAI features can work without an internet connection.

Your local:

Conversations
AI model
Database
Settings
Runtime
Generated data
remain inside your configured OpenMindAI storage location.

No OpenAI, Claude, Gemini, or other paid AI API is required for local AI chat.

🖥️ Hardware Acceleration
OpenMindAI automatically checks your computer and selects the most suitable available AI runtime.

Depending on your system, OpenMindAI can use:

GPU acceleration
Dedicated VRAM
System RAM
CPU fallback
Performance will vary depending on your hardware.

💾 First-Time Setup
On the first launch, OpenMindAI guides you through the setup process:

Choose where OpenMindAI should store its AI data.
Create your local profile.
OpenMindAI prepares the local database.
Your hardware is detected automatically.
The compatible AI runtime is prepared.
The required AI model is downloaded and verified.
OpenMindAI becomes ready for local AI use.
After setup, future launches reuse the existing installation automatically.

🔄 Updates
OpenMindAI includes an update architecture for future application and AI model releases.

When a newer supported version becomes available, OpenMindAI can notify you and update the application while preserving your local AI data.

Your conversations, models, database, settings, and workspaces are kept separate from application updates.

📦 Download
Choose the appropriate release file for your platform from the Assets section below.

For most Windows users, use the standard OpenMindAI installer.

Bootstrap launchers may also be provided for supported platforms.

⚠️ Important
The initial setup requires an internet connection to download the required AI runtime and model.

After successful setup, core local AI chat can operate offline.

AI performance depends heavily on your CPU, RAM, GPU, VRAM, selected model, and available system resources.

🛣️ What’s Next
Future OpenMindAI releases are planned to expand the local AI platform with features such as:

Additional local AI models
Intelligent model routing
Local RAG and knowledge bases
File/document intelligence
Coding agents
Web research
Vision
Image generation
Voice capabilities
These features are not part of v1.0.0 unless explicitly included in a later release.

Thank you for trying OpenMindAI v1.0.0.

Your AI. Your hardware. Your data.

v1.0.0

OpenMindAI v1.0.0 🚀

The first stable release of OpenMindAI is here.

OpenMindAI is a local-first, offline AI desktop application designed to run AI directly on your own computer using your CPU, RAM, GPU, and VRAM — without requiring a paid AI API or cloud account for core AI chat.

✨ Highlights

• Local AI chat powered by an open-weight model
• Works offline after the initial setup
• Automatic hardware detection
• GPU acceleration with supported hardware
• CPU fallback when GPU acceleration is unavailable
• Automatic AI runtime setup
• Automatic model download and verification
• Resumable model downloads
• Real-time streaming AI responses
• Stop generation at any time
• Local persistent chat history
• SQLite-based local database
• Custom local AI storage location
• Local profile/database setup
• Automatic restoration of previous conversations
• Built-in system health and setup architecture
• Application and model update support
• Portable/local storage architecture

🤖 AI Model

OpenMindAI v1.0.0 uses:

Qwen3 4B — Q4_K_M

The model runs locally through llama.cpp.

AI model files are downloaded during initial setup and are not bundled inside the application installer.

🔒 Local & Offline by Design

After the first-time setup is complete, core OpenMindAI features can work without an internet connection.

Your local:

• Conversations
• AI model
• Database
• Settings
• Runtime
• Generated data

remain inside your configured OpenMindAI storage location.

No OpenAI, Claude, Gemini, or other paid AI API is required for local AI chat.

🖥️ Hardware Acceleration

OpenMindAI automatically checks your computer and selects the most suitable available AI runtime.

Depending on your system, OpenMindAI can use:

• GPU acceleration
• Dedicated VRAM
• System RAM
• CPU fallback

Performance will vary depending on your hardware.

💾 First-Time Setup

On the first launch, OpenMindAI guides you through the setup process:

1. Choose where OpenMindAI should store its AI data.
2. Create your local profile.
3. OpenMindAI prepares the local database.
4. Your hardware is detected automatically.
5. The compatible AI runtime is prepared.
6. The required AI model is downloaded and verified.
7. OpenMindAI becomes ready for local AI use.

After setup, future launches reuse the existing installation automatically.

🔄 Updates

OpenMindAI includes an update architecture for future application and AI model releases.

When a newer supported version becomes available, OpenMindAI can notify you and update the application while preserving your local AI data.

Your conversations, models, database, settings, and workspaces are kept separate from application updates.

📦 Download

Choose the appropriate release file for your platform from the Assets section below.

For most Windows users, use the standard OpenMindAI installer.

Bootstrap launchers may also be provided for supported platforms.

⚠️ Important

The initial setup requires an internet connection to download the required AI runtime and model.

After successful setup, core local AI chat can operate offline.

AI performance depends heavily on your CPU, RAM, GPU, VRAM, selected model, and available system resources.

🛣️ What’s Next

Future OpenMindAI releases are planned to expand the local AI platform with features such as:

• Additional local AI models
• Intelligent model routing
• Local RAG and knowledge bases
• File/document intelligence
• Coding agents
• Web research
• Vision
• Image generation
• Voice capabilities

These features are not part of v1.0.0 unless explicitly included in a later release.

---

Thank you for trying OpenMindAI v1.0.0.

Your AI. Your hardware. Your data.