v2.0.0
Aug 5, 2026rohanpoudel2/image_video_compressor
TypeScript rewrite with Node 24 fixes, optimized compression, and bounded concurrency limits.
12
releases
5
active repos
105
days shipping
2w ago
last shipped
Aug 27, 2025 → Aug 26, 2026
rohanpoudel2/image_video_compressor
TypeScript rewrite with Node 24 fixes, optimized compression, and bounded concurrency limits.
rohanpoudel2/solmari
Adds AI chat interface with personas, document management, voice input, and embeddings for RAG.
rohanpoudel2/openclaw
Fixes authentication, messaging integrations, and runtime reconciliation across multiple platforms.
12 releases in 2026
See the full recap, monthly chart, change type breakdown, GitHub overview
TypeScript rewrite with Node 24 fixes, optimized compression, and bounded concurrency limits.
Rewrite in TypeScript with backward compatibility
Complete TypeScript rewrite of the codebase. All v1 commands remain functional and deprecated (not removed), ensuring existing scripts continue to work without breaking changes.
Fix four crashes on Node 24
Resolved critical defects discovered during security audit, including crashes that occurred within minutes of running v1 on Node 24.
Fix incorrect video encoding behavior
Corrected video encoding logic that was producing wrong output formats.
Add bounded concurrency limits
Implement concurrency controls to prevent unbounded resource usage during bulk compression operations.
Optimize image compression performance
Refactored image compression logic in src/image.js for improved efficiency and output quality.
+3 more entries
Solmari adds Notes feature with text tools and semantic search capabilities.
Add Notes — private second brain with text tools and semantic search
Introduces a capture-transform-store-retrieve surface for managing personal notes alongside chat. Features on-device semantic search, text transformation tools, and offline-first storage. Access via the drawer under Notes/Tools.
Adds catalog-driven model selection to replace hardcoded engine pairs
Replace hardcoded engine pair with catalog-driven model selection
Models are now selected from a recommended catalog with intelligent defaults per device. Users can download, switch between, and delete models with per-model configuration for prompts, sampling parameters, and context windows.
Streamlines chat experience, replaces dictation with OS voice typing, polishes UI.
Streamline app to core on-device chat experience
Removed non-essential features to focus on the foundational on-device AI chat functionality, reducing complexity and dependencies.
Replace custom dictation with OS keyboard voice typing
Integrated native OS keyboard dictation in place of the broken custom dictation implementation, providing reliable cross-device voice input without additional dependencies.
Polish chat UI and interactions
Enhanced the chat surface with UX improvements for a more polished messaging experience.
Adds persona presets, on-device semantic search, and dual inference backend support.
Add persona presets for quick conversation modes
Introduces one-tap persona modes (Tutor, Coder, Editor, Brainstorm) accessible from the empty state and header. Each preset merges a specialized system message to shape AI behavior.
Implement semantic chat search on-device
Enables full-text semantic search across chat history using on-device processing, allowing users to quickly find relevant conversations.
Add dual inference backend support
Extends the offline chat app to support both Apple Foundation Models and Gemma 4 as inference backends, giving users flexibility in model selection.
Adds AI chat interface with personas, document management, voice input, and embeddings for RAG.
Add chat interface with conversation management
Implemented core chat UI components including ChatScreen, ChatInputBar, ConversationDrawer, and EmptyState for managing conversations and user interactions.
Add persona system for customizable AI interactions
Introduced PersonaPicker component and personas library to enable users to select and customize AI assistant behaviors.
Implement document management for RAG
Added DocumentChip component and RAG document retrieval system to support document-based context in conversations.
Add voice input support with dictation
Integrated speech-to-text functionality through use-dictation hook and STT service for hands-free chat input.
Implement embeddings and vector search
Added embeddings service, vector store, and search indexing to enable semantic search capabilities across documents.
+3 more entries
Converts sandbox to offline AI chat application
Transform sandbox into offline AI chat application
Convert the Foundation Models developer sandbox into a fully functional on-device chat app with streaming responses, multi-turn conversations, conversation persistence, and markdown-rendered replies. Add streamChat(messages, {abortSignal}) method to foundation-model for streaming multi-turn chat support.
Migrates to Next.js App Router with sitemap generation and 404 page support.
Migrate to Next.js App Router
Upgraded the project from Hugo to Next.js 13+ App Router architecture. Reorganized page structure with dynamic routes for tours, regions, and slug-based content pages.
Update baseUrl configuration
Adjusted baseUrl settings for the Next.js migration.
Refactor component library
Converted React components (BackLink, Breadcrumbs, ContactCTA, FAQ, FloatingContact, Footer, Header, NepalTime, PageHeader) to TypeScript for improved type safety.
Update global styles and layout
Migrated CSS and layout structure to align with Next.js App Router conventions.
Add sitemap generation
Implemented dynamic sitemap.ts for improved SEO.
+3 more entries
Release version asdf for rohanpoudel2/ai project.
Release asdf
No changes detected between tags.
Released new_tag version
Release new_tag
No changes detected between tags.
README documentation updated for clarity and completeness.
Update README documentation
Fixes authentication, messaging integrations, and runtime reconciliation across multiple platforms.
Fix WhatsApp authentication state and runtime reconciliation after CLI login
Stabilized auth state handling and local runtime reconciliation in WhatsApp integration following CLI-based login flows.
Consolidate BlueBubbles HTTP traffic through typed client
Refactored BlueBubbles integration to route all HTTP traffic through a single typed client for improved consistency and maintainability.
Tolerate partial Discord channel metadata
Enhanced Discord integration to gracefully handle incomplete channel metadata responses.
Add detached runtime plugin registration contract
Introduced new contract for plugin registration in detached runtime contexts.
Default Kimi thinking mode to off
Changed default behavior to disable Kimi's thinking mode by default.
+15 more entries