Category Recommendation

LiveReview is a risk-aware AI code review platform launched by Hexmos. It prioritizes reviews by combining model analysis, code relationships, and team feedback, and supports five types of Git platforms. The free version offers 30,000 lines per month for up to three users; paid plans are tiered based on the number of lines reviewed, with no additional charges per seat.

crystl is a multi-tasking AI terminal for macOS that organizes multiple programming agents around projects, sessions, and Git worktrees, offering approval reminders, history search, and remote viewing on iPhone. The free version includes parallel processing and SSH; advanced features such as automatic orchestration are available in Guild.

Turnstone is a multi-agent assistant for Mac that connects to existing model subscriptions, APIs, or local models, allowing different assistants to divide up the work of handling data, files, and repetitive tasks. The Mac app is free, but model usage is billed separately; the Cloud service is still in beta.

Soniox offers real-time and file-based transcription APIs. STT v6 introduces proxy text context and proxy speech echo cancellation, designed for voice assistants, conferences, and dictation; however, performance claims still require verification using actual business audio.

Mika converts natural language tasks into mobile and web operations, supporting virtual screens in the background, task playback, and custom model selection; it is suitable for low-risk automated exploration, but users should carefully review permissions, data flow, and verification mechanisms before use.

Mo automatically explores applications and submits issues with reproducible evidence; Momentic provides natural language test writing, regression testing, and CI integration to help teams validate critical processes before release.

Based on business documentation and process descriptions, we help companies clarify their requirements, build intelligent agent applications, and integrate testing, deployment, and governance into a single workflow.

An open-source document analysis and quality assessment model that integrates scanned documents, tables, and formulas into a verifiable data workflow.

The Qwen team has open-sourced an AI programming agent that supports integration with multiple models, as well as code understanding, modification, and testing, making it suitable for single-device and multi-device development workflows.

Share vetted project histories, session logs, and reusable skills across programming assistants.

Integrate existing ERP and procurement data; use AI agents to investigate and resolve anomalies such as order changes and invoice discrepancies, while maintaining approval and audit controls.

An observability platform for AI application developers that tracks model calls, tool steps, retrievals, costs, and evaluations.

An open-source project management tool for AI programming assistants that uses Markdown and Git to save context, decisions, and cross-session handoffs.

A customer engagement platform for B2C teams that integrates multi-channel messaging, AI-powered customer service, lead assignment, and sales follow-up.

An AI-powered security testing tool for authorized targets that combines proxy, browser, and code inspection capabilities, offering both open-source deployment and cloud services.

A speech recognition API for Swift developers that provides unified access to Apple, Parakeet, and Qwen3-ASR, and supports speaker separation.

Skyhook has launched a Kubernetes visualization and AI-powered operations tool that consolidates resource topology, event timelines, and MCP investigations.

The MiniMax team has released an open-source programming agent workflow and self-assessment toolkit that covers review, context, and long-running tasks.

Gradium has launched a lightweight, on-device text-to-speech model that generates speech on the device; users should note that languages and licensing vary by model.

An open-source runtime for large-scale concurrent agents that allows tasks that are waiting to resume execution based on events.

Provide reusable project context, specialized workflows, and review stages for existing AI assistants, enabling collaboration across sessions and tools.

A voice model designed for real-time business calls that allows responses to undergo a text review before they are spoken.

Organize screen demos, voice recordings, and key screenshots into AI prompt text to help product, design, and R&D teams hand off requirements.

Baidu has open-sourced a document analysis model that supports multi-page joint recognition, cross-page tables, and the processing of extremely long documents.

A desktop browser with a built-in AI assistant that helps with cross-page research, meeting notes, and office tasks.

An open-source AI-powered research and report generation agent that automatically retrieves information from the web and local sources, compiles research reports with citations, and supports self-deployment and integration with Python.

An Apache 2.0 open-source platform for document understanding, retrieval, and enhanced generation, supporting complex data parsing, knowledge base retrieval, and agent workflows.

An open-source multi-model chat and agent platform from MIT that centrally manages models, document-based Q&A, and tool invocations, and supports self-hosting by teams.

Use natural language, templates, and Remix to generate prototypes for React Native and Expo apps, then export the code to continue development.

Parses complex documents—such as PDFs, Office files, and scanned documents—into structured data, supporting both on-premises deployment and RAG workflows.