Discover +1627 AI apps & tools

Pros: Local-first storage using SQLite for chat and character memory. Model Context Protocol support for external tool integration. Built-in Live2D rendering with eye-tracking and motion triggers. Multiple TTS/STT backends, including Whisper and Edge TTS.

Cons: Source builds require Node.js v18+ and Rust, increasing setup work. Customization expects web development skills for MODs and scripts. Generated responses depend on chosen language backend; verify accuracy.

Pros: MCP integration enables agents to run and manage terminal sessions. On-device voice input processes speech locally with zero latency. Integrated git tools show staging, shelving, and inline diffs in-terminal. SSH profile management keeps persistent remote sessions.

Cons: Designed for macOS 12.0+ and Apple Silicon, limiting platform reach. Autonomous agent command execution requires careful human verification. Best suited to users familiar with MCP agent workflows.

Pros: Provides five MCP tools for common channel actions. Interactive setup command and terminal CLI for quick configuration. Per-project .slack-mcp.json files scope workspace settings. Compatible with Cursor, Windsurf, and Claude Desktop hosts.

Cons: No Direct Message or Group DM support. Does not offer message search across workspaces. Scope is intentionally narrow, limiting full Slack parity.

Pros: Executes native iOS gestures, not synthetic pointer events. Provides real-time UI element inspection and hierarchy data. Integrates with MCP-compatible clients such as Claude Desktop. Distributed under Apache-2.0, allowing contribution and inspection.

Cons: Requires iOS simulator or physical device for execution. Needs Node.js plus Swift components for full setup. Automation fragile when app UI changes frequently. Targeted to iOS only, not cross-platform mobile control.

Pros: Exposes 15 MCP tools for core ERP operations. Universal form_id supports all Kingdee forms. Automatic pagination and file streaming for large exports. Automatic session recovery for long-running tasks.

Cons: Requires Python 3.10+ and the uv package manager. Needs valid Kingdee Web API credentials configured. Remote transports (SSE, streamable-http) need network security controls. Intended for developer teams rather than casual users.

Pros: Local SQLite storage preserves project context across sessions.. Rust binary keeps CLI overhead low during operations.. Includes clx-rules for project-specific policy management.. clx-doctor diagnoses empty-recall problems in long sessions..

Cons: Specialized for Claude Code, limited value outside that CLI ecosystem.. Requires a working Claude Code install and MCP support.. Installs as a system binary, adding an extra setup step.. Independent open-source project, not an official Anthropic product..

Pros: Automatically reuses DBeaver connection configurations. Enforces read-only transactions by rolling back every query. Communicates over MCP STDIO for standard client integration. Standalone launchers handle JRE provisioning on first run.

Cons: SSH key-based authentication not supported, only password SSH. Requires an MCP-compliant host to accept queries. Supports a limited set of databases (Postgres, Oracle, Firebird).

Pros: Keeps database credentials stored locally, never sent to the cloud. Supports major engines including PostgreSQL and BigQuery. Open-source under Apache 2.0 for security audits. Deployable as binary, Docker container, or Kubernetes service.

Cons: Generated model analysis requires independent verification. CLI setup assumes operator familiarity with command-line tools. Tied to MCP-compatible AI clients for full integration.

Pros: Converts ChatGPT ZIP/JSON exports into organized Markdown files. Built-in full-text search powered by the Tantivy library. Single-binary distribution with no external runtime dependencies. One-command setup for Claude Desktop and Claude Code.

Cons: Requires obtaining ChatGPT export ZIP via the service's Data Controls. Depends on an MCP-compatible host application for model access. Limited to ChatGPT export format for direct import. Targeted at power users rather than casual, nontechnical users.

Pros: Resolves model IDs into three capability tiers for tailored instructions. Detects OS, shell, and installed tools to inject local system state into prompts. Skill libraries stored in .skills directories and installable from Git repositories.

Cons: Configuration-first design requires developer tooling familiarity. Local system details are injected into prompts, requiring data caution. Full integration depends on MCP-compatible hosts and agent clients.

Pros: Supports stdio and Streamable HTTP transports for local and remote clients. Citation-backed querying anchors agent responses to specific notebook sources. Built-in localization infrastructure for multi-language processing. Artifact tools generate audio and video overviews from notebook content.

Cons: Requires Node.js (v18+) or a Python environment depending on build. Uses persistent browser session or cookie-based Google authentication. Setup needs development resources and secure session management.

Pros: Local-first agent execution for on-device data control. AIngle semantic graph memory enables verifiable, graph-structured knowledge. Supports MCP in server and client modes for broad interoperability. Gateway control plane connects agents to messaging apps like Telegram.

Cons: Requires Node.js 22+ and comfort with TypeScript and CLI. Primarily terminal-based interface, limited graphical UI options. Semantic graph memory demands additional configuration and learning.

Pros: Bridges BIM models to MCP-compatible agents for direct model queries. In-memory Wolfden enables high-speed, RAM-based data handling. URI-based schema maps BIM entities and taxonomies to identifiers.

Cons: Marked v0.2-alpha, explicitly not intended for production environments. Requires Windows host and Autodesk Revit 2025 or newer. Low-level API expects developer integration and technical setup.

Pros: Integrates Seedream models up to version 5.0 via MCP. Supports text-to-image and image-to-image edits with image URL input. Native 2K output and task polling for programmatic retrieval. Accepts English and Chinese prompts for broader prompt input.

Cons: Requires an MCP-compatible host application and developer setup. Needs a platform API token configured as ACEDATACLOUD_API_TOKEN. Processing relies on the platform’s hosted endpoints, not local-only. Non-developers face a setup and integration barrier.

Pros: Supports text-to-video, image-to-video, and character transfer workflows. Hosted endpoint removes the need for local GPU hardware. MCP tools (wan_generate_video, wan_get_task) for programmatic integration.

Cons: Requires active internet connection and an AceDataCloud API token. Top output resolution is 1080P, limiting true 4K workflows. Data is processed on the provider's hosted endpoint, not local-only.