Extract entities, topics, key phrases, and summaries from text using configurable AI providers with automatic fallback.
MIT
203,974 tools. Last updated 2026-06-14 21:27
"ONNX" matching MCP tools:
- Executes a full SQL query clustering pipeline to identify high-CPU queries and optimize database performance through grouping similar queries and analyzing performance metrics.MIT
- Store and persist conversation memories for AI agents. Supports episodic, semantic, and procedural memory types with adjustable importance weights.MIT
- Extract text from images using offline OCR. Reads text from screenshots, documents, and photos via local file paths or base64 data.MIT
- Converts any 2D image or video TOP into a depth map using Depth Anything v2 with NVIDIA TensorRT/ONNX, no depth sensor required. Outputs depth TOP path directly for displacement, pop field, or silhouette.MIT
- Execute a complete SQL query clustering pipeline to identify high CPU usage queries for optimization analysis, extracting logs, calculating performance metrics, generating embeddings, and grouping similar queries.MIT
Matching MCP Servers
- AlicenseAqualityBmaintenanceLocal RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.Last updated1291MIT
- AlicenseAqualityAmaintenanceLocal-first dev memory: indexes Git commits, PRs, Jira/Linear tickets, Confluence docs, Slack threads, and Calendar events into a local SQLite/FTS5/ONNX index, and exposes them as MCP tools so Claude Code, Cursor, and Codex can search and cite your past work.Last updated151MIT
- Executes a complete SQL query clustering workflow to identify and analyze high CPU usage queries, enabling targeted optimization of database performance.MIT
- Index PDFs into a named knowledge database layer for persistent, cited memory. Uses local embeddings without API keys.AGPL 3.0
- Create a semantic knowledge base layer from PDFs. Index files into a named database and optionally force re-index of already indexed files.
- Search official Onyx programming language documentation to find answers and code examples for development questions.
- Discover GitHub repositories containing Onyx code, sorted by stars or name to find relevant projects.
- Execute Onyx code to test and debug programs by running code snippets and returning output or errors.
- Build Onyx packages using the onyx pkg build command in a specified directory with configurable timeout settings.
- Execute WebAssembly files with the Onyx runtime by specifying file paths and execution parameters for running WASM code.
- Inspect ONNX model layers and extract specific components with layer-aware precision.
- Retrieve struct definitions and code examples for the Onyx programming language from GitHub documentation to understand data structures and implementation patterns.
- Search the Onyx backend to find relevant documents by topic, retrieve matching chunks or full documents, and filter results by document sets.MIT
- Compile Onyx programming code into executable files by running the build command in a specified directory. This tool processes source code to generate working programs.
- Generate text embeddings using ONNX Runtime C API, producing .bfvec files for semantic similarity and inference tasks.
- Retrieve Onyx programming language function definitions and code examples from GitHub documentation to support development tasks.