FunASR: FunASR is a fundamental end-to-end speech recognition toolkit. It offers industrial-grade speech recognition, being 170x faster than Whisper, supporting over 50 languages, and integrating features like speaker diarization, emotion detection, and streaming.; MemoryPilot: MemoryPilot is a state-of-the-art MCP memory server that gives AI coding assistants persistent, searchable memory. It features hybrid search (BM25 + multilingual embeddings), temporal knowledge graph, GraphRAG, AAAK compression, and zero-shot auto-classification. It is 100% local, runs as a single binary, and achieves 99.1% R@5 on the LongMemEval benchmark.
Meeting transcription with speaker labels, timestamps, and punctuation
Persistent memory for AI coding assistants across sessions