llm

A CLI in Rust to generate synthetic data for MLX friendly training

一款强大的大模型微调数据集生成和管理工具。

A comprehensive, professional guide explaining the differences, strengths, and best practices of Retrieval-Augmented Generation (RAG) and Fine-Tuning for LLMs, including workflows, comparisons, decision frameworks, and real-world hybrid AI use cases.

A reasoning assistant for your STEM education

Chat interface for OpenBB based on a instruct finetuning of a LLM, similar to ChatGPT.

Semantic search knowledge base for MCP-enabled AI assistants. Index local files or GitHub repos, query with natural language. Built on LanceDB vector storage. Works with Claude Desktop, Cursor, and other MCP clients.

Fast vector search in PostgreSQL

Official Core Services for MemFuse - the lightning-fast open-source memory layer that gives LLMs persistent, queryable memory across conversations and sessions.

Persistent cognitive memory for AI agents — drop-in MCP server for Claude Code, Cursor, Windsurf. Temporal decay, contradiction detection, knowledge graph, autonomous consolidation. Backed by the YantrikDB Rust engine. Install: pip install yantrikdb-mcp.

Self-hosted AI knowledge base with hybrid semantic search (pgvector + FTS + RRF), MCP server, multi-provider LLM inference (Ollama, OpenAI, OpenRouter, llama.cpp), multimodal ingestion (vision, audio transcription, speaker diarization), and knowledge graph. Rust + PostgreSQL.

One Mac process. Many models. Real speed. Multi-model LLM serving with prefix reuse, MTP acceleration, and OpenAI APIs — built for Apple Silicon, measured against mlx-lm and llama.cpp.

Sumi — Free, open-source voice dictation for macOS. Local-first Whisper + LLM polish, with built-in free cloud APIs.

A simple CLI to transcribe Youtube videos or local audio/video files and produce LLM-cleaned transcripts for analysis, reading, or subtitles.

大模型推理框架加速，让 LLM 飞起来

Run the LLM Swarm Router on machines to distribute Local Ai to the Swarm - More Machines - MORE SPEED

Local-first desktop assistant for the whole job hunt — scrape listings, match with a local LLM, generate applications in your own voice, and track everything on a Kanban board.

Consumer-aware compression for embedding indexes and LLM KV caches — compress by the metric the downstream consumer actually uses. PCA-Matryoshka + TurboQuant (27x @ 99.8% recall@10), asymmetric K/V, CUDA/Triton kernels, vLLM plugin, replayable CI-gated claims. MIT.

A distributed training framework for large language models powered by Lightning.

MinimalGPT is a concise, adaptable, and streamlined code framework that encompasses the essential components necessary for the construction, training, inference, and fine-tuning of the GPT model. This framework is implemented exclusively using Keras and TensorFlow, ensuring compatibility and coherence within the broader deep learning ecosystem.

A structured knowledge base for large language model technologies, covering LLMs, Agents, RAG, model training, evaluation methodologies, and AI engineering practices.