huggingface — independent software & tools
-
DMJ-Dataset-Builder
Automate the preparation, validation, and merging of high-quality instruction-tuning datasets for Large Language Models.
-
prose
A professional and lightweight dataset editor in JSONL format for training text-based AI models
-
vibe-tuning
Calibrate your Claude Code assistant to diagnose and fix recurring errors by saving permanent root cause patterns after every mistake.
-
litellm-free-models-prox-DNy
Hardened local-only LiteLLM gateway — auto-discovers free/trial LLM models from 15+ providers (OpenRouter, Groq, Gemini, Cerebras, NVIDIA NIM, SambaNova, Cohere, GitHub Models, etc.). Single OpenAI-compatible endpoint at 127.0.0.1:4000. Role-based aliases for AI coding agents.
-
Chaty
Private, on-device AI desktop app — GGUF (llama.cpp) & MLX models, a local coding agent, RAG knowledge base, Deep Research, vision and voice. 100% offline, no account, no telemetry. Windows & macOS.
-
open-model-license-index
Browse license metadata for popular open models, sourced from Hugging Face model cards, tags, and repo files.
-
python-sdk
Integrate the Assinafy API into your Python applications to manage electronic signatures, documents, and webhooks with a synchronous client.
-
sophia-agi
Wisdom before intelligence. A provenance-aware reasoning layer that abstains instead of fabricating — stops LLMs inventing attributions and merging distinct traditions. Measured: 0% fabrication on unknown-answer traps (vs 17–25% raw); −12.5pt hallucinated attributions at 0% false-positive cost. An AGI-candidate proof package, not proven AGI.
-
hugrs
Unified model weight mirror service for Hugging Face and ModelScope with shared, compressed chunk storage for efficient AI model hosting and distribution. 共享压缩分块的hf/ms统一镜像服务.
-
@huggingface/inference
Typescript client for the Hugging Face Inference Providers and Inference Endpoints
-
claude-swarm
🚀 Orchestrate parallel Claude Code workers with persistent state and behavioral governance for efficient, autonomous coding sessions.
-
fastapi-gen
Build LLM-enabled FastAPI applications without build configuration.
-
ai-nexus
-
mcp-ai-wpoos
NV Digital Open Operator System (NV oOS) is an Object-Oriented AI framework for WordPress connecting your data with OpenAI, Gemini, Anthropic, DeepSeek, Hugging Face, Cloudflare, OpenRouter & Ollama (Local) models. Create & manage AI Assistants that can interact with users, access WordPress (API) data, & perform as a MCP Server & Chat Agent
-
agent-review
Analyze git code changes to generate structured review reports using flexible AI models and integrated workflows.
-
second-brain
🧠 Capture and organize your ideas with an AI-powered system that turns thoughts into actionable knowledge, all without coding.
-
n8n-llm-workflows
🌟 Manage and deploy n8n workflows at scale with this TypeScript toolkit for LLM automation, featuring example workflows and a typed client for bulk operations.
-
audio_align
🎧 Align audio to text effortlessly with precise word-level timing using OpenAI Whisper, outputting clean JSON for seamless integration.
-
tengra-market
Marketplace for Tengra — themes, MCP modules, language packs, skills, and model indices