Machine learning compiler based on MLIR for Sophgo TPU.
Repository Index
138,199 visible repositories in the index
1,897–1,920 of 3,730 · Most stars
[ICLR 2026 Oral] BIRD-INTERACT: Re-imagines Text-to-SQL evaluation via lens of dynamic interactions.
Node.js + JavaScript reference client for the Realtime API (beta)
Get GPT like chatGPT on your terminal
This Word Does Not Exist
A lightweight inference engine supporting speculative speculative decoding (SSD).
学术常用的prompts
Fast & Simple repository for pre-training and fine-tuning T5-style models
ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers (aka The Norton for OpenClaw)
AndroidWorld is an environment and benchmark for autonomous agents
Claude Code. Any Model. The most powerful AI coding agent now speaks every language.
A MULTI-GENERATOR ENSEMBLE FRAMEWORK FOR NATURAL LANGUAGE TO SQL
Tuning LLMs with no tears💦; Sample Design Engineering (SDE) for more efficient downstream-tuning.
Lite & Super-fast re-ranking for your search & retrieval pipelines. Supports SoTA Listwise and Pairwise reranking based on LLMs and cross-encoders and more. Created by Prithivi Da, open for PRs & Collaborations.
- cross-encoder
- full-text-search
- hybrid-search
- lexical-search
The repository host gives no description.
超级AI大脑一个基于SpringCloud微服务架构,已对接GPT-3.5、GPT-4.0、百度文心一言、stable diffusion AI绘图、Midjourney绘图等。支持web,Android,IOS,H5多端应用,使用了OpenAI的ChatGPT模型实现了智能聊天机器人。用户可以在界面上与聊天机器人进行对话,聊天机器人会根据用户的输入自动生成回复。同时也支持画图,用户输入文本,便可以自动制作文生文生图。持续更新中,更多功能等着你来解锁
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
- ai-agents
- ai-security
- dlp
- golang
⚕️GenAI powered multi-agentic medical diagnostics and healthcare research assistance chatbot. 🏥 Designed for healthcare professionals, researchers and patients.
A Framework of Small-scale Large Multimodal Models
Training library for Megatron-based models with bidirectional Hugging Face conversion capability
Use Claude Code for free in the terminal, VSCode extension, or via Discord
[ICML2024 (Oral)] Official PyTorch implementation of DoRA: Weight-Decomposed Low-Rank Adaptation
- commonsense-reasoning
- deep-learning
- deep-neural-networks
- instruction-tuning
🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀
[ICLR 2026] LLM/VLM gaming agents and model evaluation through games.
- computer-use
- gaming
- harness
- llm-agents