Same agent, Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.
- observability
- llmops
- ai-observability
- openai
132,183 visible repositories in the index
481–504 of 2,136 · Most stars
Same agent, Smaller bill. The tools and infrastructure to get more work from your AI. Fewer tokens. Less compute. Lower cost.
Advanced CLI tool that scans your hardware and tells you exactly which LLM or sLLM models you can run locally, with full Ollama integration.
AI Search & RAG Without Moving Your Data. Get instant answers from your company's knowledge across 100+ apps while keeping data secure. Deploy in minutes, not months.
Toolkit for creating, sharing and using natural language prompts.
An open-source visual programming environment for battle-testing prompts to LLMs.
Open-source desktop AI agent for tools, files, knowledge, workflows, and real deliverables.
Chinese-LLaMA 1&2、Chinese-Falcon 基础模型;ChatFlow中文对话模型;中文OpenLLaMA模型;NLP预训练/指令微调数据集
Find the ghost tokens. Fix them. Survive compaction. Avoid context quality decay.
A framework for prompt tuning using Intent-based Prompt Calibration
Lucebox inference engine for heterogeneous hardware & consumer GPUs
.NET library for the OpenAI service API by Betalgo Ranul
NeMo Retriever Library is a scalable, performance-oriented document content and metadata extraction microservice. NeMo Retriever Library uses specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images that you can use in downstream generative applications.
A Model Context Protocol server for converting almost anything to Markdown
A new SOTA for RAG — an original retrieval architecture and an open-source knowledge base for humans and agents.
Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models
Infinity is a high-throughput, low-latency serving engine for text-embeddings, reranking models, clip, clap and colpali
Practical bilingual AI prompt library for prompt engineering, work, learning, content, marketing, and everyday use.
The pretty much "official" DSPy framework for Typescript
pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tidb.ai
LinkToken is an open-source unified token management platform that provides token distribution, access control, and usage analysis functions.
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparent evaluation of foundation models, including large language models (LLMs) and multimodal models.
mean Average Precision - This code evaluates the performance of your neural net for object recognition.
A general fine-tuning kit geared toward image/video/audio diffusion models.
Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time