Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

llama mistral fine-tuning mlops bentoml vicuna llm model-inference llmops llm-serving llm-inference open-source-llm llama2 openllm llm-ops llama3-1 llama3-2 llama3-2-vision

• Updated Nov 9, 2026
• Python

OpenLLMWiki: Docs of OpenLLMAI. Survey, reproduction and domain/task adaptation of open source chatgpt alternatives/implementations. PiXiu-貔貅 means fortune.

llama chatgpt chatgpt-bot chatgpt-app chatglm chatgpt-alternatives chinese-chatgpt chatzhihu chatzhangsan openllm openllmai

• Updated Dec 10, 2024

Self-hosted, Docker-first OpenAI-compatible LLM gateway with provider routing, fallbacks, API keys, and usage controls.

api-gateway self-hosted api-proxy multi-provider fastapi openai-api openai-codex llm langchain llmops openrouter openllm ai-gateway langgraph llm-observability anthropic-api llm-gateway model-routing fallback-routing llm-multi-provider

• Updated Aug 5, 2026
• Python

OpenLLM Monitor is a plug-and-play, real-time observability dashboard for monitoring and debugging LLM API calls across OpenAI, Ollama, OpenRouter, and more. Tracks tokens, latency, cost, retries, and lets you replay prompts — fully open-source and self-hostable.

nlp machine-learning sdk ai monitoring openai model-evaluation plug-and-play model-monitoring model-performance llm ollama openllm

• Updated Jul 7, 2026
• JavaScript

Perform RAG (Retrieval-Augmented Generation) from your PDFs using this Colab notebook! Powered by Llama 2

ai chatbot transformers colab colab-notebook rag huggingface llm llama-index llamacpp retrieval-augmented-generation llama2 openllm

• Updated Mar 24, 2024
• Jupyter Notebook

LLM, Fine Tuning, Llama 2, Gemma, Mixtral, vLLM, LangChain, RAG, ChromaDB, FAISS

nlp gemma faiss rag llm langchain vllm chromadb genai llama2 finetune-llm openllm mixtral

• Updated Mar 5, 2024
• Jupyter Notebook

An offline AI chat application built specifically for Ubuntu Touch, allowing users to run lightweight Large Language Models (LLMs) directly on their mobile device.

ai chatbot gemma inference-engine local-first local-ai ollama qwen openllm gguf-models openweight ubuntuai

• Updated Nov 8, 2026
• QML

NeuroSwift 1.0.0 is the world's most advanced MatMul-Free Hybrid State-Space Model (H-SSM). By integrating Dynamic Depth Scaling (DDS), Selective SSD (Mamba-2), and MLA (DeepSeek), it achieves the intelligence of the world's largest dense models with zero-latency CPU inference.

ai deep-learning neural-network transformers pytorch openai moe ssm hebbian-learning cpu-inference llm openllm claude-code

• Updated Apr 9, 2026
• Python

RAG with LlamaIndex and NVIDIA

rag nvdia large-language-models llm generative-ai llamaindex openllm

• Updated Apr 29, 2024
• Jupyter Notebook

Selectia - A family of System One-style models fine-tuned from LFM 2.5, designed for one-pass typed decisions with calibrated probabilities. Decision API (Choice, Noul, Score) powered by open LLMs.

python api decisions typesafe choice score slm logits openllm jev noul openjev

• Updated Sep 23, 2026
• Python

Genify is a powerful and versatile API that leverages advanced language models, including Google's Gemini 1.5 Pro, LLAMA 3 and other cutting-edge technologies, to deliver a wide range of natural language processing capabilities

mongodb python3 gemini-api fastapi generative-ai llama-index palm-api retrieval-augmented-generation llama2 openllm mistral-7b gemini-pro-vision gemini-pro gemini-pro-1-5 llama3

• Updated Apr 12, 2025
• Python

Build fast neural network training with 100+ steps/sec on CPU using NeuroSwift's ternary and kernel-fused engine

ai deep-learning neural-network transformers pytorch openai moe ssm hebbian-learning cpu-inference llm openllm claude-code

• Updated Oct 12, 2026

DeepSeek Harness (dsh) bundle: route the harness through OpenLLM (OpenAI-compatible) + register the OpenLLM MCP, with CLI/daemon onboarding.

plugin mcp dsh cordis llm openllm ai-gateway model-context-protocol openai-compatible deepseek-harness dsh-plugin

• Updated Nov 11, 2026
• TypeScript

Masterclass on GraphRAG for Exploring Heterogeneous Medical Knowledge

neo4j virtualization ontology healthcare openllm qwen2 graphrag gemma3

• Updated Dec 4, 2025
• Jupyter Notebook

Learn from YOUTUBE lengthy videos with effective Q & A

django reactjs nlp-machine-learning openllm

• Updated Mar 20, 2024
• Python

Web for Selectia - A family of System One-style models fine-tuned from LFM 2.5, designed for one-pass typed decisions with calibrated probabilities.

python api decisions choice score slm logits openllm typesave jev noul

• Updated Sep 27, 2026
• HTML

ollama llm setup shell script for ubunta

shell-script llm generative-ai ollama openllm

• Updated Jan 6, 2025
• Jupyter Notebook

Route LLM requests through a self-hosted, OpenAI-compatible gateway for local projects and team workflows.

go sanitization baduk self-hosted golang-library api-proxy multi-provider fastapi github-config openai-codex llm langchain llmops openrouter openllm ai-gateway langgraph llm-observability llm-gateway fallback-routing

• Updated Oct 12, 2026
• Python