#llm Repositories
2,314 repositories total
Multi-LLM peer review for code decisions. Bring your own CLI; Chorus convenes 2-4 other LLMs to review the work before you ship.
๐ An out-of-the-box powerhouse for academic PDF translation | Windows + Mac | Perfectly preserves equation formatting ยท Deep Zotero integration ยท 35 languages ยท 20+ AI translation engines ยท Tables/OCR/Glossaries ยท Batch translation | Based on PDFMathTranslate (EMNLP 2025)
๐ง AI-powered Personalized Exam System: Integrating OpenPangu LLM, Knowledge Graph RAG, and BKT algorithm for adaptive question generation and recommendation. Intelligent personalized question generation system based on LLM and Knowledge Graph.
Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414
๐งฑ AI Product Manager Starter Knowledge Base: Interview Question Bank ยท AI Fundamentals ยท Case Studies ยท Learning Roadmap | Whether you're switching careers from scratch or continuing to grow, one repository is all you need
Introductory examples for building LLM-based AI agents. Asynchronous Books: 'Large Model Application Development: Hands-on AI Agents' - These are very simple introductory examples aimed at guiding beginners. The field of LLM development is evolving rapidly, and this book serves only as an overview. You can explore more examples and code in the OpenAI Cookbook and LangChain Example.
ModelScope Purple Book | ModelScope Cookbook: A hands-on guide to open-source model applications for developers, covering model selection, inference, fine-tuning, evaluation, RAG, agents, and AIGCโfrom running your first model to building real-world applications.
Turn your workday into structured workflows agents can execute. 100% local, served over MCP.
Self-hosted Lovable/v0 alternative. Realtime database & storage included.
๐ Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future
Local-first AI agent memory with a knowledge graph, ontology constraints, and traceable reasoningโall in one SQLite file.
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, costs pennies per call with your own keys. Imports Dialogflow CX.
VectorRAG.Net is a .NET-native high-performance vector database library for semantic search and RAG (Retrieval-Augmented Generation). Core search is based on Random Hyperplane LSH candidate generation with exact rerank by dot/cosine.
Open Model Engine (OME) โ Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton
Frametell: Turn your ideas and materials into vivid explainer videos with an AI director agent. Local-first, any model.
Open source AI company OS. 38 roles, 6 templates, 4-layer memory. Your AI company remembers everything โ locally. npx clawcompany
A Model Context Protocol (MCP) server that enables AI agents and LLMs to query and analyze Prometheus metrics through standardized interfaces.
๐ Capri โ an Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.
Learn LLM Inference Engineering step by stepโfrom KV cache, PagedAttention, and continuous batching to vLLM, SGLang, and GPUs.
pi had nothing (nothing), so I made something (something) โ sorry, mariozechner-senpai, I went ahead and lovingly soiled your pure pi for you. An opinionated fork of badlogic/pi-mono with extension-first additions. Ganbare, ganbare, senpai ้ ๅผตใ้ ๅผตใๅ ่ผฉ
The Supabase of AI era. A modular, open-source backend for building AI-native software โ designed for knowledge, not static data.
AI Quantitative Stock Selection System: Automatically selects stocks daily across 7 markets, including A-shares, U.S. stocks, and Hong Kong stocks; screens announcements for red flags and verifies win rates publicly. Runs at zero cost | AI stock screener (7 markets): red-flag filter, live T+N track record & free daily runs
Self-Programming AI Assistant. Capture, automate, and refine all your workflows.
Blitz Strike โ a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report.
Open-source agentic ops platform for cloud, SRE, DevOps, support and FinOps teams. AI agents investigate incidents, cut cloud and Kubernetes waste and run approval-gated runbooks across Kubernetes, AWS, Azure, GCP and your databases. Self-hosted, bring your own models.
Open-source, local-first AI video clipper. Long video in, caption-burned speaker-tracked 9:16 clips out. Fully offline with Whisper + Ollama, or bring your own API key.
Lyrie.ai โ The world's first autonomous AI cybersecurity agent. Built by OTT Cybersecurity LLC.
KVarN is a native vLLM KV-cache quantization backend for your agents: 3โ5ร more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.
Open-source AI Employee Platform โ Create AI employees that collaborate with your real team in WeCom, DingTalk, and Feishu, just like hiring a few more colleagues.
MedResearcher-R1 is a deep research agent for medical scenarios, built on a knowledge-informed trajectory synthesis framework.
๐ก Awesome RAG: A resource of Retrieval-Augmented Generation (RAG) for LLMs, focusing on the development of technology.
Design, conduct and analyze results of AI-powered surveys and experiments. Simulate social science and market research with large numbers of AI agents and LLMs.
AI-powered contract review skill with CUAD risk detection, market benchmarks, and lawyer-ready redlines. Works with Claude Code, Codex, Cursor, and 26+ tools.
An instant, automatic manga translation app for Android phones, powered by LLMs.
This repository contains documentation created to better understand the open project
RESTai is an AIaaS (AI as a Service) open-source platform. Supports many public and local LLM suported by Ollama/vLLM/etc. Precise embeddings usage, tuning, analytics etc. Built-in image/audio generation with dynamic loading generators. Live chat deployment. Built-in block based graphical language. Prompt versioning and much more...
Cyber Doctor Projectโ"Cyber Huatuo," a multifunctional intelligent agent based on multimodal large models that lets you build a local multimodal large model with one click. After connecting it to medical and healthcare-related knowledge graphs and knowledge bases, it can perform functions such as preliminary disease assessment, medical record analysis, and professional medical knowledge Q&A, becoming your personal doctor. The Cyber Huatuo project helps disseminate medical resources across regions, enabling more people to improve their health with the help of large models. "Cyber Huatuo"โan easy-to-build personal doctor agent based on LLMs, knowledge graphs, and knowledge bases.
Run any model in Grok Bot โ one-command setup, a model picker UI, evidence-based provider wire maps, and an update-proof doctor. Not farming you, arming you.