Large Language Models: open-source projects on GitHub
154 repositories on Large Language Models, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
AWESOME LLM FOR RECOMMENDERS
Collection of 1500+ papers and resources on LLM in recommender systems. Constantly updated, covers training, inference, and evaluation quality.
★ 1,567THEPIPE: DATA FROM DOCUMENTS FAST
ThePipe uses vision‑language models to extract data from PDF, Word and PowerPoint. It recognises tables, text and images, turning them into ready‑to‑use structures. Suppo
★ 1,530 · PythonLUA N1AO AGENT: AI-PENTEST
An autonomous AI agent for system penetration, using a dual reasoning graph. Developed by Professor Lu Hui's team from Guangzhou.
★ 1,476 · PythonAWESOME-RAG: BEST RAG APPLICATIONS
Curated list of the best Retrieval-Augmented Generation projects in Generative AI. 1284 stars ⭐
★ 1,429LLM IN SPACY PIPELINE PAINLESSLY
spacy-llm connects GPT, Claude, Cohere and open models to spaCy pipeline. Configure via config, get structured Doc with entities and relations. No wrapper code — pure NLP
★ 1,399 · PythonAWESOME-LLM-RAG: BEST RAG SOLUTIONS
A collection of the best resources and libraries for building Retrieval Augmented Generation in large language models.
★ 1,374MULTI-AGENT LLMS SURVEY 2024
A comprehensive review of LLM-based multi-agent systems — progress, challenges, and prospects. The paper has been accepted at IJCAI 2024.
★ 1,335HACKINGBUDDY GPT HELPER
The project helps ethical hackers use LLMs in 50 lines of code or less. Rapid AI integration into pentest workflows.
★ 1,328 · PythonEMBEDANYTHING - POWERFUL INFERENCE ON RUST
EmbedAnything is a high‑performance, modular, and memory‑safe framework for inference, ingestion, and indexing on Rust.
★ 1,324 · RustPARALLAX: BUILD AI CLUSTER
Parallax lets you quickly deploy a distributed inference service on any infrastructure.
★ 1,301 · PythonKVPRESS: LLM CACHE COMPRESSION
Library for easy compression of LLM KV‑cache, accelerating generation and reducing GPU memory consumption.
★ 1,254 · PythonLIGHTMEM — Efficient LLM Memory
Lightweight generation with extended memory from the authors of ICLR 2026. 934 stars on GitHub.
★ 1,223 · PythonFOUNDATION MODELS FRAMEWORK
A practical lab for building and testing applications using Apple Foundation Models.
★ 1,192 · SwiftLLM SANDBOX: OPEN AND RUN CODE
A lightweight and portable sandbox for executing code in Python LLM applications.
★ 1,144 · PythonClinical Evidence Benchmark
Benchmarks assistant responses by extracting the single fact underlying each answer and testing if the action follows that evidence.
★ 1,131 · PythonObserval - AI Agent Oversight
Observal is a platform for monitoring, evaluating, and debugging AI agents with human-in-the-loop feedback. It is essential for building reliable production pipelines.
★ 1,118 · PythonONTOGPT: ONTOLOGY EXTRACTION
Ontogpt — an LLM‑tool for extracting ontologies from text, including the SPIRES method. It builds hierarchical taxonomies and generates OWL/RDF schemas ready for use in d
★ 1,099 · Jupyter NotebookMARKLLM: WATERMARK FOR LLM
MarkLLM — open-source toolkit for watermarks of large language models. Allows embedding, checking and comparing different watermark schemes. Supports popular LLM and inte
★ 1,093 · PythonFRAMEWORK FINE-TUNING FOR iOS 26
Examples of apps for the Foundation Models Framework on iOS 26 and macOS 26 — exploring fine‑tuning of LLMs directly on the device.
★ 1,060 · SwiftLLM Architecture
A step‑by‑step exploration of LLMs, from tokenization through attention to inference optimization.
★ 989DATA PREP KIT: ACCELERATE AI GENERATION
Open-source toolkit for preparing data to train and use GenAI models. Simplifies cleaning, transformation, and labeling of datasets.
★ 969 · HTMLAI-BOOTCAMP — YOUR PATH INTO AI
Self-paced GenAI bootcamp: from ML basics to AI agents. 909 ⭐ on GitHub. Jupyter Notebooks, hands‑on with top models.
★ 959 · Jupyter NotebookNEO: Vision-Language Models
A series of multimodal Vision-Language models built from scratch. 839 stars on GitHub.
★ 926 · PythonANYGPT — UNIFIED MULTIMODAL LANGUAGE MODEL
AnyGPT is a universal multimodal model built on discrete sequence modeling. It generates images, music, and speech from text and understands translation between modalitie
★ 889 · PythonAWESOME AGENTIC DEEP RESEARCH
A collection of the best resources on agentic deep research from ACL 2026 KnowFM. Helps find cutting-edge methods and tools.
★ 876HALO: FRAMEWORK FOR LLM TRAINING
Halo is an open-source framework from White Circle for training large language and multimodal models. It supports agent-based training, async-RL, distributed training, an
★ 862 · PythonPARROT.NVIM: STOCHASTIC PARROT
The plugin adds an AI parrot to Neovim, generating code and comments on the fly.
★ 792 · LuaLLM-APPS-JAVA-SPRING-AI — QUICK AI START
Examples of Java applications on Spring Boot using Spring AI and LLM for generative AI.
★ 789 · JavaLMMS ENGINE FOR MULTIMODAL MODELS
lmms‑engine — a lightweight and flexible framework for training universal multimodal models in Python.
★ 783 · PythonFree LLM API Keys
Free API keys for GPT-5.4, Claude, DeepSeek, Gemini, Grok — copy, paste, use. Updated 3-5 times a day; no credit card required.
★ 780 · PythonLOCAL-RAG: RAG WITHOUT DATA LEAK
Ingest files for RAG with an open-source LLM — everything runs locally, with no third‑party services and no data leaving your network.
★ 768 · PythonAI Engineering Fundamentals
Free markdown‑based course teaching AI engineering from machine learning basics to LLMs, fine‑tuning, RAG, agents, inference, evaluation, safety, and system design.
★ 735 · MarkdownAUTO-ANALYST - INTELLIGENT DATA ANALYSIS
Open-source TypeScript platform for automatic data analysis using AI. Get insights in seconds without writing code.
★ 710 · TypeScriptCORAL: Multi-agent Evolution
CORAL is a lightweight infrastructure for autonomous self-evolution of multi-agent systems, designed for automated research. Compatible with Claude Code, Codex, Cursor, O
★ 668 · PythonMULTI-LLM REVEALS CELLS
The project uses coordinated responses of multiple large language models for accurate cell-type annotation in single-cell RNA-seq.
★ 662 · PythonLLM News in Social Science
A collection of outstanding works where language models are applied in social sciences. Perfect for researchers and students.
★ 653TRUSTLLM: EVALUATION OF LLM TRUSTWORTHINESS
TrustLLM — a toolkit for assessing LLM trustworthiness, presented at ICML 2024. It includes benchmark suites, metrics, and datasets for measuring hallucinations, bias, an
★ 636 · PythonMULTILSPY — PYTHON LSP CLIENT
multilspy is a Python LSP-client library that simplifies interaction with language servers for IDEs and code analysis.
★ 615 · PythonKANI: MICROFRAMEWORK FOR LLM TOOLS
Kani — a Python microframework for building tool‑calling agents with support for GPT‑4, Llama and other LLMs. It lets you quickly connect arbitrary functions and tools vi
★ 613 · PythonMMMU: Multimodal Benchmark
Code evaluation for MMMU benchmark measuring multidisciplinary multimodal understanding and reasoning for expert AGI.
★ 601 · PythonRandOpt: Task Experts Optimization
Code for ICML 2026: diverse task experts are densest around pretrained weights.
★ 590 · PythonAI RESEARCHES ITSELF
🔥 Large-scale review of AI Auto-Research — how AI automates scientific research. 386 stars on GitHub!
★ 578 · HTMLWEAVE - FUTURE PLATFORM
Weave is a high-performance platform for building applications with deep AI integration: LLMs, chatbots, RAG, and autonomous agents.
★ 562 · GoPAXML - AMAZING JAX FRAMEWORK
Pax is a JAX framework for training large-scale models with high FLOP utilization and flexible parallelization.
★ 561 · PythonLLM-API-KEY-PROXY - UNIVERSAL LLM GATEWAY
A unified API for accessing any LLM with OpenAI/Anthropic compatibility, load balancing, and request translation.
★ 561 · PythonAwesome LLM Resources List
A curated list of the best articles, tutorials, and tools for hands-on work with large language models.
★ 559 · PythonSurvive LLM Chaos
Open-source Go tool for fine-tuning, building, and deploying LLMs with a single command.
★ 545 · GoVLA MODELS FOR CARS
A collection of Vision-Language-Action models for autonomous driving: an overview of past, present, and future directions.
★ 527 · HTMLTRADITIONAL CHINESE LINTER
A Rust tool that checks grammar and style of traditional Chinese (zh-TW). 367 stars on GitHub.
★ 504 · RustFLIDE: INSTANT DECISION INFERENCE
Flide is a decision model inference engine with CUDA support. Provides deterministic inference for Gemma and other models in microseconds. Ideal for AI agents requiring s
★ 501 · PythonAwesome MLSecOps Resources
A curated collection of tools, articles, and resources on machine learning security and MLOps.
★ 492TOOL LEARNING SURVEY FOR LLM
Repository with comprehensive Tool Learning survey: taxonomy, benchmarks, and LLM tool integration methods. 493 GitHub stars.
★ 492OpenRCA: AI Finds Root Causes in Code
OpenRCA is an LLM-based framework for automatic root cause detection of failures in software. Accepted at ICLR 2025.
★ 453 · PythonGradCache: Gradient Caching
A library for efficient large-batch training in contrastive learning, overcoming GPU/TPU memory limitations through gradient caching.
★ 451 · PythonREDIS-VL-PYTHON - VECTOR LIBRARY FOR AI
RedisVL is a Python client for working with vector data in Redis, simplifying the creation of AI applications and similarity search.
★ 437 · PythonLLM Inference Engineering
Step-by-step training on inference engineering techniques for large language models: KV cache, PagedAttention, batching, and frameworks vLLM, SGLang.
★ 412 · MarkdownImageIndexer: Auto-tagging photos via LLM
It indexes images, sends requests to a local LLM, and automatically adds tags to file metadata.
★ 400 · PythonCREATE PRESENTATION WITH AI
slide-deck-ai is a Python library that generates PowerPoint presentations with AI, saving time and effort.
★ 378 · PythonUPGINI: Smart Data Search
Upgini is a library for data search and enrichment that adds features from hundreds of open and commercial sources into the ML pipeline.
★ 361 · PythonRUN LLM LOCALLY ON ANY HARDWARE
TinyLLM lets you run a local LLM and chatbot on consumer hardware. The JavaScript project uses llama-cpp-python for inference without GPU. 352 stars on GitHub.
★ 357 · JavaScriptNew projects on this topic in Telegram
Telegram →