#llm Repositories
2,314 repositories total
The backend agents build with - Multimodal database, orchestration, and serving in one file
Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
A beautiful, cross-platform downloader for YouTube, TikTok, Instagram, and 1800+ sites (yt-dlp GUI) with AI video summaries and post-processing
Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.
The open LLM inference engine for AWS Trainium: NKI megakernels, 1M-token context, OpenAI-compatible API. By RunAnywhere.
Claude reads its own source code โ 17-chapter architectural deep-dive into Claude Code v2.1.88. EN/ZH bilingual.
A curated list of awesome resources, tools, and other shiny things for LLM prompt engineering.
An enterprise AI workspace for model routing, multimodal chat, files, tools, billing, identity, and operations.
One sentence creates an AI-driven world โ generate maps, characters, and watch stories emerge on their own.
This repository provides an advanced Retrieval-Augmented Generation (RAG) solution for complex question answering. It uses sophisticated graph based algorithm to handle the tasks.
ktx is an executable context layer for data and analytics agents ๐ Allow Claude Code, Codex, or other AI agents to query analytical databases accurately and with full context of your company
AI coding harness for desktop, terminal and CI. Maps your repo, edits code by symbol through AST and LSP, then runs your checks. Any model or the plan you already pay for. Get it at https://empryo.com
Turn any LLM into a Jev-style decision model: typed decisions, real probabilities, no training. (continue updating, welcome any issue and PR request)
WikiChat is an improved RAG. It stops the hallucination of large language models by retrieving data from a corpus.
[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.
AIDE: an LLM agent for machine learning engineering - the research Weco grew out of. Referenced in OpenAI MLE-bench.
Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.
Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
"Building Large Language Model Applications: Application Development and Architecture Design" is an open-source e-book about real-world LLM applications, introducing the basics and applications of large language models, as well as how to build your own model. It includes prompt writing, development, and management, exploring what the best large language models can offer, and LLM application development patterns and architecture design.
The official GitHub page for the survey paper "A Survey on Evaluation of Large Language Models".
A powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jailbreaks in their LLM APIs.
Nativ is an open-source local AI app for Mac. It runs open AI models on Apple Silicon, and nothing leaves your Mac.
ExtractThinker is a Document Intelligence library for LLMs, offering ORM-style interaction for flexible and powerful document workflows.
Self-hosted web search for AI agents and SEO. Google, Bing, Yandex, Baidu, DuckDuckGo & Ecosia, rendered in a real browser: ranked results and clean page Markdown. API, CLI, MCP ๐
NVIDIA GPU exporter for Prometheus using the nvidia-smi binary OR NVML
The community's most comprehensive, continuously-updated index of research on Large Language Models for software vulnerability detection โ papers across function-level, repository-level, agentic, and smart-contract detection, plus datasets, benchmarks, and surveys.
Charts as text in Markdown. Where they cannot be drawn, the numbers remain as a table.
Burp Suite extension that adds built-in MCP tooling, AI-assisted analysis, privacy controls, passive and active scanning and more
Chat with your data - AI data analysis and visualization on CSV, Postgres, MySQL, Snowflake, SQLite...
Guides and resources for AI engineers: an agents course, five handbooks, a hands-on second-brain project and a vetted reading list.
UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)
Source-available agent platform for Global ร China enterprises โ wire every system through one agent core. Self-hosted, any LLM.
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B
1,310 professional Agent Skills for Claude, Claude Duet, ChatGPT, Gemini, Cursor & Codex: PRDs, postmortems, leases, medical bills, payroll checks, morning briefs. 21 skills built for always-on agents like Claude Duet. Plain markdown, MIT, in Anthropic's plugin directory. Free in-browser or npx pm-claude-skills add.