#llm Repositories
2,313 repositories total
A universal git-native AI agent framework. Your agent lives inside a git repo โ identity, rules, memory, tools, and skills are all version-controlled files.
One-click, privacy-first exporter for Claude.ai chats โ clean Markdown with artifacts and attachments, ready for Obsidian and RAG.
[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
A collection of awesome-prompt-datasets, awesome-instruction-dataset, to train ChatLLM such as chatgpt ๆถๅฝๅ็งๅๆ ท็ๆไปคๆฐๆฎ้, ็จไบ่ฎญ็ป ChatLLM ๆจกๅใ
"AI Full Stack - Excellent Resource Collection Site of the Entire Network": Collects excellent resources from the entire network, records solution strategies and key points for engineering practice problems, shares various practical cases, tracks the development of cutting-edge technologies, and covers AI full-stack knowledge, including large models, programming technologies, machine learning, deep learning, reinforcement learning, graph neural networks, speech recognition, NLP, and image recognition.
AI application development, AI programming practice, and interview guide, covering core technologies and engineering practices such as LLM, Agent, RAG, MCP, Claude Code, and Codex.
A curated list of the best OpenClaw resources: official projects, skills, plugins, dashboards, deployment tooling, memory systems, and guides.
AI Werewolf game. You take one seat, and LLM players fill the rest. AI Werewolf.
OpenClaw Chinese Documentation Site: 767 Installation Tutorials and Source Code Analyses
Pure Rust + CUDA LLM inference engine โ no PyTorch, OpenAI-compatible, serves Qwen3 to Kimi-K2
21 writing rules for AI coding and writing agents. Drop-in for Claude Code, Codex, Copilot, Cursor, and Aider, so their output reads like a tech pro.
Implementing LLM architectures from scratch in PyTorch
๐ AI-powered, Lightweight RSS Reader. Supports: GitHub Pages | Vercel | Alibaba Cloud ESA Pages | Docker
SEAIT is a user-friendly application that simplifies the installation process of AI-related projects
Cost tracking for DeepSeek Harness: session and model costs, token usage, budgets, provider balances, and coding-plan quotas. Bilingual English/Chinese UI.
37 tok/s from Qwen3-Next-80B (48 GB) on a 32 GB laptop, 24 without drafts vs 2.8 for llama.cpp; reading 62 vs 16 tok/s. Faster than llama.cpp on all 13 models compared in Q4_K_M. LLMs bigger than your RAM, pure C, CPU or GPU.
A SOTA Industrial-Grade All-in-One ASR system with ASR, VAD, LID, and Punc modules. FireRedASR2 supports Chinese (Mandarin, 20+ dialects/accents), English, code-switching, and both speech and singing ASR. FireRedVAD supports speech/singing/music in 100+ langs. FireRedLID supports 100+ langs and 20+ zh dialects. FireRedPunc supports zh and en.
Give your AI a real, persistent memory. The open-source system plus templates that turn an Obsidian vault into your AI's working memory. No vector database, just markdown.
A collection of 265 rules across 26 categories that AI coding agents can use to write idiomatic, fast, and safe Rust.
[ICCV 2025] Official code of DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
ctxsync is a Python tool that automates the synchronization of local files with Claude.ai Projects
Let AI see your screen in real time: filter frames by how much they change and combine multiple frames into one image, so static scenes use almost no tokens.
AI video processing pipeline for generating vertical shorts using LLMs, Whisper transcription, highlight detection and automated editing
Persistent project knowledge graph for coding agents. MCP server with semantic search, in-process embeddings, and web explorer.
Engine-agnostic LLM gateway in Rust. Full OpenAI and Anthropic API compatibility across vLLM, TRT-LLM, TokenSpeed, SGLang, OpenAI, Gemini, and more. Industry-first gRPC pipeline, KV cache-aware routing, chat history, tokenization caching, Responses API, embeddings, WASM plugins, MCP, and multi-tenant authentication.
Stock market MCP server for Yahoo Finance data, technical analysis, portfolio tracking, and Python backtesting. Runs locally with no API key for core tools.
An open source implementation of code execution with MCP (Programatic Tool Calling)
A NestJS module to effortlessly create Model Context Protocol (MCP) servers for exposing AI tools, resources, and prompts.
Terminal UI to chat with large language models (LLM) using different model backends, and integrations with your favourite editors!
Extend existing LLMs way beyond the original training length with constant memory usage, without retraining
Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.
[Support 0.48.x] (Reset Cursor AI MachineID & Auto Sign Up / In & Bypass Higher Token Limit) Automatically register Cursor AI, automatically reset machine ID, free upgrade to use Pro features: You've reached your trial request limit. / Too many free trial accounts used on this machine. Please upgrade to pro. We have this limit in place to prevent abuse. Please let us know if you believe this is a mistake.
Looking for a job? Use AI Job Hunter! Let AI find jobs for you! Powered by DeepSeek and ChatGPT, your AI assistant acts as your digital twin, searching for jobs 24/7 and customizing responses based on your resume. Batch apply, automatically send resumes, and exchange contact information. Handle HR rejections and follow-ups. Get notified of high-intent job opportunities so you never miss a chance. BOSS Zhipin.
CocoPlus is an Agentic Operating System for Snowflake Coco. It brings structured, multi-agent workflows to data engineering projects โ covering everything from project initialization through spec, plan, build, test, review, and ship phases.
Geektime: LangChain Practical Course - These are direct and clear examples and explanations of a series of key modules from the early design of the LangChain framework. With the rapid evolution of LangChain, some code may need to be iterated with new versions. I hope that while you quickly browse the course concepts (still valuable), you will independently learn the latest code and progress of LangChain.
The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling
A curated list of decision models (System One / typed decision models): hosted APIs, open-weight models, runtimes, SDKs, applications, benchmarks, and papers.
A next-generation automatic algorithm design platform, making automated algorithm design more accessible and easier to use