#llm Repositories
2,314 repositories total
GraphBit is the worldโs first enterprise-grade Agentic AI framework, built on a Rust core with a Python wrapper for unmatched speed, security, and scalability. It enables reliable multi-agent workflows with minimal CPU and memory usage, making it production-ready for real-world enterprise environments.
Claude Codeโstyle dynamic workflows for Pi: code-mode subagents with real model routing, journaled resume, git-worktree isolation, cost accounting, an interactive /workflows TUI, an /ultracode standing opt-in, and deep research.
The definitive OpenAI, Claude, MCP, Harness, Evals, and Production Agent Systems learning roadmap.
30KB Markdown-native WYSIWYG editor for React, built for AI streaming, human editing, huge files, macOS, Web, and agent workflows.
CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.
MindWork AI Studio is a free, independent cross-platform desktop app for local and cloud LLMs across providers, built to democratize AI access.
FoJin-powered Buddhist AI persona framework โ source-grounded, boundary-aware, fidelity-tested, runtime-ready.
ComfyUI nodes for vision-language models: Qwen3-VL, Moondream 3, Florence-2, SmolVLM2, InternVL, Gemma 3, MiniCPM-V. Plus open-vocabulary detection, SAM2/SAM3 segmentation, video temporal reasoning, GGUF via llama.cpp, and hosted LLM/VLM APIs.
Leverage hallucinations from Large Language Models (LLMs) for novelty-driven explorations.
91.5% fewer tokens in tool output on Headroomโs own benchmark, where Headroom removes 61.4%. Separately, the same SWE-bench tasks resolved at 0.71x the cost of plain Claude Code. Plus memory across sessions and subscription quota pacing. Claude Code, Codex, Copilot, Gemini, and 12 more. Local, MIT.
Streaming highlighting with Shiki. Useful for highlighting text streams like LLM outputs.
A beginner-friendly tutorial to AI Agents, starting from zero. More than just a tutorial, itโs also an Agent you can run locally: read and write files, execute commands, use MCP and long-term memory, and follow every step in a built-in web interface. Start with a minimal 100-line loop, add one capability per lesson, and finish by breaking down popular Agents such as Claude Code and Codex.
new-api / sub2api proxy account management center: balance, API key, usage, rates, model price comparison | https://nvcenter.cc
Turn any document into clean, AI-ready Markdown. Local-first desktop app: reads scanned PDFs, batches folders, runs offline, and uses far fewer tokens than vision models.
Enables organizations to create and deploy customizable AI agents with support for multiple LLM providers, real-time chat, voice, document training, analytics, user management, SSO authentication, and embeddable widgets. Built with React 19, Redux Toolkit, Radix UI, and Tailwind CSS.
[ICLR2025 Spotlight๐ฅ] Official Implementation of TokenFormer: Rethinking Transformer Scaling with Tokenized Model Parameters
Fullstack "Chat with your PDFs" RAG (Retrieval Augmented Generation) app built fully on Cloudflare
A desktop application that extracts YouTube playlist transcripts and enhances them using Google's Gemini AI models. The output is a book in any language you want.
appbuilder-sdk, Qianfan AppBuilder-SDK helps developers flexibly and quickly build AI-native applications
๐ญ AI Avatar / digital human platform โ upload a photo, clone a voice, talk to any face in real time with lip-sync video. Open-source, self-hosted. Claude ยท Whisper ยท Chatterbox ยท MuseTalk.
A curated solutions to building a self-evolving second brain that helps AI agents understand your personal and team context.
A secondary development-ready Chat Bot single-turn dialogue Web MVP prototype template, built with mainstream technologies including Vue 3, Vite 8, TypeScript, Naive UI, Pinia (v3), and UnoCSS. ๐งค Features simple integration of LLM APIs, single-turn AI Q&A mode with independent responses (no context required), SSE typewriter-effect streaming output, and integrated markdown-it with Mermaid/KaTex/LaTex formula highlighting. Supports iFlytek Spark, Zhipu AI, SiliconFlow, and DeepSeek V4/V3/R1 deep reasoning model previews, compatible with <think> tags, and includes distilled skills. ๐ผ Easy to customize and rapidly build Chat-based LLM products (example screenshots included).
IIMS delivers a modern fullโstack solution via Spring Boot 3.5 (Javaย 17) and Vue 3 (TypeScript), featuring RBAC/JWT authentication, Milvusย RAG, Springย AI (Ollama/DeepSeek/OpenAI), MyBatisย Plus, MySQL, Redis, MinIO, Elementย Plus, Pinia, Vditor, Mermaid, plus dedicated EAS and DMS modules.
Can AI engines cite your site, and do they? Free 0โ100 readiness score on an open GEO rubric, plus ask and weekly citation tracking via OpenAI, Perplexity, Gemini, Anthropic and OpenRouter with your own keys. Zero dependencies; CLI, GitHub Action and MCP server.
Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike static benchmarks, this platform introduces evolving environments where agents must adapt their strategies as new information becomes available, mirroring real-world challenges.
๐ฅ cpdown - Copy to clipboard any webpage content/youtube subtitle as clean markdown with one click or shortcut
[ECCV2024] Grounded Multimodal Large Language Model with Localized Visual Tokenization
[NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understanding
Campus recruitment, fall recruitment, spring recruitment, great internship projects, guiding you to implement from scratch a large model inference framework supporting Llama2/3 and Qwen2.5.
โก DocsAgent โ chat with your Zotero library from your phone. Native iPhone app + free Mac companion. MCP server for Claude, Cursor & Cline: instant, private search across Zotero, Obsidian & Apple Notes, fully local (~15 ms).
A Deep Learning NLP repository that summarizes text preprocessing, Topic Models, and downstream tasks of state-of-the-art models such as BERT, GPT, and LLMs using TensorFlow.
Open source web infrastructure for AI. Scrape, crawl, and automate the web, clean markdown, browser sessions, ready for your agents.
A highly efficient, secure, and stable application development platform with excellent performance, easy scalability, and deep integration of AI capabilities such as LLM, AI Chat, RAG, and Agents.
Train and Infer Powerful Sentence Embeddings with AnglE | ๐ฅ SOTA on STS and MTEB Leaderboard
FineEnvs โ RL Environments 101: Building and Scaling RL Environments in the Age of LLMs
AI-native cross-platform sandboxes for developers, featuring multimodal cloud runtime and expert agents.