Trending AI reposUpdated daily from GitHub

A secure persistent personal agent server in Rust. One binary, sandboxed execution, multi-provider LLMs, voice, memory, Telegram, WhatsApp, Discord, Teams, and MCP tools. Secure by design, runs on your hardware.

In-browser Postgres sandbox with AI assistance (formerly postgres.new)

把 DeepSeek Harness 装进你的口袋：电脑上跑 dsh web，手机扫码即同步访问（局域网 + 公网，实时同屏）Put DeepSeek Harness in your pocket: run dsh web on your computer and access it synchronously by scanning a QR code on your phone (LAN + public network, real‑time screen mirroring)

Covers pre-training data, Tokenizer, Transformer, MoE,distributed training, Scaling Laws, inference & alignment .6 progressive code assignments for full-stack LLM learning | 涵盖预训练数据、分词器、Transformer、MoE、分布式训练、缩放定律、推理与对齐，6 项渐进代码作业，掌握 LLM 全栈知识

AudioMuse-AI uses sonic analysis to rediscover forgotten songs, uncover hidden connections in your music library, and generate intelligent playlists for Navidrome, Jellyfin, LMS, Lyrion, Emby and Plex: no metadata or external services required.

[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

🦞 OpenClaw & Hermes Agent 多引擎 AI 管理面板 — 内置 AI 助手（工具调用 + 图片识别 + 多模态），一键安装 | Tauri v2 跨平台桌面应用 | 11 种语言

Unleash Next-Level AI! 🚀 💻 Code Generation: DeepSeek r1 + Claude 3.7 Sonnet - Unparalleled Performance! 📝 Content Creation: DeepSeek r1 + Gemini 2.5 Pro - Superior Quality! 🔌 OpenAI-Compatible. 🌊 Streaming & Non-Streaming Support. ✨ Experience the Future of AI – Today! Click to Try Now! ✨

InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions

TokenSpeed is a speed-of-light LLM inference engine.

A 13B large language model developed by Baichuan Intelligent Technology

Beautiful git diff viewer, generate commits with AI, get summary of changes, all from the CLI

Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time

Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.

Official Repository for QuantHarness

Formal verification for AI: a Lean 4 + Dafny proof checker that catches fake AI proofs (reward hacking), and verified recursive self-improvement (RSI) for coding agents. AI for math, physics and software engineering.

[Up-to-date] Large Language Model Agent: A Survey on Methodology, Applications and Challenges

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

Turn expensive prompts into cheap fine-tuned models

Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI

A unified evaluation framework for large language models

Zero shot vulnerability discovery using LLMs

DBLab enables 🖖 database branching and ⚡️ thin cloning for any Postgres database and empowers DB testing in CI/CD. This optimizes database-related costs while improving time-to-market and software quality. Follow to stay updated.

基于 DeepSeek Harness 插件机制构建的远程访问方案，通过低延迟、端到端加密的 P2P 网络，支持使用 PC、移动端 和 Web 随时访问本地设备上的DSH 、CodeX、Cursor、Claude Code等工作区。 (Built on DeepSeek Harness plugins, this low-latency, end-to-end encrypted P2P solution lets PC, mobile, and web clients access local DSH, Codex, Cursor, and Claude Code workspaces.)

We unified the interfaces of instruction-tuning data (e.g., CoT data), multiple LLMs and parameter-efficient methods (e.g., lora, p-tuning) together for easy use. We welcome open-source enthusiasts to initiate any meaningful PR on this repo and integrate as many LLM related technologies as possible. 我们打造了方便研究人员上手和使用大模型等微调平台，我们欢迎开源爱好者发起任何有意义的pr！

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Ephemeral Workspaces, durable shared history. LayerFS gives every agent a complete, writable filesystem Workspace over shared committed history, without copying the base. Agents work in parallel, commit what changed as deduplicated checkpoints, then branch, rewind or merge. Try it with LayerFS × DSH.

A production-ready FastAPI template for building AI agent applications with LangGraph integration. This template provides a robust foundation for building scalable, secure, and maintainable AI agent services.

Control Any Computer Using LLMs.

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

dLLM: Simple Diffusion Language Modeling

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

🥨 Lobe Icons - Brings AI/LLM brand logos to your React & React Native apps — static SVG/PNG/WebP, no dependencies.

EVA Series: Visual Representation Fantasies from BAAI

Project Page for "LISA: Reasoning Segmentation via Large Language Model"

Code and documents of LongLoRA and LongAlpaca (ICLR 2024 Oral)

This codebase is for a React and Electron-based app that executes the FreedomGPT LLM locally (offline and private) on Mac and Windows using a chat-based interface

Database system for AI-powered apps

Research papers and blogs to transition to AI Engineering

[EMNLP-2024] Build multimodal language agents for fast prototype and production

Build, run and scale AI agents like API and microservices

Awesome papers about unifying LLMs and KGs

Pagekin，免费 AI 小说写作软件，从设定、蓝图到正文、审稿、定稿；支持拆解仿写、续写、改写，可导入写作 Skill（如去 AI 味）。模型需自行配置，作品在本地。Pagekin (formerly AI Novel Writer): free, open-source AI novel writing app for long novels and web fiction. Imitate, continue, rewrite; import writing skills. Local-first, no model bundled. Windows & macOS.

Apple MLX native implementations of state-of-the-art generative image & video models

MiniMax-M2, a model built for Max coding & agentic workflows.

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

能安全适用于氛围编程和企业应用的全栈自进化通用智能体

Translate full-length books and documents with Ollama, OpenAI-compatible, Gemini, Mistral, DeepSeek, Poe or OpenRouter. Preserves formatting. Resumes where you left off. No file size limits.

Awesome Reasoning LLM Tutorial/Survey/Guide

A curated list of public projects, integrations, and discussions built on Jev — TypeSafe AI's System One model for typed decisions.