LLM & Inference

MCP desktop companion for AI agent status, usage tracking, and everyday tools. Anything Universe · 桌面伙伴与日常工具入口。

👋 Hello Agent System — learn enterprise AI agent system design by building every production layer from scratch. 17 bilingual lessons (EN/中文) with tested exercises: tools, architectures, reliability, security, evals, distributed execution, cost, RAG, release ops. 企业级 Agent 系统设计训练营

记忆桥 MemoryBridge — 跨设备、跨平台的 AI 共享记忆层 | Cross-device and cross-platform shared memory for AI (CDSMP implementation)

Can AI engines cite your site, and do they? Free 0–100 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.

Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.

Method for Long Context RLMs using verifiable Lambda Calculus

:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers/LLM, with compute-matched benchmarking and a platform for autonomous architecture research.

The production framework for Predictive and Generative AI. Serve any model as an API in one line, with OpenAI/Anthropic/Ollama-compatible endpoints, a built-in chat UI, and native MCP.

Autumn-Recruit Algo Notes(秋招算法学习仓库)，面向大模型时代的算法、工程与AI学习共建仓库。从数学基础、数据结构，到机器学习、深度学习、LLM、Agent、AI-Infra、语音与数据科学，通过「理解→推导→手写 → 运行 → 验证 → 复盘构建可持续迭代的知识体系。

微信聊天分析工具，支持本地 Laya 与 API 模型，提供意图识别、情绪感知、人物画像、群聊画像、好感度分析和 MBTI 聊天推测。

SkillX: Automatically Constructing Skill Knowledge Bases for Agents

FireAct: Toward Language Agent Fine-tuning

A ChatGPT(GPT-3.5) & GPT-4 Workload Trace to Optimize LLM Serving Systems

Fast, exact inference for StartLux-Decision models on NVIDIA GPUs: the released GGUF files on int8 and 4-bit tensor cores, behind the /v1/systemone API, with up to 5.3× lower latency than vLLM in FP8 and bit-identical answers.

A curated list of battle-tested tools, frameworks, and best practices for building scalable, production-grade Retrieval-Augmented Generation (RAG) systems.

One CLI for all your robots. Connect them, command them, and let them work together, each with an LLM for a brain (Claude, OpenAI, Gemini, Grok, or local via Ollama or vLLM), VLAs for arms and decision LLMs (Jev, Laya, Kev). Drives Microduck, Open Duck Mini, LeRobot, XLeRobot, AlohaMini, ToddlerBot, or any ROS 2 base from a laptop, offboard.

Event-stream AI Agent framework for building your persona bot 🍊

Berth is a lightweight GPU resource manager written in Go. It controls which applications get access to your GPU, when they get it, and how that access is handed off.

Open desktop AI agent for Windows, macOS and Linux, written from scratch: its own agent engine, its own browser tooling and its own drawing engine that shows what it explains.

针对GPT 6.0,workbuddyV4.1flash的破甲实验项目

Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of papers on accelerating LLMs, currently focusing mainly on inference acceleration, and related works will be gradually added in the future. Welcome contributions!

OrcaReplay — Time travel for AI agents. Record, replay, fork, and debug any agent run with any model. Built by the OrcaRouter.ai team.

AI-powered vocabulary learning — a fine-tuned 1.5B model (SFT+DPO) that runs offline in your browser. Live: wordlink.lifeplayertribe.com

Zero-friction LLM fine-tuning skill for Claude Code, Gemini CLI & any ACP agent. Unsloth on NVIDIA · TRL+MPS/MLX on Apple Silicon. Automates env setup, LoRA training (SFT, DPO, GRPO, vision), post-hoc GRPO log diagnostics, evaluation, and export end-to-end. Part of the Gaslamp AI platform.

A minimal hardware-software architecture giving large language models a closed-loop physical embodiment with self-perception loops.

A hands-on course on modern LLM architectures, training, and inference, with step-by-step PyTorch implementations and runnable notebooks.

50x your usage with cheap-ag. Opus/Astra plans, a dirt-cheap model writes every line, and tests decide what ships. Your $20 plan stops hitting limits. One MCP server for Claude Code & Codex.

Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.

Your AI intranet: network the computers you already own for inference and training.

WikiSkill (arXiv:2608.27454) for Hermes Agent — self-evolving agent skills via a persistent knowledge wiki. Faithful Algorithm 1 implementation with real agent runs, isolated skill gating, and a documented live run log.

Posthorse: fresh context, same journey. No-summary context rollover for the Pi coding agent (official Pi 1.0+ or the fitchmultz/pi fork), with durable notes and history recovery.

[Public preview] Externally scored agentic ML research benchmark: 60 tasks, real competition ground truth. Open protocol, operated evaluation.

TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.

Open-source code for training and scaling up energy-based foundation models.

Interview questions and prep for AI Engineer, LLM Engineer, and Applied AI roles. Built for software engineers breaking into AI and ML practitioners levelling up: company-specific question sets, role-based study maps, worked answers, and from-scratch coding challenges.

Your personal EQ coach. Build social skills and learn to handle conflict through realistic role-play and personalized feedback.

AI 大模型世界，把 556 个大模型拟人化成像素小人的可视化站点。进来就能看到此刻谁最聪明、谁最会写代码、谁最便宜、谁刚发布，往下是国内与国外分区的厂商广场、完整的发布时间线和多维排行榜。搜索认模型名、厂商和能力，输入「多模态」会直接列出全部多模态模型。数据取自 Epoch AI、models.dev、LiveBench 与 Hugging Face，每小时自动同步，所有文案由真实数据生成，不调用任何 LLM。Next.js 静态导出，零后端。

CacheRoute is an innovative LLM scheduling scheme dedicated to enabling flexible KV cache reuse across LLM systems, improving task performance and system efficiency.

A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk.

Established strong JEV based natural language to SQL performance and well-covered semantic operators for PostgreSQL with optimized cost and latency. Reusable evidence, with native execution, parallel plans and explainable embeddings in development preview.

An agentic system that auto-optimizes LLM workloads on AMD GPUs.

把智能体当函数，把想法写成程序。Agent-native functional language with a CLI, Web IDE, goal-driven bots and live UI. Source-available; no AI training.

Shrinkflation detector for Codex

JetSpec++ && JetSpec: Causal Parallel (Tree) Drafting with Self Refinement

Turn your documents into a Markdown wiki you can read, that answers with citations. Works with any LLM provider, Ollama included. CROW classifier routing: 89% right note vs 62%, 2.1× faster ingest, 68% fewer tokens.

Jev-Mem: System-One Controlled Agentic Memory

new-api / sub2api 中转站账号管理中心：余额、API Key、用量、倍率、模型比价 | https://nvcenter.cc

Interactive desktop app with 58 labs covering ML fundamentals, transformers, RAG, agents, fine-tuning and quantization and more.

dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Acer), into a private AI server in one command: measured model lanes, OpenAI and Anthropic APIs, and a local cockpit.

A multi-agent research system for the humanities and social sciences.