New
LLM & Inference
Models, serving stacks, quantisation and fine-tuning.
Trending
New
Most starred
131 repositories ·
topics: llm, large-language-models, llm-inference, llm-serving, fine-tuning
-
101A design system for AI applications. Material, physical, tactile, technical.+1.0/wkmeasured★ 2k25
-
102DeepSeek-V4.1-Flash-1017 EXL3 2.9bpw on 2x NVIDIA DGX Spark (GB10) with TensorFold: 2.1-2.3x the vLLM kit's decode speed.+5.0/wkmeasured★ 7625
-
103Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion image/video, TTS and music, plus an MCP server so Claude Code, Codex and Cline can drive your browser. Windows, macOS, Linux.+4.0/wkmeasured★ 13225
-
104👋 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+1.0/daymeasured★ 31225
-
105精酿 BrewReel:让 DeepSeek 这类便宜模型也能做出好看的竖版宣传片。写一份产品简报,AI 挑镜头、写文案,一条命令出片。3 种配方、6 个行业、广告法校验,开源可商用。+5.0/wkmeasured★ 18024
-
106The AI chat app that sweats the details. Every top model, real memory, living documents, and your own tools.+2.0/wkmeasured★ 51224
-
107clodfarm (say it out loud): a farm of Claude Code agents. Plant a mission, they split it into sub-agents, open the work, and pace themselves on each account's real 5-hour and weekly usage. Steer it from the Claude app.+3.0/wkmeasured★ 21724
-
108Sno Station Skills: 31 tested skills that turn Claude Code and Codex into one working team. Cross-vendor peer review, automatic handoff when an agent hits its quota, a one-page morning brief, work orders with proof, and a nightly loop that learns from your own sessions. Open source, installed with one sno setup.−3.3/daymeasured★ 86123
-
109TOMC Memory: CPU context compression and task memory for Codex, Claude Code, Cursor, TRAE, WorkBuddy and other MCP clients.+1.0/wkmeasured★ 26723
-
110CodeAgent is an open-source coding agent that lives in your terminal. It understands your repository, plans multi-step changes, writes and edits files, runs commands and tests, and iterates until the task is done — all with a transparent, extensible tool loop.+1.0/wkmeasured★ 1k23
-
111MCP desktop companion for AI agent status, usage tracking, and everyday tools. Anything Universe · 桌面伙伴与日常工具入口。+1.0/wkmeasured★ 31323
-
112A 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.+2.0/wkmeasured★ 26223
-
113Component layer for AI agents: implementation-aware contracts for building project-native interface components.+1.0/wkmeasured★ 19223
-
114ARTEX · AI autonomous penetration testing system (multi-agent LLM, Go + Next.js) · AI 自主渗透测试系统 · 百度 agent+ 攻防挑战赛冠军−123/daymeasured★ 1.3k23
-
115Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.−5.7/daymeasured★ 50723
-
116AI assistant and MCP server for Blender: visual chat, scene tools, multi-agent workflows. Works with OpenAI, ChatGPT, Claude, Gemini, Ollama, OpenCode. Blender AI addon and plugin, copilot for 3D, bpy Python scripting, MCP integration.—stale★ 97622
-
117麦麦省钱助手 —— 基于麦当劳 MCP 的点餐成本优化 Skill。算出当前门店最省钱的点餐方案,并主动提示凑单陷阱。−1.0/wkmeasured★ 99222
-
118🌃 Capri — Edgerunners-inspired AI agent for your desktop. Works with Claude Code, Codex, Antigravity & more.—stale★ 38622
-
119🍟 麦当劳中国官方 MCP 智能助手技能:把 35 个原子工具编排成 4 条业务流 —— 活动推送 · 联名关注 · 最优惠点餐 · 多人群点聚合账单。算价用 calculate-price 真算,下单必二次确认。|McDonald's China MCP agent skill: campaigns, collab watch, best-value ordering, group bill splitting.−2.0/wkmeasured★ 37922
-
120构屎 GOUJI — 纯 C++/CUDA 的三值 mini LLM。2 bit/权重,零 Python;联想记忆工具路由,零训练参数;143 个缺陷与 29 个变异测试记录在案。+2.0/wkmeasured★ 9721
-
121Unofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.+2.0/wkmeasured★ 15021
-
122AI novel generation with world building, interactive choices, and persistent character state. Next.js + Go. AI 小说创作台。+1.0/wkmeasured★ 23620
-
123Self-hosted decision model (selfjev-4b) with a Jev-compatible API: Python SDK, server, fine-tuning and RLCD.+1.0/wkmeasured★ 6020
-
124STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantizationflatmeasured★ 10120
-
125A Markdown convention and linter for project docs written by AI and read by humans and agents−1.0/wkmeasured★ 19420
-
126Blender add-on: create and edit 3D models by chatting with AI - send text or an image, get working bpy code—stale★ 21820
-
127Switchless RoCE collectives, NCCL profiles and fabric tooling for DGX Spark inference recipesflatmeasured★ 4119
-
128辞达:用你选择的大模型,在 Mac 的任何地方翻译和润色文字。Translate and polish text anywhere on your Mac.—stale★ 17319
-
129Research and writing can be automated. Authorship cannot. Evidence list + agent skills for spotting AI-produced papers no human stood behind.flatmeasured★ 14619
-
130A local app that rents a GPU in your own Colab account and serves Qwen3.8 on it: 27B on an A100-40G, or Flash-Next (125B-A6B MoE) on an A100-80G. The cost is shown before it starts; chat with images; Codex or any OpenAI client uses a fixed local /v1. Auto-stop, CU ledger, live prefill/decode. Windows, macOS, Linux.flatmeasured★ 10319
-
131Watches company job boards, scores openings against your resume, and emails you when something worth applying to shows up.—stale★ 19319
← previous
page 3 of 3