OSS Today

Showing 30 of 4,859 · Category: LLM

61
blendbunjaku/optimaizr

Spend fewer tokens on the same work. A local CLI that finds wasted tokens in Claude Code, Codex, opencode and your own API calls.

TypeScript★ 1666.2/day
62
sepehr071/iran-mcp

39 MCP servers (488 tools) that give AI agents the Iranian web: Digikala, Torob, Divar, Snappfood, Jabama, MrBilit, Paziresh24, Taaghche, laws, tax, crypto, stocks, news and more. Prices in Toman.

Python★ 15810.1/day
63
zephyr4123/speakmore

SpeakMore:口述成文,划词即译。开源、免费的语音输入与翻译工具,支持 Mac 与 Windows:语音输入、语音翻译、划词翻译。兼容 Gemini、OpenAI、通义千问、DeepSeek、Kimi、智谱 GLM、MiniMax 及任意 OpenAI 兼容服务,语音输入亦可完全在本机运行。附 Typeless 逆向分析。

JavaScript★ 15611.5/day
64
Zhou-Yujing114514/deepseek-harness-linux

First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI.

TypeScript★ 1546.4/day
65
StartLuxLabs/DecisionPivot

DecisionPivot: a diagnostic benchmark for decision models in LLM systems. Contrast pairs that differ in one decisive detail, generators with independent solvers, scorer and runners.

Python★ 15012/day
66
polaris-smart/mcd-agent-gourmet

麦当劳点餐 Skill:说一句「35 元、不辣、去冰」→ 一个答案 + 一张可复制的点单卡,金额只认官方 calculate-price 当次核价(同店同时刻 单品直选 ¥48.50 vs 三件套 ¥36.50,省 ¥12.00/24.7%)。不领券、不下单、不收集 Token;零依赖 Python,免登录网页打开就是答案。

Python★ 15010.3/day
67
justxor/deepseek-local-guide-ru

🐋 Полный гайд на русском: как установить и запустить DeepSeek локально (V4, R1) на ПК, Mac и сервере — Ollama, llama.cpp, LM Studio, vLLM, Open WebUI, API, RAG, агенты, fine-tuning, лучшие фишки

Shell★ 15015.4/day
68
heterodoxin/AbliteratedOutTheBox

llama.cpp fork that abliterates at inference

C++★ 14928.4/day
69
FrigadeHQ/hob

An easier way to use AI on your own computer. A free, open-source alternative to Claude and ChatGPT that runs open-weight models like Gemma and gpt-oss locally on Mac, Windows and Linux. Private, and works offline.

TypeScript★ 14812.1/day
70
THUROI0787/absent-author

Research and writing can be automated. Authorship cannot. Evidence list + agent skills for spotting AI-produced papers no human stood behind.

Python★ 1466.7/day
71
alibaba/qz-browser-agent

Local-first AI agent for Chrome: browser automation, web research, and data extraction with your own model.

HTML★ 1469.7/day
72
ghorbelhamdi/buddy-android

Android AI assistant in a floating bubble: Claude Code, Codex, OpenCode, Gemini (Antigravity CLI) or Grok use your phone for you — read the screen, tap, type. Runs on your own plan, open source, no root, no adb, no PC.

Java★ 1346.8/day
73
janetom645-coder/mcd-buddy

麦门四重奏 McQuartet · 一个 Skill 装四个玩法:修行录 / 团餐指挥官 / 隐藏菜单实验室 / 每日运势签。基于麦当劳中国官方 MCP,187 个测试全绿,离线演示可一键复现。

Python★ 1348.1/day
74
lmliheng/Adelie

A local-first multi-agent app development platform, built on PenguinHarness

TypeScript★ 1345.9/day
75
paraboy-s/mcd-meal-pairing

麦当劳配餐决策 Skill|1881 种搭配里算出三档最优解,并告诉你为什么不是另外那些。控卡、忌口、拼单 max-min 公平分配;LLM 不参与算钱,每个数字可追溯。

Python★ 12713.2/day
76
dreamscroll-lab/asamana

Asamana is an AI-driven emergent narrative engine.

Python★ 1235.9/day
77
smallchristy123/mcmeal-compass

基于麦当劳中国官方 MCP 的营养搭配工具:套餐逐件展开求官方营养、官方计价并标出每个金额的价源、取不到就如实标"未知"而不填 0。离线可跑,无需 Token。不提供下单能力。

TypeScript★ 1227.2/day
78
TimeLovercc/mojito

Mojito — the local, evolving alternative to cloud personal AI like Meta Muse.

TypeScript★ 1204.3/day
79
YuyaoGe/doc2harness

Official Code for the paper "Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents "

Python★ 1157.3/day
80
ChangWenC/understanding-ladder

Karpathy's understanding ladder as agent skills: auto-pick text, diagram, interactive HTML, or video storyboard for any explanation. Nothing cut. English + 中文.

★ 1155.2/day
81
deeplethe/fde-gym

The online judge for the LLM era. Every case is a real customer delivery: you work it with a coding agent, and your system is judged once it is live.

TypeScript★ 1115.3/day
82
georgevibing/conch-agent

🐚 The AI assistant that just works. One self-hosted app for every model you already pay for: Claude Code, Codex, Copilot, Gemini, Ollama and more. Chat from your desktop, phone or Telegram.

TypeScript★ 1094.6/day
83
liyupi/dafeiyu-cleaner

DeepSeek 蓝色大肥鱼消除计划:识别并清理 B 站(Bilibili)评论区中由 DeepSeek 大模型、AI Agent 驱动的机器人账号(大肥鱼)的 Chrome / Edge / Firefox 浏览器插件。离线规则 + DeepSeek API 精判,AI 评论检测、空间主页鉴定、鲸鱼娘一键清场。DeepSeek AI bot detector for Bilibili comments.

JavaScript★ 10827/day
84
Sev7eEn7/dsh-sieve

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive skill disclosure. 36% smaller payload in offline replay. DSH 上下文管理与 token 优化节省插件。

TypeScript★ 1054.6/day
85
Umair/stalemap

Tell your coding agent which dependencies changed after its training cutoff. Diffs types and changelogs, writes a short block into AGENTS.md / CLAUDE.md.

TypeScript★ 10314/day
86
daimonia-ai/STC-Simplified-Technical-Chinese

STC 简明技术性中文:给 AI 用的中文写作规范。输出更自然、简短,术语更一致,任务回执更清楚。支持 CLI、独立 Skill 和网页聊天。Simplified Technical Chinese: rules, a dictionary, and tools for clear, concise AI output.

JavaScript★ 1034.8/day
87
duyongan/dots-agent

一个会主动发现任务的智能体

Python★ 1038.7/day
88
rextail-ai/lessloc

Keeps AI coding agents such as Claude Code, Codex, GitHub Copilot, Gemini CLI and Cursor to the least code that does the job and still works.

JavaScript★ 10313.5/day
89
Lemon177777/mcd-omni-assistant

麦当劳 MCP 全能助手 | 全覆盖 35 个工具 · 7 大工作流 · 14 条防错铁律 | 领券 / 点餐 / 外送 / 派对预约 / 积分到期止损,附零依赖 CLI 通道

Python★ 1005.7/day
90
ShadowSafin/Synapass

AI inference gateway and control plane for multi-provider routing, policies, caching, tools, and observability.

Go★ 1003.8/day