Havuz

Find the cheapest API for any model and connect it from your AI agent: Grandet Skill and an anonymous MCP server, backed by listed prices fr

AI coding agent that makes a team of small models beat a frontier one

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

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 clea

Context management proxy for AI coding agents: verbatim archive, on-demand recall, and saved engine state on supported backends.

An autonomous, always-on agent on your Android phone. It has its own browser, keeps a wiki memory of you, and hands the heavy jobs to your o

Cited Q&A over IIIT Delhi academic rules — answers only from official PDFs, with page links. RAG + FastAPI + Gemini.

Blinded battles between coding agents: two agents, one prompt, you pick the winner. Desktop app, runs locally.

Your coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.

Claude skill + plugin that picks the right model and effort for every task: Opus plans, Haiku/Sonnet build, every step is verified, and it e

Open-source desktop AI trading assistant for market research: chat beside live charts, price alerts, local backtests, bring your own model.

Local personal-data firewall for cloud LLMs. Scrubs names, emails, IDs and secrets before they leave your machine.

Self-hosted LLM gateway: vendor keys, rule-based routing, fallbacks, throttling and usage reporting over gRPC

Run Claude Code, Codex and other coding agents in a local VM on a clone of your project, then review their changes like a pull request. Mac

Control and observe a running Minecraft: Java Edition game from AI agents over MCP (Fabric and NeoForge, 1.21.1+)

Local-first desktop app for AI agent teams. Runs with Ollama or cloud models. Mac + Windows.

An assistant for Windows that works inside 118 desktop programs and services through code instead of screenshots. It writes each program's o

AnyFlow - flow-matching video generation: training, inference and VBench evaluation for t2v and i2v models.

PaperFold, arXiv makalelerini metin, özet ve konu haritası düzeyleri arasında yakınlaştırarak okumayı sağlayan bir araştırma makalesi okuyucusudur.

Neden yükseliyor · Bir günlük yaşında 61 yıldıza ulaşması dikkat çekiyor; ancak son 28 gündeki 6 commit ve tek farklı yazar, ilginin henüz bağımsız katkı veya sürdürülebilir aktiviteyle desteklendiğini göstermiyor. Yükselişin kesin nedeni mevcut verilerden bilinmiyor.

Local inference for diffusion language models (LLaDA, Dream), written in Mojo

Codex 风格的推理等级滑条（DeepSeek Harness 插件）：可拖动连续滑条 + 高档位渐变星尘特效

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

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

dsh-sieve: context engineering & token optimization plugin for DeepSeek Harness (DSH) — tool output filtering, context pruning, progressive

Fast Rust launcher for DeepSeek Harness, with clear Claude Code/Codex migration, model setup and lightweight local tools

Your agent, on your phone. A native Android app for Hermes Agent, running entirely on-device (Termux).

简明技术中文 / Simplified Technical Chinese: a controlled language for Chinese technical writing, modelled on ASD-STE100. 40 rules, a one-meaning-

AI-assisted text editor for Windows with local LLM support, text rewriting, style improvement and Unicode cleanup.

Open source Agentic Development Environment

Give the agent "this" and he gets a real PC.

On-device AI agent for Android, tuned for free OpenRouter/Kilo models with automatic model/key fallback and rate-limit recovery. Tools: web

Mingli AI｜真一 ZHENYI，全球首个开源 AI 算命命理大模型。以盲派做功技法为核心，融合旺衰、子平、调候；程序自动排盘，模型负责推演。权重与源码开放，支持在线体验与独立部署。

Strata 0.2.3 (engine 0.1.48) for AMD gfx906 (MI50/MI60/Radeon VII): rocBLAS solution table, Qwen3.6/Ornith engine restored, DFlash2 build fi

tsov (the shape of voice) — hum it, get a song you can keep editing. A local-first, AI-native music workspace: humming → transcription → arr

The harness that builds harnesses: tell it about your work and it builds a custom AI agent with its own tools, views, skills and UI. Runs in

TalkTact · 微信聊天助手（LSPosed 模块）：聊天页悬浮候选回复卡片（★最推荐+理由、单条改写），多套提示词 skill，角色关系档案；直通/模型分级双模式，本地代理让 API Key 不出 App 进程，会话白名单，以及本机离线的图片文字识别（OCR）。只填输入框

Two-rank tensor-parallel LLM serving over USB4v2 between AMD Strix Halo hosts: a custom Linux thunderbolt stream transport, self-healing lin

Smriti (स्मृति): private, local-first agentic RAG with System 1 + System 2 thinking over your notes, books and documents. Guardrails, tracin

DeepSeek Harness masaüstü uygulamasını Linux için AppImage, .deb ve .tar.gz paketleriyle dağıtan bir downstream fork.

Neden yükseliyor · Linux için kurulum ve güncelleme paketleri sunmayan DeepSeek Harness'a yönelik görünür bir dağıtım boşluğunu hedefliyor. 4 günlük yaşına karşılık 116 yıldız ilgi gösteriyor; ancak 4169 commit ve 6 farklı yazar verisi bu fork'un kendi geliştirme etkinliğini tek başına kanıtlamıyor, upstream geçmişi veya ölçüm kapsamı etkili olabilir.

A self-hosted job search and resume builder app that writes tailored resumes and cover letters from your profile.

Global edition of ARTEX — an LLM multi-agent autonomous penetration-testing framework. English default, switchable to Korean/Chinese/Spanish

UI for AI agents. React components for what agents do – agent trees, tool calls, traces, handoffs and approvals – and for the rest of your a

AI novel generation with world building, interactive choices, and persistent character state. Next.js + Go. AI 小说创作台。

The Agentic-Native Operating System

🐚 The AI assistant that just works. One self-hosted app for every model you already pay for: Claude Code, Codex, Copilot, Gemini, Ollama and

Use DeepSeek, GLM, Kimi, OpenRouter and more in Codex CLI and Claude Code: one local endpoint, API translation, failover. Single Rust binary

An iPad IDE with local LLM inference on an AMD GPU over Thunderbolt: the upstream Linux amdgpu driver embedded as DriverKit, LemonSeed Engin

The fastest inference engine for Qwen3.8-27B on the NVIDIA RTX 5090: up to 500 tokens/s for one agent and up to 2,000 tokens/s for many, con

WHIRL (Windows HIP Inference for RDNA LLMs): native Windows C++/HIP LLM inference engine for the AMD Ryzen AI Max+ 395 (Radeon 8060S) and Ra

GamePause for Local AI: a Windows tray app that pauses LM Studio, Ollama and other local AI servers while you game, and restores them afterw