Havuz
Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.
Yalnız hareketli, son 28 günde commit almamış repoları gizler (yıldızı olan ama bırakılmış projeler). Commit sayısı henüz ölçülmemiş repolar da gizlenir.
EtiketTüm GitHub etiketleri — repo sahiplerinin koyduğu topic'lergöster
Etiketler yükleniyor…
- 1
ChatGPT-style generative UI for Open WebUI: photo galleries, live maps with real routes, multi-day trips, budgets, calculators, live weather
19,7/gün ort. +3 son gün 18 commit 3 yazar Python 01 Kas 2026 güncellendi 2 gün önce - 2
♟️ llama-modchip v2.1: Run 30B Sparse MoE LLMs on Pure CPU (0 GPUs) at 20–60.4 tok/s with a 256K Context Window via a 1.64MB Stockfish-PVS +
12/gün ort. +1 son gün 29 commit 1 yazar Python 29 Eki 2026 güncellendi dün - 3
Native macOS workspace for Apple's container runtime. Browse, run, build and clean up Linux containers with live resource gauges, a built-in
6,3/gün ort. +0 son gün 20 commit 1 yazar Swift 29 Eki 2026 güncellendi dün - 4
Tying up what The Sims 4 leaves dangling
3,7/gün ort. +0 son gün 2 commit 1 yazar HTML 28 Eki 2026 güncellendi 8 gün önce - 5
A domain-specific medical Retrieval-Augmented Generation (RAG) system that answers health-related questions strictly based on retrieved evid
3,6/gün ort. +0 son gün 2 commit 1 yazar HTML 28 Eki 2026 güncellendi 8 gün önce - 6
The free, open source Cursor alternative. An AI code editor that runs on your own API key, your Claude Code or Codex plan, local models, or
4/gün ort. +4 son gün 95 commit 1 yazar TypeScript 27 Eki 2026 güncellendi 6 gün önce - 7
A dependency-free C inference engine for Liquid AI's LFM2 / LFM2.5 models. Terminal chat, an OpenAI-compatible server, a web agent and a ter
2,5/gün ort. +2 son gün — commit C 27 Eki 2026 güncellendi 2 gün önce - 8
Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.
2,3/gün ort. +0 son gün — commit Metal 25 Eki 2026 güncellendi 7 gün önce - 9
A 6.87 GiB GGUF build of Qwen 3.8 27B — full 27B quality on 8 GB RAM. 96.7% HumanEval, 92.9% MMLU retention, no distillation.
1,8/gün ort. +2 son gün — commit HTML 25 Eki 2026 güncellendi 8 gün önce - 10
A privacy-first local coding agent that consults frontier AI models without exposing your source code.
7,3/gün ort. +7 son gün 2 commit 1 yazar TypeScript 24 Eki 2026 güncellendi 8 gün önce - 11
This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind
4,6/gün ort. +0 son gün 49 commit 2 yazar Python 24 Eki 2026 güncellendi 5 gün önce - 12
Measures which GGUF quant of a model to run on your GPU: real speed and quality loss (KL divergence), not estimates.
1,3/gün ort. +0 son gün — commit Rust 23 Eki 2026 güncellendi 8 gün önce - 13
Private, offline AI assistant for Android and Windows: run local LLMs (Gemma 4, Qwen, any GGUF) on your phone or PC with llama.cpp, CUDA and
1/gün ort. — commit Dart 22 Eki 2026 güncellendi dün - 14
A Visual Basic 6 clone for macOS, Windows and Linux: Windows 98 look, form designer, VB6 language, 59 classic controls, VB6 project import,
1/gün ort. — commit TypeScript 22 Eki 2026 güncellendi 3 gün önce - 15
Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built
8/gün ort. +9 son gün 122 commit 3 yazar C 21 Eki 2026 güncellendi dün - 16
PROMETHEVS: run the full DeepSeek-V4.1-Flash-1017 (510 GB) on a gaming PC with 64 GB RAM and a 12 GB GPU. PROMETHEVS engine (compress-then-c
7,1/gün ort. +14 son gün 12 commit 1 yazar 21 Eki 2026 güncellendi 13 gün önce - 17
Run stock llama.cpp with the stock Unsloth Qwen3.6-35B-A3B 4-bit on a 16 GB Mac.
0,9/gün ort. +0 son gün — commit Shell 20 Eki 2026 güncellendi 10 gün önce - 18
A local AI agent built from scratch in Python with Ollama: conversation memory, system prompts, and multi-step tool calling.
2,4/gün ort. +0 son gün — commit Python 19 Eki 2026 güncellendi 4 gün önce - 19
Fine-tune Qwen2.5-Coder-7B for free (QLoRA on Kaggle T4) and run a local coding agent that runs your code instead of guessing — 8 GB Mac, ll
1,3/gün ort. +0 son gün — commit Python 19 Eki 2026 güncellendi 15 gün önce - 20
Knowledge graph and context manager for AI coding agents: Claude Code, Codex, Gemini CLI, Cursor, Copilot and local models. Code map with Pa
0,7/gün ort. +0 son gün — commit JavaScript 17 Eki 2026 güncellendi 14 gün önce - 21
A decision library for running local LLMs on multi-GPU machines without NVLink: parallelism, communication, quantization, speculative decodi
1,5/gün ort. +10 son gün — commit Python 16 Eki 2026 güncellendi dün - 22
Make your own private AI bot on your own computer. Say what bot you want; BuildBot finds apps, books and live info, shows one plan, and buil
0,7/gün ort. — commit Python 16 Eki 2026 güncellendi 12 gün önce - 23
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
22,4/gün ort. +5 son gün 208 commit 3 yazar TypeScript 14 Eki 2026 güncellendi 6 gün önce - 24
Qwen3.8-Flash-Next (180B MoE) on one 12-16 GB NVIDIA GPU, Linux or Windows. Own engine, own compression.
1,6/gün ort. +0 son gün — commit Python 14 Eki 2026 güncellendi 15 gün önce - 25
Instant context compaction for Hermes Agent. Builds the compaction summary in milliseconds with no LLM call, keeping the exact commands, exi
1/gün ort. +0 son gün — commit Python 14 Eki 2026 güncellendi 10 gün önce - 26
Native AI assistant for macOS, built with SwiftUI and llama.cpp. Run local LLMs offline, work with PDFs, and create custom AI assistants. Op
1,5/gün ort. +0 son gün — commit Swift 13 Eki 2026 güncellendi 23 gün önce - 27
YouTube 直播实时 AI 翻译字幕，支持本地 Ollama，英中双向。首次配置，日常双击启动。AI captions for YouTube livestreams with local Ollama. English ↔ Chinese. Windows/NVIDIA p
1,5/gün ort. +0 son gün — commit Python 12 Eki 2026 güncellendi 23 gün önce - 28
Open-source, Local-first AI (SI) Second Brain.
0,6/gün ort. — commit Python 11 Eki 2026 güncellendi 9 gün önce - 29
Pure-Rust MoE inference engine for Qwen3.5/3.6 GGUF. CPU+GPU hybrid experts, NVRTC CUDA kernels, OpenAI-compatible server. 2x llama.cpp pref
0,6/gün ort. +2 son gün — commit Rust 10 Eki 2026 güncellendi 2 gün önce - 30
Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion ima
5/gün ort. +1 son gün 15 commit 1 yazar JavaScript 09 Eki 2026 güncellendi 3 gün önce - 31
Turn one machine into a private ChatGPT for a whole room. One command sets up Ollama, Open WebUI, RAG and an OpenAI-compatible API sized to
2,2/gün ort. +0 son gün — commit TypeScript 08 Eki 2026 güncellendi 10 gün önce - 32
🔥 Run large open language models on your phone. A C++20 GGUF inference engine that streams models larger than RAM from flash, paces itself b
0,5/gün ort. +1 son gün — commit C++ 07 Eki 2026 güncellendi 4 gün önce - 33
Project Maya - run GLM-5.3-Flash (321B MoE), DeepSeek-V4.1-Flash-1017 (748B MoE) and MiniMax-M3.1-Flash (428B MoE) privately on your own GPU
85,7/gün ort. +37 son gün 978 commit 21 yazar Cuda 06 Eki 2026 güncellendi dün - 34
Offline AI research assistant for Android. Answers from Wikipedia and other reference packs on the phone, with citations. Gemma 4 runs on th
1,1/gün ort. +2 son gün — commit Rust 06 Eki 2026 güncellendi 12 gün önce - 35
Context management proxy for AI coding agents: verbatim archive, on-demand recall, and saved engine state on supported backends.
1,7/gün ort. +2 son gün — commit Python 05 Eki 2026 güncellendi 2 gün önce - 36
Local-first desktop app for AI agent teams. Runs with Ollama or cloud models. Mac + Windows.
0,5/gün ort. +1 son gün — commit TypeScript 05 Eki 2026 güncellendi dün - 37
Open source Agentic Development Environment
3/gün ort. +3 son gün — commit TypeScript 04 Eki 2026 güncellendi dün - 38
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.
5,4/gün ort. +2 son gün 950 commit 13 yazar TypeScript 03 Eki 2026 güncellendi dün - 39
A self-hosted job search app that writes tailored resumes and cover letters from your profile.
132,1/gün ort. +98 son gün 25 commit 2 yazar TypeScript 03 Eki 2026 güncellendi 4 gün önce - 40
An iPad IDE with local LLM inference on an AMD GPU over Thunderbolt: the upstream Linux amdgpu driver embedded as DriverKit, LemonSeed Engin
1,9/gün ort. +0 son gün — commit C 03 Eki 2026 güncellendi 27 gün önce - 41
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
1,6/gün ort. +0 son gün — commit 03 Eki 2026 güncellendi dün - 42
Desktop app for game dev with AI: make games in Unreal Engine, Unity, Godot or the browser. The agent sets up the engine, builds your game a
24/gün ort. 1.928 commit 4 yazar TypeScript 02 Eki 2026 güncellendi dün - 43
Local decision model with calibrated probabilities: send a state and yes/no, choice or score questions, get a probability for every option.
2,4/gün ort. +2 son gün — commit HTML 01 Eki 2026 güncellendi 05 Eki 2026 - 44
Started as a €70 used mini PC running an always-on AI agent (Hermes, n8n, Pi-hole, monitoring, Tailscale, encrypted backups). Now with a sec
0,8/gün ort. +1 son gün — commit Shell 01 Eki 2026 güncellendi 5 gün önce - 45
A living AI civilisation you can watch: tiny creatures discover, build, teach and pass knowledge on, with any LLM in their minds.
0,7/gün ort. +0 son gün — commit Python 01 Eki 2026 güncellendi 19 gün önce - 46
An AI workforce on your desktop. Describe the work; a team of AI agents does it in the open and hands it back checked. Any model, any harnes
1,2/gün ort. +1 son gün — commit JavaScript 30 Eyl 2026 güncellendi 14 gün önce - 47
Local AI chat and personal agents for macOS. Ollama-powered conversations, customizable characters, controllable memory, and a browser-based
0,5/gün ort. +0 son gün — commit TypeScript 30 Eyl 2026 güncellendi 30 Eyl 2026 - 48
Run Qwen3.8-Flash-Next on ONE RTX 3090 (24 GB) + 64 GB RAM: 128K context, up to 2,100 tok/s prefill, 43–51 tok/s decode. vLLM runtime with h
0,4/gün ort. +0 son gün — commit Python 30 Eyl 2026 güncellendi 30 Eyl 2026 - 49
A local-first language-learning app for the desktop. Lessons, stories and conversation practice are generated by an AI model running on your
0,4/gün ort. — commit TypeScript 29 Eyl 2026 güncellendi 2 gün önce - 50
Mission control for AI coding agents. Watch Claude Code, Codex, Gemini and a dozen more work live in one macOS terminal: live status, an edi
3,6/gün ort. +2 son gün 703 commit 5 yazar Zig 27 Eyl 2026 güncellendi dün