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
Stop paying the multimodal tax. Your AI agent keeps every image it has seen but only sends the ones it needs: lighter chats, no endless reco
18,5/gün ort. +7 son gün 222 commit 3 yazar TypeScript 24 Eyl 2026 güncellendi 2 gün önce - 2
🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forw
5,9/gün ort. +4 son gün 57 commit 2 yazar Python 27 Eyl 2026 güncellendi dün - 3
Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /rend
3,7/gün ort. +2 son gün 3 commit 1 yazar Python 19 May 2026 güncellendi 6 gün önce - 4
Black-box LLM distillation for any verifiable task, with text or image inputs: teacher API -> rejection sampling -> SFT -> eval -> GRPO
2,9/gün ort. +0 son gün — commit Python 28 Eki 2026 güncellendi dün - 5
NEWTON: Agentic Planning for Physically Grounded Video Generation
1/gün ort. +0 son gün 0 commit 0 yazar Python 13 Haz 2026 güncellendi 31 Tem 2026 - 6
DeepSeek-V4.1-Flash-1017 on one 256 GB M5 Ultra: 1M context, 70.7-104.9 tok/s decode with DSpark drafts, 1,739-1,867 tok/s cold prompts (8k-
0,8/gün ort. +0 son gün — commit Python 19 Eki 2026 güncellendi 13 gün önce - 7
Finds a stolen bike on second-hand marketplaces by ranking photos, not keywords — a CLIP pre-gate in front of a vision-LLM recognition pass.
0,8/gün ort. +0 son gün — commit Python 15 Eki 2026 güncellendi 20 gün önce - 8
基于多模态视觉感知与 LLM Agent 的 macOS 微信自动化框架 | Visual RPA for WeChat
0,7/gün ort. +1 son gün — commit Python 02 May 2026 güncellendi bugün - 9
A token-efficient, provider-agnostic vision layer for reasoning models via MCP.
0,5/gün ort. +0 son gün — commit TypeScript 12 Ağu 2026 güncellendi 18 Eyl 2026 - 10
An agent skill that reads a photo the way Sherlock Holmes reads a stranger (福尔摩斯): observe first, deduce second, every conclusion cites its
0,4/gün ort. +0 son gün — commit TypeScript 19 Eyl 2026 güncellendi 19 Eyl 2026 - 11
Can my GPU run this? Pick a GPU to get 3 fitting AI models, quantization, VRAM, speed ranges, and run commands. 한국어·English.
0,4/gün ort. +0 son gün — commit JavaScript 20 Tem 2026 güncellendi 3 gün önce - 12
Save UI inspiration from any app; a vision model curates it into a private wiki and turns your taste into a DESIGN.md your coding agent buil
0,3/gün ort. +0 son gün — commit Python 14 Eyl 2026 güncellendi dün - 13
browser-use, but for the entire desktop — give any AI Agent eyes and hands on Windows. MCP + SDK, VLM-optional, with visual loop, introspect
0,2/gün ort. +0 son gün — commit Python 24 Ağu 2026 güncellendi 8 gün önce - 14
A long-horizon CRPG benchmark for frontier agents. Raw 320x200 frames, Traditional Chinese, isometric navigation, twelve books to find.
0,2/gün ort. +0 son gün — commit Python 24 Ağu 2026 güncellendi dün - 15
Open-source video compiler that turns videos into structured knowledge for AI agents.
0,1/gün ort. +0 son gün — commit Python 07 Tem 2026 güncellendi 23 Tem 2026 - 16
Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings
0,1/gün ort. +0 son gün — commit Rust 06 Haz 2026 güncellendi bugün - 17
Gemma 4 31B Abliterated — quality-preserving guardrail removal for Google's most capable open model. Apache 2.0. Runs on Apple Silicon via M
0,1/gün ort. +0 son gün — commit Python 03 Nis 2026 güncellendi 4 gün önce