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…
- 651
Your agent, on your phone. A native Android app for Hermes Agent, running entirely on-device (Termux).
2,9/gün ort. +1 son gün 667 commit 1 yazar TypeScript 04 Eki 2026 güncellendi 2 gün önce - 652
Deterministic code-graph context engine for AI coding agents - PostgreSQL + Apache AGE + pgvector, MCP & REST, no LLM in the loop.
2,9/gün ort. +0 son gün 20 commit 2 yazar Python 08 Eyl 2026 güncellendi 7 gün önce - 653
Boot your PC straight into an LLM. Rust, UEFI-resident, no operating system underneath.
2,9/gün ort. +0 son gün 0 commit 0 yazar Rust 27 Tem 2026 güncellendi 27 Tem 2026 - 654
Automatic LLM router — 82% cost savings, 79.4% accuracy, 93.4% pass rate. Drop-in OpenAI proxy.
2,9/gün ort. +0 son gün 0 commit 0 yazar Python 12 Mar 2026 güncellendi 26 Haz 2026 - 655
~97% token reduction for AI coding sessions — zero deps, 38 languages, MCP server
2,9/gün ort. +0 son gün 169 commit 2 yazar JavaScript 31 Mar 2026 güncellendi 2 gün önce - 656
341 种代码动画风格提示词 | 来源:来自俯仰观照博主的动画画风整理
2,9/gün ort. +4 son gün — commit HTML 29 Eki 2026 güncellendi 11 gün önce - 657
FineEnvs — RL Environments 101: building and scaling RL environments in the age of LLMs
2,9/gün ort. +2 son gün 27 commit 3 yazar Python 01 May 2026 güncellendi 4 gün önce - 658
Typed-decision models (noul / choice / score) trained by a self-improving loop of AI agents — checkpoints, the code that produced them, and
2,9/gün ort. +1 son gün 16 commit 2 yazar HTML 22 Eyl 2026 güncellendi 2 gün önce - 659
Turn your Android phone into an OpenAI-compatible LLM inference server - Fully local, private and Open Source
2,9/gün ort. +2 son gün 9 commit 1 yazar Kotlin 06 Nis 2026 güncellendi 2 gün önce - 660
The Agentic-Native Operating System
2,9/gün ort. +1 son gün 160 commit 1 yazar Rust 03 Eki 2026 güncellendi dün - 661
flashmind — Gemini 3.8 Flash Smart Agent. Gives Gemini Flash persistent memory (Engram), coding skills, and no-hallucination rules. Works in
2,9/gün ort. +0 son gün 16 commit 1 yazar JavaScript 25 Eki 2026 güncellendi 14 gün önce - 662
Menu bar app for macOS, Windows and Linux that cuts Claude Code and ChatGPT Codex token costs by ~50%
2,8/gün ort. +0 son gün 495 commit 2 yazar Rust 30 Mar 2026 güncellendi 2 gün önce - 663
Free, keyless coding models routed to every coding harness through one local endpoint
2,8/gün ort. +0 son gün — commit TypeScript 17 Ağu 2026 güncellendi 3 gün önce - 664
This 14 MB Agentic LLM(Cactus Needle 2) can control your phone completely.
2,8/gün ort. +1 son gün 6 commit 1 yazar Python 30 Ağu 2026 güncellendi 18 gün önce - 665
Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit
2,8/gün ort. +0 son gün 64 commit 4 yazar TypeScript 13 Ağu 2026 güncellendi 3 gün önce - 666
AI 自主渗透测试 · 红队作战平台 | 多 Agent 自主推进 · 漏洞情报运营 · 后渗透与 C2 | LLM 三通道轮询 | 全程证据留痕 | 原百度攻防赛冠军项目独立演进版
2,8/gün ort. +1 son gün 283 commit 1 yazar Go 09 Eki 2026 güncellendi 3 gün önce - 667
MCP server + library that lets LLM agents play Windows games in the background: per-process injected input and frame capture, no window focu
2,8/gün ort. — commit C++ 02 Kas 2026 güncellendi dün - 668
ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new archi
2,8/gün ort. +0 son gün 0 commit 0 yazar Python 13 Mar 2026 güncellendi 09 May 2026 - 669
Agent 式的 SillyTavern 角色卡酒馆:高缓存命中,兼容酒馆角色卡与世界书,自带配图和一键朗读,角色形象固定,引导式创作角色卡。An agent-style SillyTavern card player for your own LLM API.
2,8/gün ort. +1 son gün 68 commit 2 yazar JavaScript 17 Eki 2026 güncellendi dün - 670
Harness-Zero: Harness Distillation via Agent-as-Harness
2,8/gün ort. +1 son gün 2 commit 1 yazar Python 20 Eyl 2026 güncellendi 14 gün önce - 671
Hojo-ASR is a high-performance speech recognition model powered by the LLM decoder.
2,8/gün ort. +0 son gün 0 commit 0 yazar Python 25 May 2026 güncellendi 26 May 2026 - 672
Arkdraw is an open-source diagramming app for creating flowcharts, UML, ER diagrams, network maps, wireframes, and mind maps with a built-in
2,8/gün ort. +0 son gün 100 commit 5 yazar TypeScript 23 Eki 2026 güncellendi 2 gün önce - 673
Open-source agentic ops platform for cloud, SRE, DevOps, support and FinOps teams. AI agents investigate incidents, cut cloud and Kubernetes
2,8/gün ort. +0 son gün 1.163 commit 10 yazar Go 07 May 2026 güncellendi 2 gün önce - 674
Local-first macOS app that copies Discord trading signals into Alpaca accounts, with a risk-limited engine, an AI assistant, and English or
2,8/gün ort. +0 son gün 217 commit 2 yazar Python 02 Eki 2026 güncellendi dün - 675
Desktop app for the pi coding agent: streaming timeline, Git review with hunk staging, session tree, native UI for pi extensions. Windows ·
2,8/gün ort. +1 son gün 103 commit 4 yazar TypeScript 20 Haz 2026 güncellendi 2 gün önce - 676
Local decision engine with typed, calibrated outputs (Noul/Choice/Score): cheap→strong cascade, ECE/Brier calibration, SystemOne protocol in
2,8/gün ort. +0 son gün 125 commit 1 yazar Python 13 Eki 2026 güncellendi 11 gün önce - 677
Agent dashboard runs reliability scans, skills, and network access probes.
2,8/gün ort. +7 son gün — commit TypeScript 19 Eki 2026 güncellendi 5 gün önce - 678
Talk to your homelab. A self-hosted, open-source, AI-native homepage.
2,8/gün ort. — commit TypeScript 29 Eki 2026 güncellendi 2 gün önce - 679
Transform any idea into a running AI-powered company
2,8/gün ort. +0 son gün 0 commit 0 yazar TypeScript 21 Haz 2026 güncellendi 30 Haz 2026 - 680
Self-hosted AI agent OS. Your memory, chat, agents, and files stay on hardware you own, offline by default, cloud by choice. Offline AI memo
2,8/gün ort. +1 son gün 7 commit 1 yazar Python 05 Nis 2026 güncellendi dün - 681
Multi-LLM peer review for code decisions. Bring your own CLI; Chorus convenes 2-4 other LLMs to review the work before you ship.
2,8/gün ort. +0 son gün 0 commit 0 yazar TypeScript 30 Nis 2026 güncellendi 13 Ağu 2026 - 682
🛰 Every AI coding agent on your machine, on one screen — live cost, tokens and tool calls across every provider, and a hold on anything dang
2,8/gün ort. +0 son gün 419 commit 2 yazar TypeScript 05 Tem 2026 güncellendi dün - 683
CTX Fit finds the cheapest AI coding setup that reliably works on your repository, then applies the winner as a reviewable change.
2,8/gün ort. +0 son gün 0 commit 0 yazar Python 08 Nis 2026 güncellendi 26 gün önce - 684
Hermes Agent plugin: say 'make me a <role>' and your agent builds a complete, working Bot — name, face, SOUL.md, memory, tools, skills, rout
2,8/gün ort. +1 son gün 19 commit 1 yazar Python 17 Eyl 2026 güncellendi dün - 685
破限本地AI女友后宫,Agent+画图语音向量数据库+live2D+桌宠+酒馆角色卡导入+webchat,QQ+Telegram双通道,8G显存可跑 uncensored Fully offline AI girlfriends harem Openclaw/Claude cod
2,7/gün ort. +2 son gün 22 commit 1 yazar Python 02 Haz 2026 güncellendi dün - 686
lowfat - slim your command output. strips noise, saves tokens.
2,7/gün ort. +0 son gün 1 commit 1 yazar Rust 09 Nis 2026 güncellendi 3 gün önce - 687
#1 open-source code reviewer on Code-Review-Bench
2,7/gün ort. +0 son gün 1 commit 1 yazar Go 11 Mar 2026 güncellendi 7 gün önce - 688
AI-powered data-to-video generation. Upload a table, get a narrated animated data story.
2,7/gün ort. +4 son gün 0 commit 0 yazar TypeScript 20 Haz 2026 güncellendi 3 gün önce - 689
Run a hive mind of agents to focus on a specific goal
2,7/gün ort. +2 son gün 0 commit 0 yazar Rust 10 Tem 2026 güncellendi 09 Eki 2026 - 690
DSH Android 客户端:内置 Termux 环境跑 Node,在 Node 上跑 DSH 引擎,WebView 加载官方 Web GUI
2,7/gün ort. +0 son gün 277 commit 6 yazar JavaScript 11 Eki 2026 güncellendi 2 gün önce - 6912,7/gün ort. +0 son gün 0 commit 0 yazar 02 Nis 2026 güncellendi 19 Haz 2026
- 692
A dishwasher-loading game on a physical simulation of one real machine, built to benchmark language models and playable in a browser. The ga
2,7/gün ort. +0 son gün 20 commit 3 yazar TypeScript 12 Eki 2026 güncellendi 23 gün önce - 693
[NeurIPS 2026 Spotlight] Fast, lossless LLM inference via dual-view diffusion decoding.
2,7/gün ort. +0 son gün 0 commit 0 yazar Python 13 May 2026 güncellendi 13 Ağu 2026 - 694
Agent! now supports macOS 14.6 or later, Apple Silicon and Intel, latest release. The Best AI agent for Mac: drives any app via Accessibilit
2,7/gün ort. +0 son gün 43 commit 4 yazar Swift 11 Mar 2026 güncellendi 4 gün önce - 695
Live truecolor terminal dashboard for a locally running LLM: tok/s, TTFT, GPUs, context, MTP acceptance, layer and real expert routing (llam
2,7/gün ort. +0 son gün 96 commit 4 yazar Rust 11 Eyl 2026 güncellendi 6 gün önce - 696
AI coding agent harness. Five modes: practice to playoffs. Stop your AI from over-engineering. Code like a man. Elbow out bloat. Score clean
2,7/gün ort. +0 son gün 8 commit 1 yazar TypeScript 27 Haz 2026 güncellendi 15 gün önce - 697
An inference framework customized for AI MAX 395, compatible with both Linux and Windows, and supports deploying only qwen3.8-flash-next. Th
2,7/gün ort. +2 son gün 179 commit 5 yazar C++ 19 Eyl 2026 güncellendi dün - 698
neatroots: see, check and replay your AI agent's runs on your machine while you build it. Local-first, by Neatlogs.
2,7/gün ort. +0 son gün 197 commit 20 yazar TypeScript 09 Eki 2026 güncellendi 3 gün önce - 699
A unified Swift API for Apple’s Foundation Models-style experience across cloud and local LLM providers. Bring OpenRouter, Ollama, Claude, G
2,7/gün ort. +0 son gün — commit Swift 30 Eki 2026 güncellendi 2 gün önce - 700
Turn any course PDF into an interactive 3D pop-up textbook with your own AI (Claude, OpenAI, Gemini, Ollama or Claude Code). Runs locally, o
2,7/gün ort. +1 son gün — commit JavaScript 02 Kas 2026 güncellendi 5 gün önce