Açık kaynak radarı

Havuz

Takip ettiğimiz konularda yükselen açık kaynak projeler — yıldız ivmesi, gerçek geliştirme aktivitesi ve AI değerlendirmesiyle.

repo · sayfa 1 / 1

Sırala

Yıldız/gün (hız)Son gün (★/gün)Son hafta (★/gün)Son ay (★/gün)Toplam yıldız AI önem skoru Bana uyum Commit (28g)Yazar (28g)En yeni

Konu

Tümü AI / LLM18 Veri9 Geliştirici araçları13 Diğer3 SaaS altyapı13 Web11

Geliştirici araçları

Tümü developer-tools 3.390 cli 2.770 self-hosted 2.483 observability 361 benchmark 354 static-analysis 302 git 280 github-actions 253 monitoring 233 documentation 205 testing 171 ci-cd 112 debugging 94

Süz

Yalnız hareketli Yalnız analizli≥ 0 ≥ 100 ≥ 500 ≥ 2.000

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

Sırala:

Etiketler yükleniyor…

Aktif llm-inference

1
mw00/project-maya 2.448
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
87,4/gün ort. +55 son gün 897 commit 20 yazar Cuda 06 Eki 2026 güncellendi bugün
cuda glm glm-5 llm llm-inference local-llm mixture-of-experts moe
2.448
2
AtomicBot-ai/Atomic-Chat 1.921
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https
8,9/gün ort. +9 son gün 176 commit 3 yazar TypeScript 31 Mar 2026 güncellendi dün
ai-chat ai-tools apple-silicon chatgpt deepseek desktop-app gemma gguf
1.921
3
surya-koritala/Glyd önem 54gpt6-luna uyum 10gpt6-luna 321
Glyd, model ağırlıklarını ve KV cache'i bit düzeyinde kayıpsız biçimde sıkıştırıp GPU'da kullanmayı hedefleyen bir compression yazılımıdır.
Neden yükseliyor · README, yaygın bir maliyet sorununa doğrudan yanıt verdiğini ve 32B ile 72B modellerde daha az GPU ile çalışmaya dair ölçümler sunuyor; ancak 9 günlük repoda 170 yıldız ve 474 commit'in yalnızca 2 farklı yazardan gelmesi, ilginin ve geliştirme temposunun geniş bir katkıcı tabanına dayandığını göstermiyor. Yükselişin kesin kaynağı veya bağımsız benimsenme verisi bilinmiyor.
7,1/gün ort. +1 son gün 47 commit 1 yazar Rust 19 Eyl 2026 güncellendi dün
benchmark c-abi cli compression cuda data-compression deduplication delta-compression
321
4
Magnvs7/Promethevs 85
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
6,5/gün ort. +55 son gün 12 commit 1 yazar 21 Eki 2026 güncellendi 11 gün önce
deepseek llm local-inference mixture-of-experts quantization consumer-hardware deepseek-v4 llm-inference
85
5
leonxger/deepseek-colab 24
Uncensored DeepSeek-V4.1-Flash IQ2_XS on Google Colab
6/gün ort. +10 son gün 1 commit 1 yazar Python 30 Eki 2026 güncellendi 4 gün önce
colab cuda deepseek deepseek-v4 gguf google-colab gpu llama-cpp
24
6
amurgola/LumaBrowser 130
Local AI desktop app: a Chromium browser with a GPU-aware llama.cpp runtime, OpenAI-compatible API, AI chat and agents, Stable Diffusion ima
5,2/gün ort. +0 son gün 15 commit 1 yazar JavaScript 09 Eki 2026 güncellendi dün
ai-agents ai-browser browser-automation chatgpt-alternative desktop-app electron gguf llama-cpp
130
7
hasso5703/alzeo 245
dgx-spark-qwen38 is an open-source installer that turns an NVIDIA DGX Spark, or any GB10 machine (ASUS, Dell, HP, Lenovo, MSI, GIGABYTE, Ace
3,1/gün ort. +0 son gün — commit Python 15 Ağu 2026 güncellendi bugün
ai-agents asus-ascent-gx10 dgx-spark gb10 image-generation llm-inference local-ai local-llm
245
8
jaylfc/taOS 589
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. +0 son gün 7 commit 1 yazar Python 05 Nis 2026 güncellendi bugün
agent-framework ai-agents ai-platform apple-silicon distributed-computing llm orange-pi raspberry-pi
589
9
benmaster82/Pithos 18
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
2,6/gün ort. +4 son gün — commit C 27 Eki 2026 güncellendi bugün
lfm2 lfm25 ai-agent avx2 c coding-agent cross-platform gguf
18
10
nicorobinreal/llmspeed 168
Feel how fast a local LLM runs before you buy the hardware
2,5/gün ort. +1 son gün — commit TypeScript 28 Ağu 2026 güncellendi 14 gün önce
benchmark gpu hardware inference llm llm-inference local-llm ollama
168
11
JustVugg/lumabri 211
Run large AI models across your computers and servers. Powered by Colibri. Pure C.
2,3/gün ort. +1 son gün 327 commit 1 yazar C 04 Ağu 2026 güncellendi bugün
c cluster-computing colibri distributed-inference llm-inference local-ai mixture-of-experts peer-to-peer
211
12
0xBakeer/TandemLLM 73
An environment where open models work as agents: a first-level harness with routing, skills, memory and sandboxed tools, on an engine that d
2/gün ort. +3 son gün — commit Python 28 Eyl 2026 güncellendi bugün
dgx-spark llm-inference nvfp4 qwen speculative-decoding ai-agents exl3 inference-engine
73
13
dadwritestech/LlamaForge 120
Open-source control panel for the real llama.cpp: see where a model lands in your VRAM before loading, every llama-server flag per model, on
1/gün ort. +0 son gün — commit Python 06 Tem 2026 güncellendi dün
cuda dashboard gguf gui huggingface inference llama-cpp llama-server
120
14
Reederey87/glm53-flash-exl3-2x-dgx-spark 63
GLM-5.3-Flash EXL3 (320B MoE) on 2x NVIDIA DGX Spark — production serving kit, 1M context, 97%+ multi-session prefix caching, DFlash2 spec d
0,9/gün ort. +0 son gün — commit Python 27 Ağu 2026 güncellendi 16 gün önce
dgx-spark flashinfer gb10 glm llm-inference self-hosted sparse-attention tensor-parallel
63
15
gpillon/ignis 51
OpenAI-compatible inference server for Qwen3.8 on one RTX 5090 / RTX PRO 6000: the 27B at ~170 tok/s (peaks ~370), Flash-Next (125B MoE) at
0,8/gün ort. +1 son gün — commit Rust 01 Eyl 2026 güncellendi bugün
blackwell coding-agents cuda inference-engine llm llm-inference local-llm mixture-of-experts
51
16
0xBakeer/Qwen3.8-27B-FP8-on-a-single-DGX-Spark 55
Serving Qwen3.8-27B-FP8 on a single DGX Spark (GB10): 7.88 to 58.5 tok/s single-stream from decode strategy alone, weights untouched. Specul
0,7/gün ort. +0 son gün — commit Python 16 Ağu 2026 güncellendi 30 Eyl 2026
benchmark dflash2 dgx-spark fp8 gb10 llama-cpp llm-inference llm-serving
55
17
Sandermage/sndr_core_engine 133
SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere sm_86, 2× A5000/3090). Qwen3.6-35B-A
0,7/gün ort. +0 son gün — commit Python 17 Nis 2026 güncellendi 01 Eki 2026
cuda llm-inference qwen vllm speculative-decoding tool-calling rtx-3090 awq
133
18
0xBakeer/Qwen3.8-27B-4-bit-on-a-single-DGX-Spark 51
Serving 4-bit Qwen3.8-27B on a single DGX Spark (GB10): 75 tok/s single-stream, 246 tok/s aggregate at 8-way concurrency. NVFP4 vs MixedInt4
0,6/gün ort. +0 son gün — commit Python 16 Ağu 2026 güncellendi 30 Eyl 2026
autoround benchmark dgx-spark gb10 int4 llm-inference llm-serving marlin
51
19
duongngocbinh56599-ui/local-llm-lab 94
Honest local LLM deployment planning and benchmarking for high unified-memory Macs and future Linux/NVIDIA rigs.
0,6/gün ort. +0 son gün — commit Python 05 Haz 2026 güncellendi 19 Eyl 2026
apple-silicon benchmark hardware-planning llama-cpp llm-inference local-llm mlx ollama
94
20
Datura-ai/lium-localmaxxing 36
Reproduce Lium's LocalMaxxing leaderboard runs (7 boards, 20 Verified) on a rented Lium GPU in one script — vLLM/llama.cpp recipes, measured
0,6/gün ort. +0 son gün — commit Shell 06 Eyl 2026 güncellendi 26 Eyl 2026
gpu lium reproducible benchmark llama-cpp llm-inference vllm
36
21
infercrane/infercrane 53
Open-source infrastructure for the full inference lifecycle: deploy, observe, scale, optimize, and safely release self-hosted models behind
0,6/gün ort. +0 son gün — commit Go 09 Ağu 2026 güncellendi 2 gün önce
ai-infrastructure aws gcp golang gpu-inference inference kubernetes llm
53
22
wundercorp/loki 28
The agent that evolves with you 𖤍
0,5/gün ort. +0 son gün — commit Python 11 Eyl 2026 güncellendi 2 gün önce
agent agent-orchestration agent-skills agentic-ai agents ai autonomous-agents cli
28
23
NVIDIA/swe-serve 23
SWE-Serve: an agentic benchmark of 53 production inference-engineering tasks derived from merged SGLang pull requests, run with Harbor.
0,5/gün ort. +2 son gün — commit Python 18 Eyl 2026 güncellendi 25 gün önce
benchmark evaluation llm-agents llm-inference sglang
23
24
tonyd2wild/The-Sparky-Command-Center 48
Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional
0,5/gün ort. +0 son gün — commit TypeScript 23 Tem 2026 güncellendi 21 gün önce
dashboard dgx-spark gpu-monitoring homelab llm llm-inference mlops monitoring
48
25
jaeseok614/ai-hardware-fit 44
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 dün
gpu gpu-calculator korean llama-cpp llm llm-inference local-llm ollama
44
26
john-rocky/apple-silicon-llm-bench 73
Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the
0,4/gün ort. +0 son gün — commit Python 02 May 2026 güncellendi 16 gün önce
apple-silicon benchmark coreml ios llama-cpp llm llm-inference macos
73
27
anthony-chaudhary/fak 45
Agentic Runtime
0,3/gün ort. +1 son gün — commit Go 21 Haz 2026 güncellendi bugün
agent-kernel agentic-ai ai-agents ai-gateway claude-code context-compression gguf golang
45
28
syndicalt/llmff 46
Bounded, inspectable LLM inference pipelines from declared YAML — runs offline against Ollama or any OpenAI-compatible local server, emittin
0,3/gün ort. +0 son gün — commit Rust 22 May 2026 güncellendi 07 Tem 2026
agent-tools cli inference-pipeline json-schema llm llm-inference llm-pipeline llmops
46
29
ruashots/flashnext-2x3090 17
What I run on my inference server: Qwen3.8-Flash-Next on two RTX 3090s, and how I got here
0,3/gün ort. +0 son gün — commit Python 27 Ağu 2026 güncellendi 22 gün önce
benchmark llama-cpp llm-inference local-llm mixture-of-experts qwen rtx-3090
17
30
pur4v/p2ptokens 28
Distributed, peer-to-peer, decentralized network for LLM inference — peers seed & leech completions, metered by BitTorrent-protocol-style up
0,2/gün ort. +0 son gün — commit Rust 12 Tem 2026 güncellendi 15 Tem 2026
ai decentralized distributed inference libp2p llm llm-inference p2p
28
31
Quartermaster-Labs/Quartermaster 33
Local AI for your whole house: chat, images and voice on your own GPU. Computes each model's flags, fits them to your VRAM, and hot-swaps th
0,2/gün ort. +0 son gün — commit Go 17 Haz 2026 güncellendi 2 gün önce
anthropic-api gguf golang image-generation inference-server llamacpp llm llm-inference
33
32
noname9006/LlamaToaster 15
Benchmark llama.cpp on your own GPU/CPU boxes and compare against everyone else's — sweep runner, an sha256-keyed index of ~4M GGUF files, a
0,2/gün ort. +0 son gün — commit TypeScript 12 Ağu 2026 güncellendi dün
benchmark fastify gguf gpu huggingface inference-performance llama-cpp llamacpp
15
33
thc1006/qwen3.6-speculative-decoding-rtx3090 35
llama.cpp speculative decoding measured on one RTX 3090, Qwen3.6-35B-A3B UD-Q4_K_XL, commit 3737e4137. Published figures are re-derived from
0,2/gün ort. +0 son gün — commit Python 21 Nis 2026 güncellendi 14 gün önce
ampere benchmark cuda ggml inference-benchmark llama-cpp local-llm mixture-of-experts
35
34
KumphanartDansiri/v100-vllm-2026 23
Benchmarks and notes for running modern LLMs with vLLM on 8x Tesla V100-32GB in 2026.
0,2/gün ort. +0 son gün — commit Python 26 Haz 2026 güncellendi 10 Tem 2026
benchmark cuda fp8 llm-inference moe sm70 tesla-v100 v100
23
35
colomalabs/coloma 14
The Continuous Verification and Optimization layer for self-hosted LLMs
0,1/gün ort. +0 son gün — commit Python 14 Tem 2026 güncellendi 17 Tem 2026
llm-inference mlops self-hosted vllm vllm-serving
14
36
icedmoca/neura 20
Neura lets you run long, tool heavy coding sessions without blowing up token costs by compressing old context into references and only resto
0,1/gün ort. +0 son gün — commit Rust 02 May 2026 güncellendi 11 Tem 2026
claude-code cli codex codex-cli coding-cli llm-inference token-optimization memory-retrieval
20
37
zorost/sparkduet 0
Serve DeepSeek and Qwen, run an on-demand model library, and fine-tune with Unsloth QLoRA on 2x NVIDIA DGX Spark. TP=2 vLLM lanes behind one
0/gün ort. +0 son gün — commit Python 25 Ağu 2026 güncellendi 07 Eyl 2026
coding-agents deepseek dgx-spark fine-tuning gb10 homelab llama-swap llm-inference
0