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

AI / LLM

Tümü ai-agents 5.761 llm 4.926 mcp 4.405 claude 2.833 anthropic 1.288 openai 993 rag 870 agents 806 prompt-engineering 797 image-generation 626 generative-ai 387 knowledge-graph 385 text-to-speech 300 semantic-search 215 speech-recognition 173 embeddings 155 vector-search 138 llmops 109

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 classification

1
aaddrick/building-with-typesafe-jev önem 29gpt6-luna uyum 23gpt6-luna 152
Coding agent’lara TypeSafe AI Jev ile typed decisions ve calibrated confidence kullanmayı öğreten, topluluk projeleri ve code sketch’leri içeren bir agent skill’idir.
Neden yükseliyor · İki günlük yaşında 69 yıldız almış; bu erken ilgiye işaret ediyor. Ancak son commit ve farklı yazar verisi ölçülmediğinden ilginin kaynağı ve proje aktivitesi hakkında daha güçlü bir çıkarım yapılamaz.
3,6/gün ort. +2 son gün 0 commit 0 yazar Python 26 Eyl 2026 güncellendi 01 Eki 2026
agent-skill agent-skills ai-agents calibration classification claude-code claude-code-plugin claude-code-skill
152
2
StartLuxLabs/StartLux-Decision 1.664
Open decision models from 0.8B to 27B: a calibrated probability for every option in one pass, and a short thought only when unsure. Engine f
42,7/gün ort. +10 son gün 22 commit 2 yazar Python 29 Eyl 2026 güncellendi 16 gün önce
agents calibration classification decision-making gguf inference llama-cpp llm
1.664
3
receptron/laya 1.043
Run Laya, the open-source Jev-compatible System-1 decision model, from Node.js / TypeScript via ONNX Runtime
21,3/gün ort. +4 son gün 6 commit 2 yazar TypeScript 19 Eyl 2026 güncellendi 22 gün önce
classification decision-model inference llm local-first machine-learning nodejs onnx
1.043
4
mrmps/classifier-dev 436
Zero-shot text classification over plain HTTP — no API key, no account. One Cloudflare Worker, a CLI, and an MCP server. https://classifier.
5,1/gün ort. +0 son gün 4 commit 2 yazar TypeScript 13 Ağu 2026 güncellendi 2 gün önce
api classification cli cloudflare-workers llm mcp text-classification zero-shot
436
5
nicobrenner/jeffy 121
Pretrained text classifiers you can run and retrain on CPU
3,4/gün ort. +0 son gün — commit Python 02 Eki 2026 güncellendi 9 gün önce
classification embeddings local-first logistic-regression multilingual no-gpu-required pretrained-models sentiment-analysis
121
6
marcreichel/laya-php 112
Classify text in PHP without an LLM bill: typed decisions in 100+ languages, self-hosted. Laravel-ready SDK for Laya, a Jev AI alternative.
2,7/gün ort. +1 son gün 39 commit 1 yazar PHP 26 Eyl 2026 güncellendi 2 gün önce
ai classification decision-engine decision-model jev jev-ai jev-api laravel
112
7
ikermoel/open-alternative-jev 77
Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM i
1,5/gün ort. +0 son gün 0 commit 0 yazar Python 18 Eyl 2026 güncellendi 25 Eyl 2026
calibration classification jev jev-alternative llm logprobs open-jev open-source-jev
77
8
parsehawk/parsehawk 73
Turn documents into structured JSON with local-first document AI. Run 100% locally by default, with API, CLI, and Web UI.
0,5/gün ort. +0 son gün — commit Python 25 Haz 2026 güncellendi 19 gün önce
artificial-intelligence classification document-ai document-processing extraction json json-schema llm
73
9
tomerglick57/Jevstiller 73
Distill a repeated Jev classification task into a local model, on the fly — same answers, your hardware.
1,6/gün ort. +1 son gün — commit Python 21 Eyl 2026 güncellendi 7 gün önce
classification distillation jev knowledge-distillation llm mlops model-cascade python
73
10
PyModel/jev-judge-mcp 47
Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate,
1/gün ort. +0 son gün — commit Python 23 Eyl 2026 güncellendi 13 gün önce
agent-tools ai-agents ai-guardrails classification claude-code fact-checking guardrails llm
47
11
mattn/go-jev 46
Go SDK and CLI for TypeSafe Jev: typed decisions (yes/no, choice, score) from a model
1/gün ort. +0 son gün — commit Go 23 Eyl 2026 güncellendi 23 Eyl 2026
ai classification cli go golang jev llm sdk
46
12
shaharia-lab/jev-cli 44
Command-line tool for TypeSafe AI's Jev model. Ask yes/no, multiple-choice and rubric questions about any text and get calibrated probabilit
0,9/gün ort. +1 son gün — commit Rust 19 Eyl 2026 güncellendi 5 gün önce
ai-agents classification cli command-line-tool devtools jev llm mcp
44
13
manjunathshiva/opendecider 38
Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID
0,9/gün ort. +0 son gün — commit Python 27 Eyl 2026 güncellendi 4 gün önce
apple-silicon calibration classification decision-model gguf huggingface llm mlx
38
14
jwuthri-cloud/SelfJev 33
Self-hosted decision model (selfjev-4b) with a Jev-compatible API: Python SDK, server, fine-tuning and RLCD.
1,9/gün ort. +0 son gün — commit Python 21 Eki 2026 güncellendi 17 gün önce
classification decisions fine-tuning guardrails llm llm-evaluation lora python-sdk
33
15
porespellar/Zer0Fit 32
Zero-shot forecasting, tabular classification, and regression via MCP — exposes Google TimesFM 2.5 and TabFM v1.0.0 to AI assistants. Just a
0,3/gün ort. +0 son gün — commit Python 10 Tem 2026 güncellendi 04 Eyl 2026
ai classification forecasting foundation-models llm machine-learning mcp open-webui
32
16
agencyenterprise/jev-recipes 24
248 small Jev decisions for JavaScript and TypeScript: route, rerank, gate, grade, compare, and label text for agents, RAG, support, code re
0,5/gün ort. +0 son gün — commit TypeScript 22 Eyl 2026 güncellendi 2 gün önce
agent-tools agents ai-agents ai-sdk classification guardrails jev langchain
24
17
spinfinc/spinf-serve 21
Bulk classification and decision inference on one GPU: the content is read once, every question about it is scored in the same pass. OpenAI-
1,6/gün ort. +0 son gün — commit Python 25 Eki 2026 güncellendi 10 gün önce
batch-inference classification content-moderation decision-model extraction fp8 gemma inference-engine
21
18
Singularity-Compute/super-decider 19
Decisions, not essays: a choice, a yes or no, or a score with a calibrated probability. Open weights, Jev-compatible API, adaptive thinking.
0,8/gün ort. +0 son gün — commit Python 13 Eki 2026 güncellendi 13 gün önce
ai-agents calibration classification decision-model diffusion-llm guardrails jev llm-routing
19
19
xSarumo/TidyFS 19
Linux TUI smart file organizer with TF-IDF and local LLM classification
0,1/gün ort. +0 son gün — commit Go 10 May 2026 güncellendi 27 Haz 2026
classification filesystem linux ml tui tui-app utilities utility
19
20
zhulinchng/jevper 19
Jev-shaped (TypeSafe System One) classification wrapper over OpenAI-like clients
0,4/gün ort. +0 son gün — commit Python 23 Eyl 2026 güncellendi 07 Eki 2026
classification confidence llm logprobs openai pydantic python structured-output
19
21
alleyxd/AnyDecide 18
Turn any local language model into a fast decision API with typed, probabilistic answers
0,6/gün ort. -5 son gün — commit Python 09 Eki 2026 güncellendi dün
calibration classification decision-model fastapi llm lora
18
22
SerendipityOneInc/instinct 17
Instinct: single-forward-pass decision models (choice / true-false / score) returning a probability per candidate
0,4/gün ort. +0 son gün — commit Python 29 Eyl 2026 güncellendi 30 Eyl 2026
calibration classification decision-model llm qwen transformers vllm
17
23
aegea-dev/videre 16
Multimedia library for the age of AI
0,2/gün ort. +0 son gün — commit Rust 24 Ağu 2026 güncellendi 4 gün önce
duplicate-detection duplicate-removal embedding face-clustering face-search geolocation image-processing image-search
16
24
paramjeetn/jev-cookbook 16
The complete cookbook for Jev by TypeSafe AI — 120+ use cases, 10 runnable examples, 4 composition patterns, and first-principles theory for
0,3/gün ort. +0 son gün — commit Python 22 Eyl 2026 güncellendi 22 Eyl 2026
agentic-ai ai-agents ai-engineering classification cookbook decision-engine jev llm
16
25
Micha0827/snapjudge 14
Typed decisions (choice / score / yes-no) from local Qwen models on Apple Silicon. Probabilities come straight from the logits, no text gene
0,3/gün ort. +0 son gün — commit Python 18 Eyl 2026 güncellendi 21 Eyl 2026
apple-silicon classification decision-making fastapi llm llm-evaluation local-llm logits
14
26
prasanthj/duckdb-jev 14
High-throughput, robust native DuckDB extension for batched and streaming TypeSafe/Jev classification, scoring, and semantic predicates from
0,3/gün ort. +0 son gün — commit C++ 20 Eyl 2026 güncellendi 18 gün önce
ai classification cpp data-engineering duckdb duckdb-extension jev llm
14
27
backant-io/jevelry 13
Use Jev everywhere to make & track decisions
0,3/gün ort. +0 son gün — commit TypeScript 22 Eyl 2026 güncellendi 19 gün önce
agent-skill classification claude-code codex confidence cursor decision-model jev
13
28
saibimajdi/typesafeai-dotnet-sdk 12
Community .NET SDK for the TypeSafe AI System One API — typed noul, choice, and score questions with structured, confidence-scored answers.
0,2/gün ort. +0 son gün — commit C# 16 Eyl 2026 güncellendi 4 gün önce
ai classification csharp dotnet llm sdk systemone typesafe
12