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
Download official Windows ISOs directly from Microsoft's CDN. Web app + CLI tool. No account, no ads, no browser required.
0,2/gün ort. +2 son gün — commit TypeScript 10 Nis 2026 güncellendi 01 Eki 2026 - 2
Benchmark, evaluate, and optimize skills to ensure reliable performance across all LLMs
0,3/gün ort. +1 son gün — commit TypeScript 06 Mar 2026 güncellendi 28 May 2026 - 3
A composable framework for reproducible evaluation of long-running agents.
0,8/gün ort. +1 son gün — commit Python 02 Ağu 2026 güncellendi 7 gün önce - 4
Run your real agent with and without your skills, MCPs, and rules. See which ones actually help, and what they cost in tokens. Supports Clau
1,3/gün ort. +0 son gün 68 commit 1 yazar Python 13 May 2026 güncellendi 2 gün önce - 5
⚡ Unit tests for AI. Test prompts, compare models, save money.
0,5/gün ort. +0 son gün — commit Python 11 Nis 2026 güncellendi 22 May 2026 - 6
skilled: open-source agent skill evaluation CLI and MCP server for Codex and Claude Code. Test skills, detect regressions, and improve with
1/gün ort. +0 son gün — commit TypeScript 22 Ağu 2026 güncellendi 3 gün önce - 7
Benchmark your local LLMs: speed, memory, and quality, in one command. TUI leaderboard for Ollama, LM Studio, llama.cpp, and vLLM.
0,6/gün ort. +0 son gün — commit Python 03 Ağu 2026 güncellendi 10 Ağu 2026 - 8
Benchmarking Agents on Real-World Terminal Tasks
0,3/gün ort. +0 son gün — commit Python 07 May 2026 güncellendi 31 May 2026 - 9
Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.
0,3/gün ort. +0 son gün — commit Python 12 May 2026 güncellendi 16 Ağu 2026 - 10
Regression testing and configuration sweeps for RAG pipelines, with the statistics to know whether a change actually helped.
0,2/gün ort. +0 son gün — commit Python 09 Ağu 2026 güncellendi 13 Ağu 2026 - 11
Local-first evaluation framework for RAG systems and AI Agents. 18+ metrics, CLI + SDK, framework-agnostic. The pytest of AI evaluation.
0,1/gün ort. +0 son gün — commit Python 08 Tem 2026 güncellendi 8 gün önce - 12
Open-source control plane for governed ModelOps — fine-tune, evaluate, promote, and serve models as cost-capped, policy-gated, audited comma
0,1/gün ort. +0 son gün — commit Python 16 Tem 2026 güncellendi dün - 13
The open testing standard for voice AI agents. Deterministic + semantic + RAG augmented evaluation. Local first. Zero telemetry.
0,1/gün ort. +0 son gün — commit Python 01 May 2026 güncellendi 22 Haz 2026 - 14
Semantic cache strategy bench: replay recorded request traces through candidate caching policies and measure which one actually pays off.
0,3/gün ort. -1 son gün — commit Python 03 Eyl 2026 güncellendi 04 Eyl 2026