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…
- 51
Canonical memory infrastructure: BM25 recall over trusted files for AI agents.
0,1/gün ort. +0 son gün +0 son 30g — commit Python 26 May 2026 güncellendi dün - 52
Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks
0,2/gün ort. +0 son gün +0 son 30g — commit Python 09 Tem 2026 güncellendi 13 Tem 2026 - 53
Eval-driven multimodal agent for identifying trees, logs, bark, leaves and wood from photographs. Dendrology is the reference domain; the e
0,2/gün ort. +0 son gün +0 son 30g — commit Python 25 Tem 2026 güncellendi 4 gün önce - 54
A coding agent that builds it's own tools and mines it's own skills and always ships with receipts.
0,1/gün ort. +0 son gün +0 son 30g — commit Rust 11 Tem 2026 güncellendi bugün - 55
Benchmark of AI coding agents building web apps and deploying them to Cloudish, DigitalOcean, Render and Vercel, measuring success, time, to
0,7/gün ort. +0 son gün +0 son 8g — commit Python 12 Eki 2026 güncellendi 9 gün önce - 56
Decision harness for TypeSafe Jev — confidence gates, shadow mode, recipes, and evals. Claude CLI 48.9s → Jev 1.3s on the same row-filter jo
0,3/gün ort. +0 son gün +0 son 30g — commit TypeScript 18 Eyl 2026 güncellendi 25 Eyl 2026 - 57
The canonical standard for building production-grade agentic products — autonomy × oversight, composition patterns, the 9-layer harness, a 3
0,1/gün ort. +1 son gün +0 son 30g — commit Python 30 May 2026 güncellendi 28 Eyl 2026 - 58
Self-hosted system for improving AI agents, by InferEdge
1,4/gün ort. +0 son gün +0 son 3g — commit Python 26 Eki 2026 güncellendi bugün - 59
Claude Code plugin marketplace — agentic-engineering (spec-driven shape→decide→execute→measure→eval with adversarial review) + github-keeper
0,1/gün ort. +0 son gün +0 son 30g — commit Python 27 Haz 2026 güncellendi 29 Eyl 2026 - 60
What can Jev actually do? Reproducible experiments and research reports exploring its capabilities and limits.
0,4/gün ort. +0 son gün +0 son 3g — commit Python 29 Eyl 2026 güncellendi 13 gün önce - 61
Does the model pick the right tool? Tool-routing tests for your MCP server: run them on Claude and OpenAI models, see where each request lan
0,8/gün ort. +0 son gün +0 son 4g — commit TypeScript 19 Eki 2026 güncellendi 4 gün önce - 62
A langGraph-powered multi-agent RAG assistant for warranty, return, and consumer decision workflow.
0,8/gün ort. +0 son gün -0,1 son 30g — commit Python 11 Haz 2026 güncellendi 26 Eyl 2026 - 63
Open benchmark for Claude Code SEO skills — real headless execution against fixture sites with planted-defect answer keys. Deterministic sco
0,4/gün ort. +0 son gün -0,1 son 30g — commit JavaScript 02 Tem 2026 güncellendi 17 gün önce - 64
Build agentic systems. Run them with confidence. Orchestrate agents, automate business processes, inspect every execution, and keep humans i
5,3/gün ort. -65 son gün -7,4 son 30g 125 commit 11 yazar Python 28 Mar 2026 güncellendi dün