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
Phoenix-native LLM evaluation, prompt testing, model comparison, red teaming, and observability for Elixir
0,2/gün ort. +0 son gün — commit Elixir 20 Mar 2026 güncellendi 3 gün önce - 52
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 — commit Python 25 Tem 2026 güncellendi 2 gün önce - 53
A coding agent that builds it's own tools and mines it's own skills and always ships with receipts.
0,2/gün ort. +0 son gün — commit Rust 11 Tem 2026 güncellendi 2 gün önce - 54
Red Team AI Benchmark: Evaluating LLMs for authorized offensive-security tasks
0,1/gün ort. -1 son gün — commit Python 09 Tem 2026 güncellendi 13 Tem 2026 - 55
Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model
0,1/gün ort. +0 son gün — commit Python 19 Haz 2026 güncellendi 2 gün önce - 56
Practical LLM evaluation for teams that ship to production. Deterministic + LLM-as-judge evaluators, dataset support, CI/CD integration.
0,1/gün ort. +0 son gün — commit Python 24 Nis 2026 güncellendi 21 Eyl 2026 - 57
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 - 58
Canonical memory infrastructure: BM25 recall over trusted files for AI agents.
0,1/gün ort. +0 son gün — commit Python 26 May 2026 güncellendi 14 Tem 2026 - 59
Portable YAML evals for AI agents and model harnesses.
0,1/gün ort. +0 son gün — commit Rust 07 May 2026 güncellendi 15 Haz 2026 - 60
How do you KNOW if a 'skill' is any good - deterministically? This runs controlled skill-vs-no-skill experiments. It doesn't just ask, “Did
0,1/gün ort. +1 son gün — commit Python 04 Haz 2026 güncellendi dün - 61
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 — commit Python 27 Haz 2026 güncellendi 29 Eyl 2026 - 62
Two Claude Code skills for adversarial code review (single-model PAR and multi-model MMAR with cross-critique to catch hallucinations), plus
0,1/gün ort. +0 son gün — commit Python 08 May 2026 güncellendi 06 Haz 2026 - 63
The canonical standard for building production-grade agentic products — autonomy × oversight, composition patterns, the 9-layer harness, a 3
0,1/gün ort. +0 son gün — commit Python 30 May 2026 güncellendi 28 Eyl 2026