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
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 7g — commit Python 25 Tem 2026 güncellendi 4 gün önce - 52
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 7g — commit Python 12 Eki 2026 güncellendi 9 gün önce - 53
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 7g — commit TypeScript 18 Eyl 2026 güncellendi 25 Eyl 2026 - 54
Claude Code/Codex skills, evals, harnesses/context tools, and learning resources that make it easy to build with Jev, TypeSafe's System One
0,4/gün ort. +0 son gün +0 son 7g — commit Python 28 Eyl 2026 güncellendi bugün - 55
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 - 56
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 7g — commit Python 27 Haz 2026 güncellendi 29 Eyl 2026 - 57
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 - 58
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 - 59
Same model, different wrapper: a from-scratch benchmark comparing coding-agent harnesses (codex, pi, opencode, cursor, devin) and open model
1/gün ort. +0 son gün -0,1 son 7g 0 commit 0 yazar Python 19 Haz 2026 güncellendi 27 Ağu 2026 - 60
Open-source skills for Claude Code and Codex, with an MCP server, a PyPI package and Suede Awesome Everything, a directory that scores AI ag
0,8/gün ort. -1 son gün -0,1 son 7g 153 commit 2 yazar JavaScript 24 May 2026 güncellendi bugün - 61
neatroots: see, check and replay your AI agent's runs on your machine while you build it. Local-first, by Neatlogs.
3/gün ort. -1 son gün -0,1 son 7g 224 commit 20 yazar TypeScript 09 Eki 2026 güncellendi 3 gün önce - 62
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 -0,1 son 7g — commit Rust 11 Tem 2026 güncellendi bugün - 63
Joy — a local-first personal assistant. Rust core (loop / memory / tools / graph / evals), TypeScript gateways + dashboard, Python thin SDK.
2/gün ort. +0 son gün -1,6 son 7g — commit Rust 20 Eyl 2026 güncellendi dün - 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 -13,4 son 7g 125 commit 11 yazar Python 28 Mar 2026 güncellendi dün