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…
- 151
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 — commit TypeScript 18 Eyl 2026 güncellendi 25 Eyl 2026 - 152
TypeSafe (Jev) skill routing for Hermes Agent: names the one skill worth loading, before the model call. Opt-in, stdlib only, ~$0.001 per ro
0,3/gün ort. +0 son gün — commit Python 16 Eyl 2026 güncellendi 21 Eyl 2026 - 153
JEV-guided context compaction for OpenCode. Prune stale tool history instead of rewriting conversations with an LLM.
0,4/gün ort. +0 son gün — commit TypeScript 26 Eyl 2026 güncellendi 11 gün önce - 154
An unofficial, provider-neutral Unix client for Jev from TypeSafe AI. Written in Go.
0,4/gün ort. +0 son gün — commit Go 26 Eyl 2026 güncellendi 9 gün önce - 155
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 — commit Python 28 Eyl 2026 güncellendi bugün - 156
Local gateway that routes coding-agent tool decisions through Jev and can attach a read-only advisor (GPT or Claude).
0,7/gün ort. -10 son gün — commit TypeScript 16 Eki 2026 güncellendi dün - 157
Coding-agent tools on TypeSafe's Jev, measured in public. review-router: caught 13 of 13 CVE fixes a filename rule sent to a quick review. j
0,3/gün ort. +1 son gün — commit Python 20 Eyl 2026 güncellendi 12 gün önce - 158
Jev judgment, not generation: prune long tool output, screen fetched pages for injected instructions, and gate completion claims inside Deep
0,3/gün ort. +0 son gün — commit TypeScript 20 Eyl 2026 güncellendi 6 gün önce - 159
Shepherd is an end-to-end AI Software Engineering platform that supervises the complete software delivery lifecycle—not just code generation
0,1/gün ort. +0 son gün — commit Rust 31 May 2026 güncellendi dün - 160
Runtime constraints for the pi coding agent: checks every side-effecting tool call against what you said, before it runs. Powered by TypeSaf
0,3/gün ort. +0 son gün — commit TypeScript 18 Eyl 2026 güncellendi 24 gün önce - 161
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 16 gün önce - 162
A decision model that returns calibrated answers to yes/no, choice, score and multi-label questions.
0,4/gün ort. +0 son gün — commit Python 29 Eyl 2026 güncellendi 12 gün önce - 163
Chrome extension that cleans up your LinkedIn feed: hides engagement bait, self-promo and off-topic posts using Jev, TypeSafe AI's typed cla
0,3/gün ort. +0 son gün — commit TypeScript 19 Eyl 2026 güncellendi 20 Eyl 2026 - 164
Agent skills for designing, training, evaluating and improving application-specific decision systems. Primitive/model selection, data assemb
0,3/gün ort. +0 son gün — commit Python 18 Eyl 2026 güncellendi 28 Eyl 2026 - 165
Let Jev steer Claude Code: the right reasoning effort, subagent model and skill for every prompt. A Claude Code plugin powered by TypeSafe's
0,3/gün ort. +0 son gün — commit TypeScript 23 Eyl 2026 güncellendi 30 Eyl 2026 - 166
Per-turn model routing for the Pi coding agent: a small judge picks the cheap or the strong tier for each message, with multi-model failover
0,1/gün ort. +0 son gün — commit TypeScript 23 Tem 2026 güncellendi 13 gün önce - 167
What can Jev actually do? Reproducible experiments and research reports exploring its capabilities and limits.
0,4/gün ort. +0 son gün — commit Python 29 Eyl 2026 güncellendi 14 gün önce - 168
Community-maintained JEV runner integration for Midscene Test
0,3/gün ort. +0 son gün — commit TypeScript 21 Eyl 2026 güncellendi 16 gün önce - 169
A 4B decision model built for Korean.
0,9/gün ort. +0 son gün — commit 21 Eki 2026 güncellendi 14 gün önce - 170
One grounded Jev/Playwright core: typed SDK, persistent CLI, and MCP server with native browser operations and deterministic assertions.
0,3/gün ort. +0 son gün — commit JavaScript 17 Eyl 2026 güncellendi 3 gün önce - 171
Don't trust an Agent. Test it. Open-source lab for agent credit — exams → evidence → explainable, recomputable scores. Built for the day age
0,2/gün ort. +0 son gün — commit TypeScript 29 Ağu 2026 güncellendi 16 gün önce - 172
x402 risk-check provider: signed pre-payment verdicts — OFAC, phishing feeds, transaction simulation, drainer-kit code, and our own EIP-7702
0,3/gün ort. +0 son gün — commit TypeScript 27 Eyl 2026 güncellendi 2 gün önce - 173
Jev? Déjà vu. Browser agents that run on instinct, no Jev needed. One look at the page, one call to any open model, one action. Faster than
0,3/gün ort. +0 son gün — commit Python 22 Eyl 2026 güncellendi 23 Eyl 2026 - 174
High-performance, high-precision, locally-fast-deployed Jev-class medical decision service on national medical exams — four readings, one ro
0,1/gün ort. +0 son gün — commit Python 25 Eyl 2026 güncellendi 28 Eyl 2026 - 175
Research design for a Jev-native agent system:enable more options than jev provided with virtulization and paging, tool integration, externa
0/gün ort. +0 son gün — commit Python 23 Eyl 2026 güncellendi 28 Eyl 2026