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
The black box for AI-written code. Passive decision graph linking every commit to the agent prompts behind it: drift detection, DLP audit of
2,3/gün ort. +0 son gün 10 commit 2 yazar Rust 02 Tem 2026 güncellendi 9 gün önce - 2
AutoHarness: Automated Harness Engineering for AI Agents
2,1/gün ort. +0 son gün 0 commit 0 yazar Python 02 Nis 2026 güncellendi 02 Nis 2026 - 3
Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness: a ctx.memory capability seam with a zero-dependency S
1,6/gün ort. +1 son gün 39 commit 2 yazar JavaScript 13 Ağu 2026 güncellendi 2 gün önce - 4
Read-only Kubernetes operations audit as an Agent Skill. 403 checks, a report a person can read, every morning.
0,9/gün ort. +0 son gün — commit Python 25 Eki 2026 güncellendi dün - 5
The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit
0,9/gün ort. +1 son gün — commit Rust 25 Mar 2026 güncellendi 4 gün önce - 6
EU AI Act compliance proxy for AI systems. Drop-in HTTP proxy that monitors every AI interaction for regulatory risks, logs to a tamper-proo
0,8/gün ort. +5 son gün — commit TypeScript 22 Mar 2026 güncellendi 15 Haz 2026 - 7
Don't make LLMs honest. Make every factual claim auditable. — An LLM Claim Auditing Layer with T1-T7 truth gradients. 98.1% business effecti
0,5/gün ort. +0 son gün — commit Python 10 May 2026 güncellendi 10 May 2026 - 8
Self-hosted LLM gateway audit station: model fingerprint attribution, cache/tool/web/thinking evidence, IQ and integrity scores.
0,5/gün ort. +0 son gün — commit Go 30 Eyl 2026 güncellendi 19 gün önce - 9
Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes
0,3/gün ort. +0 son gün — commit Python 09 May 2026 güncellendi 10 Eyl 2026 - 10
Paste the text you would put in an AI bot's profile. Get back what is already there and the lines that are missing.
0,2/gün ort. +0 son gün — commit HTML 06 Eyl 2026 güncellendi 14 Eyl 2026 - 11
Hermes Agent-focused architecture and runtime health checks
0,2/gün ort. +0 son gün — commit Python 24 Nis 2026 güncellendi 16 May 2026 - 12
Provena : Context governance for agentic AI — tamper-evident audit trails, provenance validation, EU AI Act compliance. 6 framework adapters
0,2/gün ort. +0 son gün — commit Python 15 Tem 2026 güncellendi 5 gün önce - 13
Enterprise AI traffic gateway — unified compliance, routing across 20+ LLM providers, semantic cache, quotas, and audit. SDK / network / OS-
0,2/gün ort. +0 son gün — commit Go 26 May 2026 güncellendi 09 Eyl 2026 - 14
Live audit log of every command, file, and network connection a Claude Code (or any matched) session makes, from the kernel.
0,1/gün ort. +0 son gün — commit C 01 Haz 2026 güncellendi 16 gün önce