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
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with defau
13,9/gün ort. +1 son gün — commit Rust 02 Eki 2026 güncellendi bugün - 2
Agentshield is open source defense for Kubernetes and AWS. It learns how your workloads really talk, flags lateral movement with evidence, a
3,6/gün ort. +0 son gün — commit Go 21 Eki 2026 güncellendi dün - 3
Open Source Agentic Security Scanner
2,6/gün ort. +0 son gün 3 commit 1 yazar Python 23 May 2026 güncellendi 21 gün önce - 4
A daily vulnerability briefing for AI-agent-managed machines — deterministic matching against OSV + CISA KEV; the LLM only explains. MIT
1,4/gün ort. +0 son gün — commit Python 25 Eki 2026 güncellendi 13 gün önce - 5
AgentGuard: Zero-Trust Security Foundation for AI Agents
1/gün ort. +1 son gün — commit Python 27 May 2026 güncellendi dün - 6
Research into flattening compaction strategics
0,8/gün ort. +0 son gün — commit Python 21 Eki 2026 güncellendi 16 gün önce - 7
A collection of public writeups on attacks against AI agents: prompt injection, tool abuse, memory poisoning, and data exfiltration.
0,6/gün ort. +0 son gün — commit 21 Ağu 2026 güncellendi 22 Ağu 2026 - 8
Tamper-evident audit trails for AI agents: hash-chained Runtime Records, dependency-free, verifiable by anyone.
0,6/gün ort. +0 son gün — commit Python 11 Haz 2026 güncellendi 6 gün önce - 9
AiGuard —— 本地优先的 AI 流量安全网关：本机 MITM 代理只接管 AI 域名，请求侧脱敏、响应侧流式还原，并识别七类风险信号。原文不落盘、不上传。（注意如果你需要模型直接使用token或者其他密钥进行操作，请放入白名单或关闭该功能！！！！）
0,3/gün ort. +0 son gün — commit Rust 14 Eyl 2026 güncellendi 6 gün önce - 10
Praxis Policy Engine (PPE)
0,2/gün ort. +0 son gün — commit Rust 03 Ağu 2026 güncellendi dün - 11
Sandboxed OCI container images for AI coding agents, built reproducibly with Nix.
0,2/gün ort. +0 son gün — commit Shell 15 Mar 2026 güncellendi dün - 12
The identity provider for AI agents — registry, scoped delegation, in-path MCP enforcement, instant revocation, tamper-evident audit.
0,2/gün ort. +0 son gün — commit Go 04 Tem 2026 güncellendi 21 Tem 2026 - 13
The autonomous pentester that proves its findings — AI-driven, evidence-first, behind-login.
0,2/gün ort. +0 son gün — commit TypeScript 12 Haz 2026 güncellendi 5 gün önce - 14
Kernel-enforced policy for coding agents (eBPF LSM). YAML in the repo; deny is EPERM. Claude gets Semantic feedback after deny.
0,2/gün ort. +0 son gün — commit C 24 Ağu 2026 güncellendi 09 Eyl 2026 - 15
Runtime visibility for Python MCP servers. Captures tool calls, session lifecycle, module imports (SHA-256), and subprocess execution as str
0,2/gün ort. +0 son gün — commit Python 31 Mar 2026 güncellendi 3 gün önce - 16
Empowers the AI to perform penetration testing, vulnerability assessment, reconnaissance, and security reporting — all through natural langu
0,2/gün ort. +2 son gün — commit Python 27 Haz 2026 güncellendi 3 gün önce - 17
Coral is an open-source, local-first session bridge that lets AI agents borrow a user's already-authenticated browser sessions on a per-site
0,2/gün ort. +0 son gün — commit Python 05 May 2026 güncellendi 19 gün önce - 18
StealthBench is a benchmark for evaluating whether autonomous agents operate with the operational security (OPSEC) discipline that separates
0,1/gün ort. +0 son gün — commit Python 27 Tem 2026 güncellendi bugün - 19
Open-source AI vulnerability discovery
0,1/gün ort. +0 son gün — commit TypeScript 23 Nis 2026 güncellendi 30 Haz 2026 - 20
An autonomous agentic pipeline that finds, proves, and patches real C memory-safety vulnerabilities end-to-end using a single 7B open-source
0,1/gün ort. +0 son gün — commit Jupyter Notebook 16 Haz 2026 güncellendi 16 Haz 2026 - 21
Public source of the Dreadnode capabilities in app.dreadnode.io — agents, tools, skills, MCP servers, and workers.
0,1/gün ort. +0 son gün — commit Python 04 May 2026 güncellendi 5 gün önce - 22
Red Team + Blue Team agents for Claude Code. Automated security auditing with ~100 lines of Markdown each.
0,1/gün ort. +0 son gün — commit 14 Nis 2026 güncellendi 14 Nis 2026 - 23
Runtime authorization for AI agents — Node.js SDK
0,1/gün ort. +0 son gün — commit TypeScript 04 Nis 2026 güncellendi 04 Nis 2026 - 24
A lightweight toolkit for building secure AI systems with built-in middleware, protected memory, and AI safety models that mitigate prompt i
0,1/gün ort. +0 son gün — commit Python 23 May 2026 güncellendi 27 gün önce - 25
CLI for reducing accidental secret disclosure in LLM coding sessions
0,1/gün ort. +0 son gün — commit TypeScript 03 Nis 2026 güncellendi bugün