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
Open-source antivirus and firewall for AI agents: block risky tools, secret access, prompt injection, malicious packages, MCP servers, plugi
4,8/gün ort. +7 son gün +7,7 son 7g 3.148 commit 6 yazar Python 28 Mar 2026 güncellendi dün - 2
OWASP MCP Security Testing Guide
0,4/gün ort. +2 son gün +1,1 son 7g — commit 01 Haz 2026 güncellendi 19 gün önce - 3
Authority control plane for autonomous work. EMILIA Gate enforces finite customer-owned mandates at protected executor boundaries; the open
2,6/gün ort. +0 son gün +0,4 son 7g 159 commit 4 yazar TypeScript 13 Mar 2026 güncellendi 2 gün önce - 4
Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drif
3,4/gün ort. +1 son gün +0,4 son 7g 1 commit 1 yazar Python 11 May 2026 güncellendi 13 gün önce - 5
Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential con
3,2/gün ort. +0 son gün +0,1 son 7g 0 commit 0 yazar Rust 17 Mar 2026 güncellendi 18 May 2026 - 6
Cross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memor
1,7/gün ort. +0 son gün +0,1 son 7g 3 commit 1 yazar JavaScript 18 Mar 2026 güncellendi 3 gün önce - 7
OAuth 2.1 Authorization Server for the Model Context Protocol (MCP)
0,6/gün ort. +0 son gün +0,1 son 7g — commit Go 11 Haz 2026 güncellendi 9 gün önce - 8
reconnaissance for agent attack surfaces
0,5/gün ort. +0 son gün +0,1 son 7g — commit Go 26 Tem 2026 güncellendi 26 Eyl 2026 - 9
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 +0,1 son 7g — commit Python 31 Mar 2026 güncellendi 5 gün önce - 10
The Project shares all information on MCP related CVE's published
0,2/gün ort. +0 son gün +0,1 son 7g — commit 07 May 2026 güncellendi 29 Eyl 2026 - 11
An OWASP-aligned intentionally vulnerable platform for learning and testing AI, LLM, RAG, MCP, and Agentic AI security.
0,2/gün ort. +0 son gün +0,1 son 7g — commit TypeScript 04 Haz 2026 güncellendi 10 Haz 2026 - 12
Open-source runtime security and execution control for autonomous AI agents. ALLOW, BLOCK, ESCALATE at the execution boundary with auditable
0,2/gün ort. +0 son gün +0,1 son 7g — commit Python 28 Tem 2026 güncellendi 3 gün önce - 13
Screens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a clien
0,5/gün ort. +0 son gün +0,1 son 7g — commit TypeScript 18 Eyl 2026 güncellendi 13 gün önce - 14
Open-source config scanner for AI coding agents: scores the permissions, hooks, sandbox and MCP settings of Claude Code, Codex, Cursor and G
0,1/gün ort. +1 son gün +0,1 son 7g — commit Rust 09 May 2026 güncellendi dün - 15
Static security scanner for npm/PyPI packages, MCP servers, agent skills and repos. Runs locally, never runs the code, no LLM. CLI, Claude C
0,1/gün ort. +0 son gün +0,1 son 7g — commit Python 07 Haz 2026 güncellendi dün - 16
Self-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards
3,8/gün ort. +0 son gün +0 son 7g 18 commit 1 yazar Rust 02 Nis 2026 güncellendi dün - 17
Agyn is an open-source Kubernetes-native runtime that moves AI agents like Claude Code and Codex from laptops to company infrastructure with
1,3/gün ort. +0 son gün +0 son 7g 0 commit 0 yazar TypeScript 05 May 2026 güncellendi 19 Eyl 2026 - 18
AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源
0,6/gün ort. +0 son gün +0 son 7g — commit TypeScript 12 Mar 2026 güncellendi 29 Eyl 2026 - 19
Free, MIT-licensed MCP security testing from ClearFrame. Scan, audit, compare, and review locally; continue in the ClearFrame CLI or Mac app
0,6/gün ort. +0 son gün +0 son 7g — commit TypeScript 19 Mar 2026 güncellendi 3 gün önce - 20
A practical governance framework for organizations adopting the Model Context Protocol (MCP), the open standard that lets AI agents connect
0,9/gün ort. +0 son gün +0 son 7g — commit 24 Tem 2026 güncellendi 08 Eyl 2026 - 21
Public SDKs and integration contracts for Armorer Guard.
0,2/gün ort. +0 son gün +0 son 7g — commit Python 12 Nis 2026 güncellendi 10 gün önce - 22
Cryptographic trust and authorization evidence for AI agents. Every action a receipt, every grant a proof.
0,2/gün ort. +0 son gün +0 son 7g — commit Rust 29 Mar 2026 güncellendi 24 Eyl 2026 - 23
AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.
0,1/gün ort. +0 son gün +0 son 7g — commit Python 14 Nis 2026 güncellendi 3 gün önce - 24
Open-source AI security platform providing perimeter defense for LLMs and AI agents through swarm analysis, policy enforcement, adversarial
0,2/gün ort. +0 son gün +0 son 7g — commit TypeScript 18 Haz 2026 güncellendi 2 gün önce - 25
Python SDK for accurate and verifiable agent tool use. Agents verify that answers came from the right source and were not changed. Downstrea
0,1/gün ort. +0 son gün +0 son 7g — commit Python 27 Nis 2026 güncellendi 7 gün önce - 26
MCP server exposing WinDbg/DbgEng (live user-mode, kernel, crash dumps, Time Travel Debugging) to AI agents over stdio or over HTTP with --l
0,1/gün ort. +0 son gün +0 son 7g — commit Rust 30 May 2026 güncellendi dün - 27
Open-source AI gateway for LLM and agent traffic — multi-provider routing, guardrails, semantic caching and MCP support. Written in Go.
0,1/gün ort. +0 son gün +0 son 7g — commit Go 26 May 2026 güncellendi dün - 28
Stateless governance proxy for MCP (2026-07-28): policy, dry-run, human confirmation, audit, tracing
0,3/gün ort. +0 son gün +0 son 7g — commit Python 13 Eyl 2026 güncellendi 4 gün önce - 29
BrokenMCP is a vulnerable implementation of the Model Context Protocol (MCP) for educational purposes.
0,2/gün ort. +0 son gün +0 son 7g — commit Python 14 Ağu 2026 güncellendi 17 Ağu 2026 - 30
MCP gateway with GraphQL tool aggregation
0,1/gün ort. +0 son gün +0 son 7g — commit Rust 19 Tem 2026 güncellendi 19 Eyl 2026 - 31
Sandboxed multi-scanner security for AI skills, MCP servers, and package trees — coverage honesty, SIE judging, heatmap posture, guided tria
0,1/gün ort. +0 son gün +0 son 7g — commit Python 01 Ağu 2026 güncellendi dün - 32
MCP security scanner & config linter for AI coding agents. Finds leaked secrets, risky commands, broad permissions and invalid MCP servers i
0,7/gün ort. +0 son gün +0 son 4g — commit TypeScript 14 Eki 2026 güncellendi dün - 33
Open-source local MCP runtime that checks AI-agent tool calls, gates risky actions on approval, verifies results, and avoids blind retries a
0,1/gün ort. +0 son gün +0 son 4g — commit TypeScript 28 Tem 2026 güncellendi 3 gün önce - 34
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, red-flag patterns, ref
0,2/gün ort. +0 son gün -0,1 son 7g — commit Shell 30 Nis 2026 güncellendi 30 Nis 2026 - 35
The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, a
0,5/gün ort. +0 son gün -0,3 son 7g — commit Python 25 Nis 2026 güncellendi 3 gün önce