Havuz

iFixAi, AI agent’ları yapılandırılabilir testler ve model judge’larıyla denetleyip puan kartı ve raporlar üreten bir Python aracıdır.

Neden yükseliyor · 153 günlük bir depoda 15.702 yıldız ve son 28 günde 9 commit ile 5 farklı yazar görünmesi güçlü ilgiye ve devam eden katkıya işaret ediyor. README’de birden fazla kullanım yolu ve agent ekosistemi entegrasyonları öne çıkarılıyor; ancak yıldızlar ürün kalitesini veya değerlendirmelerin doğruluğunu kanıtlamaz.

mu, coding agent kararlarının bir kısmını küçük bir judge modeline devrederek pi tabanlı CLI ve desktop agent sunar.

Neden yükseliyor · 14 günlük yaşına rağmen 386 yıldız, son 28 günde 731 commit ve 11 farklı yazar raporlanıyor; bu kısa sürede dikkat ve geliştirme hareketliliğine işaret ediyor. Ancak bu veriler kalıcı benimseme veya üretim olgunluğunu tek başına kanıtlamıyor.

ADR, AI agent’ları keşfetmek, etkinliklerini gözlemlemek ve riskli davranışları tespit etmek için araçlar ile benchmark’lar sunan açık kaynaklı bir güvenlik sistemidir.

Neden yükseliyor · AI agent güvenliği güncel ve kurumsal ölçekte büyüyen bir ihtiyaç; Uber’in projeyi açık kaynak olarak yayımlaması, README’de üretimde kullanıldığını ve MLSys 2026’da kabul edilen bir makaleyle desteklendiğini belirtmesi ilgiyi artırıyor. 167 günde 1.620 yıldızın yanı sıra son 28 gündeki 44 commit ve 15 farklı yazar, kayda değer proje etkinliğine işaret ediyor; ancak yıldız geçmişi olmadan yükseliş hızını doğrulamak mümkün değil.

9Router — Pro edition of 9Router with Prompt Injection (system prompt or chat script per global / API key / model), per-key token quotas, ac

AI Agent Identity and Access Management and Inference Firewall

Open-source runtime AI agent security tool - monitors and controls AI agents, catching malicious tool use, prompt injection, and policy drif

Open-source adversary emulation for AI agents and MCP servers.

Deterministic safety solutions for probabilistic AI agents

Engineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, m

Chinese-first LLM jailbreak benchmark & red-team toolkit | 中文LLM安全评测框架 | by POJIA.AI

rook by TestMu AI: Agent Assurance from the terminal. Test how your AI agents actually behave across workflows, tools, and actions, and catc

Agent-ergonomic CLI for TypeSafe's Jev: fast calibrated judgments (pick, rate, check, rank, triage, guard) from the shell

Security scanner for MCP servers, source trees, and packages, with explicit findings and coverage reporting.

Alignment-research scaffold (autoresearch-style) for LLM guardrails: search over a single policy.md surface

🛡️ Regex catches 0%, Meta's Prompt Guard 2 catches 1% of 629 realistic AgentDojo injection attacks when they're buried in tool output. Repro

Benchmarking repository-borne prompt injection attacks and lightweight defenses for local coding agents. DL4C @ ICML 2026.

Agents propose. People approve. Change control for AI agents: everyday work runs on its own, anything an agent can't take back waits for a t

Soup Wall: open-source security for AI agents and model traffic. Local Agent, Gateway, self-hosted Console. Apache-2.0.

Command-line tool for TypeSafe's Jev AI model

Adversarial security testing for AI agents — prompt injection, tool misuse, memory poisoning, and MCP scanning, with CI-ready regression tes

A modular, drop-in middleware collection for Laravel AI SDK agents. Offers middleware across security, observability, performance and guidan

🦞 Local, read-only security audit for your OpenClaw agent. Finds config, prompt-injection and supply-chain risks, watches for drift, and ve

Self-hosted personal AI agent with a WebUI, memory, tools, MCP, sub-agents and automations. Connect local or cloud LLMs.

Self-hosted LLM security proxy. PII redaction, prompt injection defense, KVKK/GDPR/PCI-DSS compliance. Sub-millisecond latency

Find known secrets in your AI coding agent sessions (Claude Code, Codex, Cursor), then guard the next one with local hooks that trace risky

Prompt-injection, jailbreak and secret-leak defense for DeepSeek Harness: Aho-Corasick detection with allow/ask/block interception and sanit

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

Auto-permission engine for Antigravity CLI (agy): deterministic AST parser + LLM classifier

Skill router and prompt-injection firewall for AI coding agents: gives Claude Code, Codex and Cursor the few skills, MCP servers and tools e

[ACL 2026] PIArena: A Platform for Prompt Injection Evaluation

Red-team your RAG pipeline for prompt injection, source-document leakage, and cross-document smuggling, in CI. The gap between RAG eval (RAG

Self-hosted AI security proxy. Redact PII, block prompt injection, route to any LLM provider. OpenAI-compatible.

A terminal-based, multi-domain support-ticket triage agent grounded in a local support corpus.

Document extraction and validation for logistics companies.

Evidence-grounded evaluation for AI agents — verifies each claim against the agent's real tool outputs (constrained, evidence-grounded model

Crash-test insurance claim AI agents before production.

Deterministic security analysis for agent skill files.

Static security scanner for npm/PyPI packages, MCP servers, agent skills and repos. Runs locally, never runs the code, no LLM. CLI, Claude C

Safety benchmark for personal AI agents under realistic prompt injection. 120 test cases across 5 professional domains, 3 injection vectors,

Zero-Trust Semantic Scraper & Firewall Proxy for AI Coding Agents. Intercepts and neutralizes web-scraped prompt injections locally before t

Self-hosted LLM gateway that turns flat-rate AI subscriptions (Claude Code Max, ChatGPT Plus, Codex, Copilot, M365, Gemini) into one OpenAI/