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.

mutual layer for multiple agents from different environment or providers to work on same interface or device, toward the same final goal

A Hub/research area, for jailbreaking LLM's, and breaking their safety filters.

A clinical decision-evidence benchmark: pull the one fact an answer rests on, and see whether the assistant's action moves with the evidence

Tamper-evident tracing, policy gates and cross-checks for AI agents: see what the agent did, and why.

An AI that administers Linux through typed, approval-gated, Ed25519-audited actions. The model selects the action; the daemon builds the com

Open-source AI security verification for model artifacts, live endpoints, MCP servers, and recorded agent traces. Reproducible evidence for

A really fast and lightweight harness for AI agents

Protecting digital communications against audio deepfakes with real-time AI. This system analyzes audio streams to detect synthesized voices

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

A structured, versioned archive of adversarial prompt engineering techniques against Large Language Models — for AI safety research, red-tea

A modular threat detection library for AI and LLM pipelines. It provides language-agnostic guardrails through a configurable pipeline of loa

Context bomb strings

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

Enterprise Zero-Trust AI Security & Governance Gateway: Real-Time Prompt Injection Defense, Action Scoping, HITL Approvals, Post-Quantum Mer

A senior microsoldering technician, available to every repair shop from the seasoned pro to the apprentice. Powered by Claude Opus 5

Second-model AI auto-review for DeepSeek Harness approval requests: a read-only reviewer subagent returns structured allow/deny verdicts wit

Curated archive of jailbreak and prompt-injection experiments for AI model robustness research, red-teaming, and defensive evaluation.

Turn Android Termux into an autonomous AI agent and security orchestrator. Powered by a local ReAct framework with 50 system tools and MCP s

Agent skill for deepfake detection & media safety — detect AI-generated audio, images, and video with Resemble AI

Local-first verification layer for AI agents: evidence, provenance, policy gates, human approval, and auditable Trust Receipts before a clai

A custom coding harness for TypeSafe AI's Jev: an LLM proposes, Jev answers narrow questions, code decides, every step leaves a receipt.

Open-source test harness for AI agents. Stress-test production agents with adversarial multi-turn scenarios in CI

👾 下一代透明智能体架构 | Next-Gen Transparent Agent Architecture 🔍 全行为审计 | 🛡️ 两段式安全调用 | 🧠 双水位记忆 | ⏰ 心跳任务 📊 P0 级事故率降低 80% | 兼容 OpenClaw + Claude Code 技

A Geiger counter for AI agents — one read-only command that inventories every agent, MCP server, plugin, and AI extension on a machine

AI 执行与监察体系（Agent Oversight Framework）：分层治理规范 + L2 运行时监察参照实现——证据分级、自校正、边界诚实。A layered governance spec for AI agents, plus a runnable referenc

Myrtia — agent-native red teaming for LLMs and AI agents: a deliberating council of attacker models (propose, cross-critique, Borda vote, ch

Audit any agent decision across its past, present, and future, on one typed graph.

An open database of real-world AI agent incidents.

Tactical Identity Operator for Linux & Hybrid Active Directory

Your AI's guard dog. Doberman sits at runtime, gating every input, output and tool call to stop unsafe or unintended actions before they exe

One config to rule all your AI agents: portable (every project, every session), effective (curated writing, routing, skills), and safer (des

AgentGuard: Zero-Trust Security Foundation for AI Agents

Free local guardrail for AI coding agents: every tool_call judged on-device (regex + Laya), allow/review/block

Parent-operated starter kit for designing a private, child-facing Hermes Agent profile

Open-source MCP control plane for AI coding agents: mechanical time-locks, evidence-gated proof receipts, red-team remediation, and persiste

Run coding agents without babysitting them. Keep jobs focused, bounded, checked and accountable from start to finish. Finally run your agent

Stop AI agents from doing things they shouldn't. The action authorization layer — pre-execution, deterministic, policies included. Drop in.

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, go

Runtime enforcement boundary for AI agents: a local sidecar that gates every outbound call against Cedar policies you own. Deterministic, ca

Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with tool-name, argument (glob/regex), and

An orchestration runtime for multi-agent AI systems. Declare agents, tools, and policies as YAML; Orloj schedules, executes, routes, and gov

Deterministic telemetry & control plane for multi-agent AI systems. Atomic POSIX JSONL event bus, W3C/OpenTelemetry DAG reconstruction, and

Behavioral testing for AI agents.

Code review via the change impact measure

The vendor-neutral protocol for AI agent safety & security — and the neutral benchmark that ranks the vendors.

sofagent is an open-source FDE Harness for AI coding agents — on entry, write your business judgment into files (workflows, ontology, AI nod

Open-source AI model evaluation and benchmarking framework for LLMs (OpenAI, Ollama, Claude, Gemini)

Verify what AI coding agents can actually read, write, execute and reach using synthetic canaries.

RLCDAlignBench: 44 alignment-failure detection benchmarks and code for 'Just Ask Jev' (RLCD zero-shot detector of AI alignment failures)