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.

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

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

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

Agentlens is a trusted agent trading platform. Here, you can quickly find the Agent that meets your needs, and you can also publish your ow

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

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

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

Delta MCP is a free app that sits between your AI apps and their MCP servers: any server, every tool. It checks each task before it runs, ap

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

Dyno Lab — an AI safety, alignment and interpretability research workbench for Apple Silicon. Explore activations, probes, SAEs and interven

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

AI Initiative Ledger — local spend meter and budget gate for AI tasks. Meters every vendor leg (LLM, speech, telephony, search, tools), hard

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

Universal AI Charter: plain-language governance principles and a public certification registry for AI models, built on disclosure instead of

Evidence validation and policy engine for AI-assisted biological curation

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

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

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

👾 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

Govern: one Decionis verdict before a workflow step runs — a deploy, a migration, an infrastructure change, an agent's action — with a signe

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

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

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

Context bomb strings

Agent Execution Partnership AEE is an open-source control plane that ensures every AI agent action is authorized before it runs, observable

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

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

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

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

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

Illustrated comic-style cheat sheets for ML, LLMs, AI safety, LeetCode and Git, plus a SwiftUI study app (Panels) to read them and quiz your

Code review via the change impact measure

An open-source engineering governance standard defining trust boundaries for conversational AI agents in high-stakes domains. MIT Licensed.

GateMem: a benchmark and evaluation toolkit for memory governance in multi-principal shared-memory LLM agents.

Behavioral testing for AI agents.

AgentGuard: Zero-Trust Security Foundation for AI Agents

Kernel-enforced authority and spend platform for AI agents

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

Subagent Verification for Claude AI Code Networks 2026

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

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

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

Automated Proof-of-Carrying Change Management for AIOps 2026

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

Open-source governance and hard gates for AI coding agents across Claude Code, Codex CLI, and Pi.

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

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

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

⚡ Millisecond System-1 judgement for every tool call in DeepSeek Harness — Jev-powered risk classification & evidence-gated auto-approval. F