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

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

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

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

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

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

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

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

Code review via the change impact measure

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

Behavioral testing for AI agents.

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

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

Automated Proof-of-Carrying Change Management for AIOps 2026

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

A benchmark for AI agents as teammates. Paper: https://arxiv.org/abs/2611.02633

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

An unattended maintainer for one repository. It reviews, files, prunes, and merges only against proof that a guard bites.

State-Aware Collaboration Protocol: auditable work receipts for AI agents.

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

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

A Socratic supervision layer for AI coding agents.

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

Humanlike — deterministic persona, context, memory and privacy controls for conversational AI agents · Детерминированное поведение ИИ-агенто

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

Monitoring & Safety layer for all your agents. Open Source CLI & Skills for Claude Code, Codex, Cursor, Jev and your preferred agents.

Six skills tell coding agents how to work. Two guards enforce the parts that should not depend on judgment.

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

Paste a URL, find out something true about the site. Three URL-only readings on one page: Slopmeter scores how much of it is still the templ

🔐 The local-only AI secret manager for the AI-coding era with MCP, CLI, Web UI, TUI, Chrome Extension and Mobile App. No cloud, No telemetry

AI agents now operate with authority. Authority without discipline is how complex systems fail. Nuclear’s control loop, ported to AI-assiste

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

Real-time web dashboard for AI-agent behavior monitoring, built on Perplexity's Numbat. Zero-dependency Python.

Guardrails for AI coding agents — block catastrophic tool calls before they run. Semantic, agent-neutral, near-zero false positives.

Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid STS + NLI. Works with LangChain, LlamaIndex

Tamper-evident evidence and verification layer for AI agents. Verify any agent's session offline with just openssl. No cloud, no lock-in.

Diagnosing policy grounding in LLM judges via causal erasure. Companion code to the AIES 2026 submission READ.

Lightweight RAG provenance middleware. Verifies every claim in an LLM response is grounded in a retrieved source - without an LLM call.

Streaming privacy for LLM apps: pii-leak-benchmark (does your gateway leak PII in streams?), chunk-invariance (one-line test for split-bound

A police department for your Claude Code agents — a logging-only hook + CLI that audits the main agent and every subagent and reports rule o

A structured workflow system for AI coding agents - harness engineering, execution loop, skills, hooks, and a learning loop. Works with Clau

Code-First AI Compliance. The open-source regulatory engine for the EU AI Act. Automate your risk assessments directly within your CI/CD pip

A small, vetted, self-evolving harness for Claude Code — curated, not dumped. Skills, safety guards, and a self-improvement loop.

Decomposing and measuring evaluation awareness in existing benchmarks and our proposed EvalAwareBench.

Session-layer circuit breaker for LLM & agent traffic — a transparent streaming proxy that meters every session and kills the one that goes

📜🦀🌐 Intelligent, Secure and Effortless Super Full-Stack Framework 🌐🦀📜"Rust for those who want to build securely and easily, but not suffer"

CatchBench: a benchmark for auditing agent failures across the full lifecycle.

最系统的AI全栈学习实战手册