Havuz

Autonomous development for real products. Governed agents build from specs you approve, follow the rules you set, and nothing merges until a

Reverify, AI agent’larının reverse engineering ve kod doğrulama iddialarını deterministik araçlarla sınayan, CLI ve MCP server sunan bir Python aracıdır.

Neden yükseliyor · Repo yalnızca 28 günlük olmasına rağmen 1.245 yıldıza ve son 28 günde 83 commit’e ulaşmış; AI agent’ları için doğrulanabilir çıktı ihtiyacıyla MCP entegrasyonu dikkat çekmiş olabilir. Dört farklı yazarın katkısı aktiviteyi destekliyor, ancak yıldızlar tek başına benimseme veya kalite kanıtı değil.

Open memory & reliability layer for AI agents + independent judging/verification (NACRE judge, caliber-bench meta-benchmark, preregistered c

Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence

From ticket to reviewed pull request. Free and open-source, on your machine.

Stop hooks that stop AI coding agents (Claude Code, Codex) from claiming "done" without proof. A Lean quality system: every defect becomes a

Agents can work. They cannot declare success. A governed coordination protocol for multi-agent AI work: eight contracts (task, resource, own

Agent workflow for deadline-bound execution with evidence gates

Typed judgment tools for MCP agents. TypeSafe's Jev model as verify, screen, find, classify, rerank, decide, compare, extract, review, gate,

Your coding agent says done. Show the receipt. Evidence-first workflows, practical skills, and plugins for Claude Code and Codex.

Automated Proof-of-Carrying Change Management for AIOps 2026

an implementation of the ideas in Erik Meijer's "Guardians of the Agents: Formal Verification of AI Workflows" (Communications of the ACM, J

verification toolchain for TypeScript (Tech Preview)

Covert Coder — a local-first sovereign AI development environment for governed models, workflows, execution, evidence, and verification.

Verifiable AI coding agent harness / 可验证的 AI 编码代理：evidence hash-chain · hollow-answer gate · manual verification checklist · 6 engines + MCP

a DSL that blocks AI mistakes via proof

From any API surface to verified AI agent tools: Go CLI + MCP + skills + SQLite + policy + proofs.

Overnight experiment: can an AI agent make money, and can you trust what it reports? The agent produces claims; a separate verifier it canno

The orchestration layer under your coding agent. Turns work into a typed graph, runs one model per node, and takes the verdict from outside

AI-Native Formal Specification Language — a bounded model checker (Lark + Z3) built for LLM write/verify/repair loops.

"make", but for correctness claims. Decides when a coding agent's work is actually done, and un-decides it when you edit the code.

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

Claude Code / Codex CLI skill that scaffolds a runnable UVM testbench (APB / AHB-Lite / AXI4-Lite + generic-bus fallback) from an IP spec

Catalogue of languages designed for Agents

The Fable Method: a structured problem-solving loop that gives any model Fable 5 grade thinking. Four Hermes Agent skills (think/act/prove/g

A polygraph for your state machine: an LLM derives a formal model from your code, then Polygraph replays real traces against it and exhausti

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

Based on lectures on the LLM-Verifier Interface at the Summer School on Foundations of Programming and Software Systems (FoPSS 2026)

Chinese template for designing Multica multi-agent + skill workflows around task type, budget, models, and verification gates.

For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI