Havuz

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

✅ Acceptance is open-source e2e testing for Agents. Your coding agent turns a prompt into observable checks, runs the real product, and publ

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

TLA+ model checking and Lean proofs for coding agents, with explicit tool setup.

Builds up to a goal in a field you have no expertise in: splits it into the foundations that goal actually needs, mobilizes what you already

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.

verification toolchain for TypeScript (Tech Preview)

An operating harness for repositories maintained by AI coding agents. Memory hierarchy, verification ladder and reusable workflows.

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

Neuro-symbolic agents with verified memory. MCP math tools, an algebra repair Skill, and an open challenge. Verify solutions, learn checked

Governed execution layer for AI coding assistants: clarify intent, route capabilities, review evidence, verify results, and write back lesso

An SDK for verifiable intent, inline with code: one-line claims above your functions, verified at the rigor you choose and flagged when they

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

An open standard for agent-native software requirements.

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

Fable-style verification gate for Claude Code: don't say done until it's verified. Port of the Codex plugin by Agent Korea (플라잉따릉이).

A pipeline of Agent Skills that run the full SDLC — requirements to deployment, then a per-feature design→build→verify loop — as one pipelin

Evidence-gated Claude and Codex council orchestration.

Catalogue of languages designed for Agents

Catch your AI agents when they lie about what they shipped — verifies claims against git instead of believing the agent.

Evidence-backed proof of done for Claude Code, Codex, Cursor, and other AI coding agents. Run real checks, bind results to current Git state

a DSL that blocks AI mistakes via proof

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

Interactive physics & CAE simulators. 1600+ educational tools with live demos at https://novasolver.jp

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

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

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

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

22 production-grade skills for AI coding agents — setup, scope, discipline, code review, security, session management, governance, ops, and

OpenCode++: a Coding Agent Reliability Harness for OpenCode, adding context, edit boundaries, command evidence, verification gates, impact 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

RobloxForge Docs 2026: Official MCP Vertical Slice Verification Layer for Studio

Give any AI agent a disposable email inbox in one tool call. MCP server for email verification, auth flows, and testing.

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

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

Codex harness for consistent AI-assisted development workflows, including agent instructions, standard setup/check/test/eval scripts, CI,

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

Audits AUR PKGBUILD updates before you install: detects structural changes, suspicious commands, typosquatting, and novelty signals, then pr

Minimal Ed25519-signed activity receipts for verifiable AI agents — self-attested, offline-verifiable, no blockchain.

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

Fast, deterministic verifier and gate for AI agents: exact math, claim and citation checks, shell/write policy, hash-chained step ledger and

Click does not replace Nx, Bazel, pytest, or Jest. It sits above existing verification tools and manages which verification evidence remains

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

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

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

Verify that an AI agent's on-chain claims are actually true. A claim-level groundedness checker for Solana / memecoin agents.

Fable-inspired verification-first workflow skill for Codex

A living standard for a web stack that AI agents can verify, not just generate

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