Havuz

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.

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

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

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

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

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

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

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

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 open standard for agent-native software requirements.

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

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

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

Check that source map mappings actually point where they claim — token-level verification, not just valid JSON.

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

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

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

Redpen makes coding agents prove they are actually done.

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

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

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

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

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

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

AI agents should not make irreversible changes. TraceFold escrows the inverse before an effect lands, or refuses it, and issues receipts any

"Done" means nothing — a menhera-style completion gate for Claude Code that blocks empty completion claims until tests actually ran green an

Fable-inspired verification-first workflow skill for Codex

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

Bounded loops for coding agents: test gates, held-out acceptance checks, hard stops, git-backed resume

A local verification receipt for AI coding agents

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

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

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

Proof-of-done for AI coding agents. Local evidence receipts for Codex, Claude Code, Cursor, and GitHub Actions.

A self-correcting system of nested engineering loops: plan & execute repo work; safely implement audit findings; design greenfield & improve

🛡️ An open-source trust verification CLI to validate and verify real-world claims with @openapi®.

Gatemole compiles human-owned intent into obligations, links evidence artifacts to those obligations, and produces deterministic release dec

A small, file-first verification harness that turns an AI agent's "I'm done" claim into an auditable admission decision. 100% offline & zero