Reverify

A local AI verification toolkit checks binary claims and Python or C rewrites against evidence, with a CLI and MCP server under the MIT license.

Reverify helps developers and reverse engineers check AI-generated claims against actual binary files and code behavior. It returns verified, refuted or inconclusive verdicts with evidence, so an assistant's proposed explanation can be checked before you rely on it.

Binary verification: Check bytes, instructions, imports, patterns and emulated behavior in PE, ELF and Mach-O files, with disassembly support for x86, x64, ARM and ARM64.
Code comparisons: Compare a Python or C rewrite with a reference implementation over shared inputs; when outputs differ, the result includes the failing input and both outputs.
Session handoffs: Pass a long task to a fresh session through a handoff file in Claude Code, Codex, Gemini CLI or OpenCode.
Coding assistant integration: Give Claude Code, Cursor and other compatible agents access to verification tools through an MCP server, or use the standalone CLI.

The local toolkit is open source under the MIT license and has a pure-Python core. Optional engines include Capstone for disassembly, Unicorn for CPU emulation, LIEF for binary parsing and Z3 for proofs. Optional angr analysis adds function boundaries, call graphs and cross-references.

Code comparisons establish agreement over the inputs tested. Binary checks can return an inconclusive verdict when they can't establish or refute a claim.

Agent Memory MCP Servers and Agent Skills Guardrails, Security and Sandboxing LLM Evaluation and Testing macOS Windows Linux Code execution Guardrails MCP OpenAI-compatible API Persistent memory Resumable workflows Tool calling

Nobody has claimed Reverify yet

Work on Reverify? Claim this page and we'll verify you by hand. Reverify gets the verified checkmark, and you can upgrade the listing.

Want more people to find it? Promote it

Something wrong or outdated on this page?

Videos about Reverify

View all Reverify videos

Reef and local AI tools: GitHub project roundup

Similar to Reverify

View all tools

Cua

2 videos

An AI agent toolkit for desktop automation, local virtual machines on Apple Silicon, and computer-use evaluation, with MIT-licensed core tools.

30KUpdated 1 day agoMIT

macOS · Windows · Linux#Code execution#MCP#Tool calling

Cua supplies desktops and automation tools for developers building AI agents that operate native apps and browsers. You bring your own agent and model; Cua provides the computer environment and ways to interact with it.

Computer and Browser AgentsGuardrails, Security and SandboxingLLM Evaluation and TestingLLM Libraries and SDKsMCP Servers and Agent Skills

ECC

2 videos

An MIT-licensed coding assistant toolkit with local Markdown memory, testing and review workflows, and support for self-hosted model endpoints.

281.6KUpdated 2 days agoMIT

Windows#Guardrails#MCP#Multi-agent workflows

ECC adds reusable engineering workflows to AI coding assistants. It's for developers who want editable plans, test-first development and separate review contexts across sessions.

Agent MemoryAI Code ReviewGuardrails, Security and SandboxingMCP Servers and Agent Skills

Agno

3 videos

A self-hosted Python AI agent framework and runtime that serves agents through REST and MCP, with database storage and a web control plane.

42.8KUpdated 1 day agoApache-2.0

Docker · Web#Guardrails#Human approval#LLM tracing

Agno is a framework and runtime for developers building customer-facing or internal AI agents. It combines agent development, service hosting and a web interface for managing runs on infrastructure you control.

Agent FrameworksGuardrails, Security and SandboxingLLM Evaluation and TestingLLM Observability and TracingMCP Servers and Agent Skills

Hypha

A self-hosted TypeScript AI agent framework provides policy-controlled tool use, recoverable workflows and local storage adapters under Apache 2.0.

447Updated 1 month agoApache-2.0

#Agent Skills#Code execution#Guardrails

Hypha is a TypeScript AI agent framework for developers building applications that need controlled tool use and recoverable work. It separates an agent's planning and tool choices from the execution layer that decides which actions may proceed.

Agent FrameworksAgent MemoryGuardrails, Security and SandboxingLLM Evaluation and TestingLLM Observability and Tracing

Semantica

3 videos

An MIT-licensed Python toolkit for AI context graphs, with source-linked decision records, rule-based reasoning and agent framework integrations.

14.1KUpdated 2 days agoMIT

Docker · Web#Guardrails#Hybrid search#Knowledge graphs

Semantica is a Python toolkit for teams building AI systems that need shared context, traceable decisions and policy checks. It connects facts and decisions to their evidence in queryable knowledge graphs.

Agent MemoryGuardrails, Security and SandboxingLLM Observability and TracingMCP Servers and Agent SkillsRAG Frameworks and Pipelines

Nox

A local security scanner for AI apps and MCP servers that checks prompt injection and agent permissions, with offline analysis under Apache 2.0.

11Updated 6 days agoApache-2.0

#AI red teaming#Git integration#MCP

Nox is a security scanner for developers building LLM applications, RAG systems and agents with tool access. It traces untrusted input into model calls and model output into dangerous operations, including paths across functions and files.

Guardrails, Security and SandboxingLLM Evaluation and TestingMCP Servers and Agent Skills