reverify
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
- stars
- 1,226
- 30-day movement
- +14749/day
- Related entries
- 60
- Connections
- 1
reverify is a Python tool, shipped as both an MCP server and a CLI, that verifies claims made by AI agents against ground truth using deterministic tools, with evidence attached to each check. It is oriented toward reverse engineering work — binary analysis, disassembly, CTF and malware analysis — and keeps grounded facts and context available across agent resets.
Reach for it when an LLM-driven agent proposes conclusions in reverse-engineering tasks and you want deterministic verification rather than trusting the model's output.
Use it to
- Verify agent claims against ground truth with evidence
- Run as an MCP server alongside an LLM agent
- Assist binary analysis and disassembly workflows
- Support CTF or malware-analysis sessions with grounded context
- Persist verified facts across agent context resets
For Developers building AI agents for reverse engineering and security work
- Role
- agent-app
- Language
- Python
- Licence
- MIT
- Forks
- 239
- Open issues
- 5
- Last push
- 2026-09-07
- Latest release
- v0.1.0 · 2026-09-02