DEDUPEDRea
A plug-in that lets your AI agent take apart an app and explain how a feature works.
5 use cases: Rebuild a feature you saw, in your own project; Map how a website's front end works; List modules and IPC in an Electron app · GitHub
Reverify
Reverify is a Python toolkit and MCP server where deterministic tools verify every AI claim about a binary or code before it counts as fact.
4 use cases: Check an AI's claims about a binary before trusting them; Test an AI's code rewrite against the original before merging; Stop a long AI coding session from losing grounded facts · GitHub
Ablation
Ablation is a self-contained reverse engineering framework that, when used with Codex or Claude Code, works as an autonomous reverse engineering system.
4 use cases: Trace network input to dangerous sinks in a binary; Scan an x86-64 ELF for heap and format string bugs; Map entry points and sinks in a source repository · GitHub
Claude AD
Claude-AD is a Claude Code plugin that gives Claude an Active Directory pentest method: skills, agents and slash commands for authorized internal assessments that drive standard tools such as netexec, impacket, certipy, bloodyAD and BloodHound CE.
4 use cases: Scope an AD assessment in the right phase order; Map low-privilege to Domain Admin attack paths; Review ADCS ESC1 through ESC17 misconfigurations · GitHub
Awesome Reverse Engineered
A searchable index of 12,869 open-source tools that were built by reverse engineering closed apps, APIs, devices, protocols, file formats, games and AI products.
4 use cases: Check for an existing tool before reverse engineering a device; Let Claude Code pick a tool for a task with no official API; Find a maintained emulator or client on the web index · GitHub
Seep Reverse Lab
Seep Reverse Lab is a Lua-based, agent-driven workbench that wraps reverse engineering tools (Radare2, JADX, Apktool, Frida) and runs CWE-602 client-side authorization audits.
4 use cases: Audit an app feature gate for CWE-602 authorization flaws; Map a Windows PE binary's protections and key functions; Map an APK's control flow without flooding the agent context · GitHub
Geiger
Geiger is a read-only, dependency-free command that inventories the AI agents, MCP servers, plugins, and AI extensions on a machine and labels what each one can execute, read, or reach.
5 use cases: See every AI agent and MCP server on a machine; Turn a scan into an HTML report with fix steps; Alert when a new executing or secret-holding agent appears · GitHub
Tracekit
Tracekit is a Python tool that gates each AI agent tool call before it runs, signs every call and decision into a tamper-evident hash chain, and lets anyone verify each run offline.
4 use cases: See a denied command and a tamper check in 5 seconds; Record every tool call of a Python agent run; Check a run file offline against a key you pinned · GitHub
Agent Safe Pipeline
AgentSafe is an open-source gateway that sits in front of an AI agent's or API's consequential HTTP requests, checks each one for authorization, and then forwards it once, holds it for a person, or refuses it, leaving chained evidence of each decision.
4 use cases: Test whether an agent can reach a payments API directly; Hold high-value API calls until a person approves them; Keep a chained record of every agent API action · GitHub
Prism Browser Community
Prism Browser Community is a local, open-source multi-profile fingerprint browser built on a customized Chromium and Electron.
4 use cases: Keep each of your own accounts in its own browser profile; Check how a profile scores on fingerprint test sites; Build the Chromium 144 fingerprint kernel on Windows · GitHub
X64 DBG MCP Server
A native Windows plugin for the x64dbg debugger that exposes its debugging functions as MCP tools over HTTP, so AI assistants can control the debugger.
3 use cases: Find the original entry point of a packed binary; Step through a live process with an AI assistant; Triage a binary by strings, patterns, and references · GitHub
MCP Audit Tool
A pure-Python command-line security scanner that audits MCP client configuration files for secrets, unpinned packages, risky launch commands, and tool poisoning indicators.
3 use cases: Find leaked keys and risky MCP servers on your machine; Block risky MCP config changes in pull requests; Export a JSON audit report for team review · GitHub
Autonomous Pentest Agent
Autonomous Pentest Agent is an open source Go and Next.js system where LLM agents run penetration tests autonomously, with a web UI for tasks, assets, findings, and approvals.
3 use cases: Install the pentest agent locally and reach the web UI; Import asset data from ScopeSentry into the asset graph; Retest a fixed vulnerability and record whether it still reproduces · GitHub
Voxenra
Voxenra is a cross-platform desktop DICOM viewer for CT, MR and PET/CT that covers image review, MPR and 3D views, PET/CT fusion, measurement and segmentation, and local AI auto-segmentation through TotalSegmentator.
3 use cases: Segment CT organs locally with AI and refine the result; Measure lesions on CT or MR and export a PDF or CSV report; Review PET/CT fusion and align it manually · GitHub
Phantom KV
phantom-kv is a Python project that tests a refusal-removal method, which loads a small trained bank of key and value tensors into a language model's KV cache without changing the model weights.
3 use cases: Compare refusal-removal methods on one eval set; Verify that a graft unloads cleanly and stays bound to its model; Summarize graft dose findings for a red-team report · GitHub
Dexsql Release
DexSQL is a closed-source tool that runs SQL queries over classes, methods, strings and call references in Android APK and DEX files, from the command line or through an MCP server for AI agents.
3 use cases: Trace which methods log a given string and who calls them; List hardcoded URLs in an APK with one SQL query; Search all DEX files in an app in a single query · GitHub
Redcell
REDCELL is an open-source platform where LLM agents run a penetration test end to end inside a Kali container and write the report.
3 use cases: Run an authorized pentest and export the report; Practice web pentesting on vulnerable apps; Triage source code findings and export SARIF · GitHub
Awesome Reverse Engineering
A curated list of reverse-engineering tools and learning resources for binaries, apps, firmware, file formats, and protocols.
5 use cases: Learn assembly and reversing basics for free; Triage an unknown executable to see what it can do; Trace calls in a running program with Frida · GitHub
Vuln Hunter
VulnHunter is an open-source agentic AI security scanner that traces attacker-reachable entry points to exploitable flaws, proves them with proof-of-concept tests, and proposes test-first fixes.
5 use cases: Hunt exploitable flaws in your own codebase; Fix a confirmed finding with a failing test first; Verify that a security fix really closes the finding · GitHub
Numbat
numbat is a Go command-line tool that watches AI agent activity on a laptop or workstation, detects risky behavior with local rules, can optionally block some actions before they run, and rebuilds past sessions from on-disk artifacts.
3 use cases: Audit past agent sessions without changing any config; Monitor live Codex activity into a local record file; Block a risky Codex action with a custom deny rule · GitHub
Recurse
Recurse is an open source desktop reverse engineering app, built with Tauri and Rust, with an AI agent that works on binaries through a pluggable analysis engine.
4 use cases: Triage an unknown binary in one desktop session; Let an MCP-capable agent query a binary headlessly; Decompile and de-obfuscate a suspicious function · GitHub
Pentest Harness
Pentest Harness is a self-hosted, open-source AI agent workspace for authorized security testing that runs with your own AI model API key.
3 use cases: Run an authorized pentest workspace on your own machine; Work through CTF challenges and security labs with an AI agent; Switch between AI providers and models during a long engagement · GitHub
Aifw
AI-FW is a self-hosted gateway that inspects, governs, routes, and audits prompts and responses between AI agents and the models they call.
4 use cases: Put a firewall in front of your existing LLM calls; Keep a metadata-only audit trail of agent calls; Route Claude Code and Cursor traffic through the gateway · GitHub
Blitzstrike
Blitz Strike is a TypeScript MCP server that packages a three-tier security audit (recon, source analysis, live validation) as tools an AI agent can call.
4 use cases: Triage a source tree for reachable, unauthenticated sinks; Verify live web findings with marker and control tests; Score, dedupe, and report findings for a write-up · GitHub
Agent Security
SolonGate Agent Security is a local, open-source Go gateway that checks AI coding agent tool calls against policy, detects secrets, and writes an on-device audit trail.
4 use cases: Stop an AI coding agent from reading your .env secrets; Lock files so a coding agent cannot delete or edit them; Confine a coding agent to one project folder on Linux · GitHub
Box
Strands Box is an open source Rust sandbox engine that restricts what AI agents can execute, read, write, and reach on the network.
4 use cases: Run a coding agent inside a restricted Box sandbox; Keep API keys away from an agent with credential injection; Audit every policy decision an agent made · GitHub
Skills
A collection of 56 portable security skills in 10 installable plugins for authorized defensive assessment, red teaming, penetration testing, detection engineering, and engagement operations.
4 use cases: Audit agent tools for poisoning and excess privilege; Test RAG tenant boundaries with controlled fixtures; Plan an authorized engagement and assemble findings · GitHub
AI Security Tool
AI Security Tool is an open-source, cross-platform terminal and vulnerability scanner that combines multi-protocol remote access, CVE and SBOM supply chain auditing, and autonomous AI agents.
4 use cases: Scan a project's dependencies for CVEs and SBOM gaps; Run one command across several SSH sessions at once; Host the Web UI for a team with login enabled · GitHub
Eleven
Eleven is an agent-first reverse-engineering app for macOS, Windows and Linux that lets any ACP agent read, rename, annotate and suggest patches for binaries, Android apps and GPU kernels.
4 use cases: Triage an unknown binary with an agent in one window; Explain an Android APK's code and resources with an agent; Rename functions and add notes with agent changes you approve · GitHub
Other categories · All use cases · Hot repos
Questions
What is the best AI repo for Security and science in 2026?
Right now the top pick on Deduped is Rea: A plug-in that lets your AI agent take apart an app and explain how a feature works.
How are these Security and science repos ranked?
By how hot they are on GitHub (stars gained and mentions in the AI sources we track), then by how many practical use cases we found. The list is rebuilt every day.
Get 5 new use cases every morning. Free, one short email, unsubscribe anytime.
Get them free