Rea

What is Rea about?

Rea offers a unified workflow for reverse engineering any software. It combines a command‑line interface and a Model Context Protocol (MCP) server so that large language model agents can inspect binaries, retrieve strings, symbols, decompiled pseudocode, and build evidence records without leaving the local environment.

How to use Rea?

1. Install the CLI (recommended):

   npm install --global rea-agents
   rea setup
   

   The setup command detects existing tools, proposes changes, and applies them after confirmation.
2. Add the skill to an agent (optional):

   npx skills add morluto/rea
   

   The agent can then be asked to run REA commands.
3. Run commands directly:

   npx -y rea-agents analyze /path/to/app
   npx -y rea-agents decompile /path/to/app
   npx -y rea-agents compare left.json right.json
   

   Or, with the global rea command after installation:

   rea analyze /path/to/app
   

4. Use MCP: Configure the MCP server (see serverConfig below) and let agents invoke REA capabilities via RPC calls.

Key features of Rea

• Three‑step investigation model: Decompile → Understand → Recreate.
• 70 built‑in tools covering native inspection, workflow orchestration, macOS utilities, artifact graph handling, browser CDP observation, and process capture.
• Evidence v2 records: Every result is stored as deterministic, signed evidence bundles with provenance metadata.
• Cross‑version workspaces: Persistent, content‑addressed investigations that can be resumed or compared across two releases.
• Local‑only analysis: Runs entirely on the developer’s machine; no code or binaries are uploaded.
• Support for Hopper (deep native analysis) and native macOS/ELF/PE utilities.
• Controlled process capture and passive Chrome/Edge CDP observation with strict allow‑lists.
• CLI and MCP parity: Same workflows are available from the terminal or via agent RPC.

Use cases of Rea

• Feature extraction: Understand how a proprietary app implements a specific function (e.g., offline search) and generate a compatible implementation in your stack.
• Security auditing: Decompile and trace suspicious strings or symbols to their runtime code paths.
• Migration & compatibility: Compare two versions of an application to identify behavior changes before a rewrite.
• Documentation: Produce structured function dossiers, call graphs, and evidence bundles for internal knowledge bases.
• Agent‑assisted development: Enable LLM agents to query binary behavior during coding sessions, reducing manual reverse‑engineering effort.

FAQ from Rea

• Do I need Hopper installed? REA can use an existing Hopper installation; if missing, rea setup --install-hopper will download and install the official demo package.
• Can REA run on Linux? Yes. Supported distros are Ubuntu 24.04+, Fedora 41+, and Arch 64‑bit. The setup script installs Hopper’s Linux demo, Xvfb, and other dependencies.
• Is any data uploaded to a cloud service? No. All analysis is performed locally. Only the agent or model provider you use may have its own policy.
• Can REA recover original source code? It provides decompiled pseudocode, assembly, and metadata but does not claim to recreate the exact original source.
• What agents are supported? Any agent that can communicate with a local MCP server. Setup auto‑configures Claude Desktop and Cursor; others can use the manual MCP JSON.
• How do I uninstall REA? Run rea uninstall or rea uninstall --purge-data to remove MCP registrations and cached state while preserving Hopper and other system tools.
• What is the licensing model? REA is MIT‑licensed. Hopper remains a separate commercial product; the demo mode is free, a paid license is optional.

English · 简体中文 · 日本語 · 한국어 · العربية

REA: Reverse Engineer Anything

One CLI and MCP server for agents to reverse engineer anything

See a feature you like. Understand how it works, down to the binary level.

Quick start · Current status · Investigation model · 70 tools · Roadmap · How it works

npm install --global rea-agents && rea setup

See a feature in an app that you want in your own product? Give the app to your agent—even without its source code. With REA, the agent can investigate the feature, explain how it works, show its evidence, and build a version adapted to your stack and requirements.

REA gives agents one consistent way to investigate software. Today that includes deep native analysis through Hopper, complete function dossiers, reproducible Evidence v2 records, and controlled process capture. The longer-term toolkit extends the same agent workflow to packaged apps, JavaScript bundles, websites, APIs, protocols, mobile artifacts, firmware, runtime behavior, and differences between versions.

Reverse engineering normally makes the operator choose a tool, learn its API, move evidence between programs, and decide what to inspect next. REA gives that work to the agent through commands, skills, structured results, and repeatable investigation workflows.

Just ask your agent

Install the REA skill:

npx skills add morluto/rea

Then ask:

Use REA to understand how search works in the Notes app, show me the
evidence, and build a similar feature for my project.

Notes is only an example. Name any app you want to understand, or ask the agent to start with an overview.

The investigation model

REA shows how it reached its conclusions. It does not claim to recover original source code or automatically clone an application.

Why REA

Quick start

Install the CLI — recommended

npm install --global rea-agents
rea setup

Installing the CLI does not update Homebrew, Node.js, npm, Hopper, or agent configuration. rea setup detects what is already present, prints every proposed change, and asks before applying it.

REA detects Claude Code, Claude Desktop, Codex, Cursor, Gemini CLI, Windsurf, and Devin. Registrations are additive, backup-first, and read back after writing. You can safely rerun setup.

An optional curl wrapper installs the same CLI package and starts setup only when a terminal is available:

curl -fsSL https://raw.githubusercontent.com/morluto/rea/main/install.sh | bash

Pass installer options after bash -s --, for example --dry-run, --no-setup, or --version 1.0.0. The curl wrapper never installs prerequisites or configures integrations itself. See Installation and setup for its exact mutation boundary.

With an agent — recommended

npx skills add morluto/rea

Ask your agent to set up REA. It will check your Mac, explain anything it needs to install, ask for approval, and guide you through system prompts. After setup, restart the agent if it asks you to load the full REA toolset.

Review the setup plan, approve it if appropriate, then describe the app or feature you want to understand. Hopper can run in its free demo mode; if it shows a first-run prompt, choose the demo or enter an existing license.

From Terminal — no installation

npx -y rea-agents setup
npx -y rea-agents doctor
npx -y rea-agents analyze /Applications/Notes.app

Review the setup plan before confirming it. Restart a configured agent so it loads REA.

From Terminal — install the rea command

npm install --global rea-agents
rea setup
rea doctor
rea analyze /Applications/Notes.app

Update that global installation in place:

rea upgrade

REA checks npm for the latest release and verifies that the running package is the global installation it will replace. Source, local, and npx copies report the manual npm install --global rea-agents@latest command instead of updating an unrelated global package.

Choose either the no-install commands or the global installation. You do not need both.

Requirements

• macOS 12 or newer
• Ubuntu 24.04+, Fedora 41+, or 64-bit Arch Linux
• Node.js 22.19+ or 24.11+ (including newer releases)
• npm; REA does not require or install a particular npm version

Deep binary analysis currently uses Hopper, a separate desktop application with its own license. Setup reuses an existing installation. If Hopper is missing, interactive setup proposes the official package and includes it in the confirmation plan. Unattended installation requires rea setup --yes --install-hopper.

If something is not working, run:

npx -y rea-agents doctor

rea doctor --json is read-only and distinguishes unsupported hosts, missing dependencies, a missing local analysis engine, configuration drift, and healthy checks. Paid-license activation is optional: on Linux, REA runs the supported Hopper demo build on a private Xvfb display and selects Hopper's offered demo mode for each analysis session.

Linux installation and troubleshooting

On macOS, approved setup downloads Hopper's official DMG, verifies it, and installs the app into ~/Applications without Homebrew or administrator privileges. Hopper may show its demo or license prompt when first opened; no manual drag-and-drop is required.

On Ubuntu 24.04+, Fedora 41+, and 64-bit Arch Linux, approved setup downloads the pinned official Hopper 6.4.2 package, restricts downloads to Hopper's public origin, verifies the published size and checksum, and invokes apt-get, dnf, or pacman to install Hopper and the Xvfb, Python, X11, and XTEST packages used by demo sessions. When REA is not already running as root, pkexec presents the system authorization prompt. REA never invokes sudo. Demo sessions run on an isolated 1280×1024 Xvfb display. REA verifies the exact supported Hopper binary, its owned process ancestry, the expected dialog geometry, and bridge state before selecting Try the Demo; any mismatch fails closed.

The normal Linux launcher is /opt/hopper/bin/Hopper. If Hopper was installed elsewhere:

export HOPPER_LAUNCHER_PATH=/absolute/path/to/Hopper
rea doctor --json

If doctor reports a missing analysis engine even though the file exists, inspect shared-library resolution with:

ldd /opt/hopper/bin/Hopper | grep 'not found'

Install the missing distribution packages and rerun rea setup. Linux demo automation requires Xvfb, Python 3, libX11.so.6, and libXtst.so.6; approved setup installs those direct runtime dependencies and does not interact with the user's desktop display. Hopper's free demo supports analysis with vendor-defined limits, and a paid license is optional. The curl installer places the rea command in ~/.local/bin on Linux; add that directory to future shell PATH values if it is not already present.

REA defaults HOPPER_LAUNCHER_PATH to /Applications/Hopper Disassembler.app/Contents/MacOS/hopper on macOS and /opt/hopper/bin/Hopper on Linux. Explicit configuration always takes precedence.

To remove only REA-owned MCP registrations and the managed skill:

rea uninstall
rea uninstall --purge-data # also removes only ~/.rea/cache and ~/.rea/state

Uninstall preserves Hopper, Node.js, evidence, captures, external evidence roots, unrelated skills, and other MCP servers. It refuses malformed client configuration and never follows purge-data symlinks.

CLI or agent?

Filesystem evidence commands and MCP file tools are disabled until the operator approves absolute roots:

export REA_EVIDENCE_ROOTS_JSON='["/absolute/path/to/evidence"]'
export REA_INVESTIGATION_INPUT_ROOTS_JSON='["/absolute/path/to/releases"]'
rea evidence-import /absolute/path/to/evidence/bundle.json
rea evidence-export /absolute/path/to/evidence/bundle.json /absolute/path/to/evidence/canonical.json
rea compare /absolute/path/to/evidence/left.json /absolute/path/to/evidence/right.json
rea investigate-versions /absolute/path/to/releases/v1 /absolute/path/to/releases/v2 /absolute/path/to/evidence/releases.json --yes --workspace-name releases

investigate-versions inventories both versions, checkpoints their observed Evidence, derives an artifact comparison, and records a changed-behavior report. Both input paths must resolve beneath REA_INVESTIGATION_INPUT_ROOTS_JSON; workspace files remain independently restricted by REA_EVIDENCE_ROOTS_JSON. The workspace uses deterministic content identities and monotonic CAS-linked revisions, so the same request resumes an interrupted run or reuses a completed run without replacing earlier investigations. It currently compares static artifact structure only; it does not execute either version, and its report keeps every difference labeled as a behavior candidate. See Persistent investigation workspaces.

Historical source import requires a separate allowlist and never treats source as current behavioral authority:

export REA_REFERENCE_ROOTS_JSON='["/absolute/path/to/source"]'
rea import-reference-source /absolute/path/to/source

Exports never replace an existing file unless --overwrite is explicit. Imports are size/depth bounded, validate every Evidence v2 ID and manifest, and never execute bundle content.

Provider-neutral analysis snapshots persist successful, immutable REA calls and their Evidence v2 records. They are exact caches rather than Hopper databases: REA reuses an entry only when the binary digest, format, architecture, operation parameters, loader arguments, and provider identity match. Custom Hopper loader overrides disable snapshots because their provider configuration cannot be replayed safely. Cursor-dependent and mutating calls are never cached. Snapshot files can contain proprietary analysis results and local paths, so REA keeps them local, writes them with owner-only permissions, and requires a separate approved root:

export REA_ANALYSIS_SNAPSHOT_ROOTS_JSON='["/absolute/path/to/analysis"]'
rea analyze /absolute/path/to/app --snapshot /absolute/path/to/analysis/app.json
# The same exact query can now be answered from the snapshot.
rea analyze /absolute/path/to/app --snapshot /absolute/path/to/analysis/app.json

Exact CLI evidence replays happen before any provider starts. In MCP sessions, pass snapshot_path to open_binary to import a snapshot atomically while opening its matching target; MCP providers may still start before a cached call is replayed. Pass snapshot_path and, when required, overwrite: true to close_binary to save atomically before Hopper resources are released. If the save fails, REA deliberately leaves the session open.

One prompt, a full investigation

Reverse engineer the Notes app. Find how offline search works, explain it,
and build a version for my project using TypeScript and SQLite.

REA gives the agent a clear path from that request to working code:

REA handles the app analysis in steps 1–5. The agent performs step 6 with its normal file-editing and test tools, using what it learned about the app.

What agents can do

• Investigate a feature you like and build a version tailored to your own product.
• Explain how a feature works when its source code is unavailable.
• Reconstruct an app's authentication, storage, update, or networking flow.
• Recover enough structure to document an undocumented format or interface.
• Trace a suspicious behavior from a string or symbol to the code that implements it.
• Run, checkpoint, resume, and reuse a content-addressed artifact investigation across two versions.
• Turn recovered behavior into product features, tests, migration notes, ports, or interoperable replacements.
• Analyze Swift and Objective-C metadata without manually untangling every mangled symbol.
• Leave names, comments, and bookmarks in Hopper so human and agent analysis reinforce each other.

70 tools for investigation

The public interface describes what the agent is trying to learn. Providers decide how to answer. macOS utilities handle common semantic inspection without launching Hopper; Hopper handles deeper native analysis; the process harness implements controlled behavioral capture.

Current status

REA is already useful for native application investigation on macOS:

• Open Mach-O, ELF, PE, .app, ZIP, APK, IPA, ASAR, plist, JavaScript, source-map, and Hopper database targets.
• Attach to a user-owned Chrome-family browser over a configured loopback CDP endpoint, list only pages on approved exact origins, and capture bounded passive web evidence without navigation or JavaScript evaluation.
• Traverse content-addressed artifact graphs without extraction; on macOS, read-only DMG traversal additionally requires native_mount_approved: true and REA_ARTIFACT_NATIVE_MOUNT_ENABLED=true. Materialize only approved occurrences into absent output roots.
• Build bounded function dossiers with pseudocode, assembly, CFG edges, comments, calls, references, strings, and names.
• Search and trace features across symbols, strings, metadata, references, and call paths.
• Record every successful result as deterministic Evidence v2 with artifact and provider identity, confidence, authority, limitations, and locations.
• Export and import evidence bundles across sessions.
• Persist automatic cross-version artifact runs as canonical, lock-protected workspaces with tamper-evident revision commitments.
• Capture approved PTY scenarios as Process Capture v4 Evidence, including committed run manifests, raw and rendered terminal frames, scripted interactions, descendant settlement, named filesystem checkpoints, deterministic command shims, and loopback HTTP/WebSocket exchanges.
• Compare complete artifact inventories by stable path, content, metadata, and relations; incomplete evidence never implies equivalence.
• Compare explicit function dossiers across text, calls, references, strings, and address-normalized CFG topology with per-facet unknowns.
• Compare canonical Evidence bundles by exact membership, explicit observation pairs, and residual-unknown histories without turning omissions into behavioral absence.
• Aggregate runtime comparisons into observed behavior changes while keeping static artifact/function differences labeled as candidates.
• Build bounded, Evidence-cited direct call paths by exact address without treating missing dossiers as graph leaves.
• Correlate exact static/runtime findings through explicit hypotheses without claiming causality from cochange.
• Verify finite behavioral and structural reconstruction specifications with pass, fail, and unknown kept distinct.
• Track residual unknowns through immutable CAS revisions, evidence-qualified resolution, contradictions, probes, and validated dependency relationships.
• With explicit unknown_registry_approved: true, record bounded trace/capture residuals, typed provider unavailability, and capture disagreements automatically.
• Start six guided MCP workflows with live, session-aware completion for documents, procedures, providers, evidence, captures, artifact IDs, and active unknowns.

Hopper is the first provider, not the boundary of the project. Some current workflows still require Hopper and macOS; every evidence record identifies the provider and limitations behind its result.

Website observation with CDP

REA can inspect an already-running Chrome-family browser that you own. Browser observation is disabled by default and requires a literal loopback CDP endpoint plus exact approved page origins:

export REA_BROWSER_OBSERVE_ENABLED=true
export REA_BROWSER_CDP_ENDPOINTS_JSON='["http://127.0.0.1:9222"]'
export REA_BROWSER_ALLOWED_ORIGINS_JSON='["http://127.0.0.1:3000"]'

rea list-browser-targets http://127.0.0.1:9222 --approved --json
rea inspect-web-page http://127.0.0.1:9222 TARGET_ID --approved --json

list_browser_targets and inspect_web_page expose the same Evidence v2 contracts over MCP. Inspection is passive: REA does not evaluate page JavaScript, navigate, click, close the page, or close the browser. It redacts query values and never retains headers, bodies, cookies, storage values, console argument values, or WebSocket payloads. Existing activity before attach is explicitly unavailable. See Website observation with CDP for browser startup, schemas, limits, and the threat model.

Roadmap

REA is growing into a toolkit for understanding software across static artifacts and observed behavior. The next capability families are:

1. Artifact decomposition — DMG, ASAR, ZIP, packages, universal-binary slices, application resources, embedded frameworks, mobile packages, and artifact graphs.
2. Web and Electron investigation — extend the shipped passive CDP observation with approved interaction, screenshots, Electron IPC, route discovery, controlled replay, and visual or structural differences.
3. Deterministic behavior harnesses — stronger process-tree ownership, protocol fixtures, network policy, filesystem tracing, signals, reconnects, and cross-version comparison.
4. JavaScript and source recovery — bundle indexing, AST/module reconstruction, source-map discovery, historical-source matching, and CodeDB-backed cross-references.
5. Runtime observation — approval-gated LLDB, Frida, system logs, process and filesystem observers, and native API tracing.
6. More static-analysis providers — native platform utilities first, followed by Ghidra, IDA/Hex-Rays, Binary Ninja, Rizin, LIEF, and other engines behind provider-neutral capabilities.
7. More targets and platforms — Windows-native providers and ConPTY verification, Linux parity, websites and APIs, mobile artifacts, firmware, document formats, and other software-defined systems.
8. Differential reconstruction expansion — add automatic function matching, protocol/UI comparison, controlled replay, residual-unknown planning, and reconstruction verification to persistent version runs.

Roadmap items describe direction, not shipped support. New providers must produce the same evidence and safety metadata as existing capabilities before they become part of the public workflow. Once REA has multiple optional toolchains, setup can become capability-selective; the consent rules for that future work are recorded in the installation roadmap.

See the static-analysis provider evaluation for the current research matrix and admission gate.

Using REA with other agents

Setup currently configures Claude Desktop and Cursor automatically. Any agent that supports local MCP servers can use REA with the configuration below.

Manual MCP configuration

{
  "mcpServers": {
    "rea": {
      "command": "npx",
      "args": ["-y", "rea-agents", "mcp"]
    }
  }
}

MCP clients that support prompts can also discover six ordered investigation workflows through prompts/list. Their optional identifier arguments use the current session for bounded completion/complete suggestions; see Guided MCP prompts and completion.

How it works

The CLI and MCP server use the same application workflows and evidence contracts. A provider declares which capabilities it supports and the side effects those capabilities may have. Terminal commands are short-lived; an MCP session can retain an active target and evidence ledger across an investigation. Approved persistent workspaces keep canonical Evidence and resumable run checkpoints across both process and session lifetimes.

CLI

The agent workflow above is the easiest way to use REA. For a one-off overview from the Terminal:

npx -y rea-agents analyze /Applications/Notes.app
npx -y rea-agents inspect /Applications/Notes.app
npx -y rea-agents inspect /Applications/Notes.app --detail detailed --limit 20
npx -y rea-agents search /Applications/Notes.app "offline"
npx -y rea-agents function /Applications/Notes.app 0x1000
npx -y rea-agents xrefs /Applications/Notes.app 0x1000
npx -y rea-agents trace /Applications/Notes.app "offline"
npx -y rea-agents compare /absolute/path/to/left-evidence.json /absolute/path/to/right-evidence.json
npx -y rea-agents investigate-versions /path/to/v1 /path/to/v2 /absolute/path/to/evidence/releases.json --yes
npx -y rea-agents capabilities
npx -y rea-agents providers

Run npx -y rea-agents --help for direct decompilation, bounded search and other options. analyze and inspect share the same overview workflow; function, xrefs, and trace return the same Evidence v2 envelopes as MCP.

Or install the rea command globally:

npm install --global rea-agents
rea --help
rea upgrade
rea mcp

REA accepts a Mac .app folder directly. If an agent cannot find an app by name, tell it where the app is installed.

CLI exit status

setup returns 1 for planned, needs_confirmation, or needs_human because configuration is not ready; rerun it after approval or remediation. doctor returns 1 when any check is unhealthy. Output format, full envelopes, filters, and token controls never change the operation status.

When REA feeds a shell pipeline, enable pipefail so a downstream formatter cannot hide its failure:

set -o pipefail
rea inventory-artifact ./app.asar --json | jq . > inventory.json

Current Hopper provider

REA starts Hopper when needed; Hopper does not need to be running first. Hopper's launcher internally activates the application, so opening a target may bring Hopper to the foreground. REA asks macOS to start Hopper hidden and in the background when possible, but cannot guarantee that it will remain behind the current application.

REA derives explicit format and architecture arguments to prevent common FAT and ARM selection dialogs. Other Hopper or macOS dialogs may still require a person. REA reports timeouts and remediation through CLI or MCP results instead of attempting to answer UI prompts.

Closing a REA session shuts down its bridge and removes its private socket directory. It does not quit a Hopper application the user may be using.

Advanced process-capture setup

Process capture is disabled by default. Enabling it requires REA_PROCESS_CAPTURE_ENABLED=true, approved executable and working roots in REA_PROCESS_EXECUTABLE_ROOTS_JSON and REA_PROCESS_WORKING_ROOTS_JSON, and an environment allowlist in REA_PROCESS_ALLOWED_ENV_JSON. Because the current PTY adapter uses host networking, it also requires REA_PROCESS_ALLOW_EXTERNAL_NETWORK=true.

Capture a scenario or compare two saved Process Capture v4 Evidence records:

rea capture-process ./scenario.json > authority.json
rea capture-process ./reconstruction.json > reconstruction.json
rea compare-process-captures authority.json reconstruction.json

The comparison reports each observed dimension separately and identifies the first terminal, interaction, exit, filesystem, protocol, process, or shim divergence. See Process Capture v4 for scenario fields, command-shim replay, checkpoint triggers, limits, and safety behavior.

If the native PTY backend is unavailable, install Xcode command-line tools and run npm run rebuild:native. Linux source builds require Python, make, and a C++ toolchain. Compatible packaged binaries do not require this rebuild.

ASAR inventory verifies Electron integrity metadata for both archive entries and .asar.unpacked companion files. Integrity failures identify the logical path, declared and calculated SHA-256 values, and whether the entry was unpacked; REA does not silently accept the mismatched artifact.

Security model

REA does not provide a hosted analysis service. Hopper communication uses an authenticated private local socket. Dynamic capabilities are disabled by default and require both operator policy and explicit per-call approval. REA is not a security sandbox: providers and launched targets run with the current user's permissions, and each capability reports its side effects and limitations. Report vulnerabilities through the private process in SECURITY.md.

FAQ

No. REA starts Hopper when an operation needs it. An already-running Hopper application is also supported.

Hopper's launcher internally activates the application. REA requests background startup, but macOS and Hopper may still bring a window or dialog forward. See Hopper application behavior.

No. Setup can install Hopper for you, but Hopper remains separate software with its own license. REA supplies the CLI, MCP server, and workflows that make it usable by agents.

REA has no hosted analysis service. Current providers analyze artifacts and capture behavior locally. Your agent or model provider may have its own data policy, so review that separately.

No decompiler can guarantee the original source. REA gives an agent pseudocode, assembly, symbols, strings, metadata, and relationships that it can use to explain or compatibly recreate observed behavior.

Any agent that can run a local MCP server can use the manual configuration. Setup currently detects and configures Claude Desktop and Cursor automatically.

Development

See CONTRIBUTING.md for setup, architecture, tests, and release instructions. Generated API documentation is available under docs/api.

Project links

npm · Issues · Security · Contributing · Hopper

License

MIT