Files
rea/docs/index.md
Edgar ArakelyanandClaude Opus 5.5 fc4c381dd7 feat(desktop): keep an agentenv computer up and drive it through REA's MCP tools (#9041)
* feat(desktop): keep an agentenv computer up and drive it through REA's MCP tools

- A Python helper keeps one agentenv computer up per build with
  run_bundle(keep=True) and reports its address, MCP URL, control token
  and sandbox id; it tears the computer down when stdin closes.
- AgentEnvComputer owns the helper, waits for readiness, holds one MCP
  session to the computer's computer_* tools, records through the
  computer-recording routes, and removes the sandbox's containers by
  label when agentenv cannot confirm teardown. The token never leaves it.
- start_build_computer starts a computer from a request (archive package,
  apt repository or .deb, opened on demand with REA in /opt/rea) or from
  a bundle folder; act_on_build_computer forwards screenshot, click,
  drag, scroll, type, key and wait and returns the driver's images
  unchanged; close_build_computer tears it down.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(desktop): remove a build computer's container by name when agentenv cannot confirm teardown

agentenv's local provider runs an ordinary computer as agent-<sandbox id>
without the agentenv.sandbox label, so the label-only fallback found
nothing and reported a running computer as removed. The fallback now
lists containers by exact name and by label. The real test holds its
recording open long enough for a first frame, checks the container by
name, and runs rea inside the computer; the guide and tool descriptions
say the app opens from the Applications menu and that a screenshot after
opening a menu should come from a wait.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(desktop): own failed build-computer starts, keep ids past oversized screenshots, bound recordings

- A start is owned from the helper's spawn. One that fails and whose
  teardown is unconfirmed stays held under a computer_id close can retry;
  closeAll refuses new starts, cancels and joins starts in progress, then
  closes every held computer.
- When the first screenshot is too large, the error carries REA's result
  with the computer_id, and start_build_computer takes screenshot region,
  format and quality.
- Recordings are refused before reading when the manifest's total exceeds
  the allowance, then fetched one segment at a time, each read bounded and
  checked against its size and sha256.
- The helper keeps the tail of its output (a new tail retention mode in
  ProviderProcessSupervisor), so a build's own error is not crowded out.
- A helper that reported no computer exits on its own before SIGTERM, so
  no phantom owner is kept.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

* fix(desktop): bound a build computer's action log

Every action kept its full arguments for the computer's whole life, so a long
session grew REA's memory without limit. The log now keeps the latest 256
actions within 256 KiB, cuts each string to 1 KiB and each list to 64 items
(naming what it cut), and keeps the total and the last applied index of each
kind of action, so rules over the whole session hold after entries drop.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-06 11:01:11 +08:00

13 KiB

layout, hero, features
layout hero features
home
name text tagline actions
REA Reverse Engineer Anything Understand binaries, applications, and runtime behavior with one CLI and MCP server.
theme text link
brand Get started /installation
theme text link
alt View on GitHub https://github.com/morluto/rea
title details link
Investigate with your agent Connect REA to your coding agent, describe the app or feature you want to understand, and follow the evidence. /mcp-prompts
title details link
Inspect across formats Explore native binaries, JavaScript and Electron apps, .NET assemblies, Android packages, firmware, and websites. /installation
title details link
Keep the evidence Analysis runs locally and returns observations, limitations, and unknowns through the CLI and MCP. /mcp-contracts

Start with one command

npx rea-agents setup

Choose your agent, review the planned changes, and approve setup. Native binary analysis can use an existing Hopper, Ghidra, or IDA installation; static JavaScript analysis needs no native analysis engine.

For a first result from an extracted JavaScript application or ASAR:

npx -y rea-agents@latest analyze-javascript-application /absolute/path/to/app --json

See installation and setup for requirements and configuration.

For runtime instrumentation, see the Frida guide.

Choose a guide

Task Guides
Identify a desktop installation Runtime candidates, evidence and follow-up files
Inspect native functions, references, or types Native binaries, Go metadata, Rust dependencies, CPython pyc files, PE certificates, PE imports, PE TLS/load config, ELF notes, Binary hardening, Linux kernel modules, Apple IPS, Erlang BEAM, offline ELF layout, recorded crashes
Select a native provider or import format Ghidra semantics, Windows, DOS, raw bytes, GameCube DOL, MIPS, PSP, NativeAOT, IDA, Kuna, JEB
Analyze JavaScript or Electron artifacts Static analysis, tracing and comparisons, application graph, source recovery
Compare static JavaScript with runtime observations Runtime attribution, reconciliation, Electron observation, Electron fuses
Inspect assemblies, packages, or firmware Godot PCK, UnityFS, wxapkg, U-Boot uImage, .NET, Python packages, Android, APK signatures, Apktool resources, ADB acquisition, Apple, Harmony, firmware, ESP images, ESP flash images, WASM, EVM
Observe or compare a browser scenario CDP observation, scenarios, runtime evidence, historical captures
Serve recorded behavior as an agent environment Agent environments
Trace captured website source Source locations, module traces, script export
Capture and compare a command Process capture
Capture a Linux desktop application in use Desktop application capture
Read a captured application's state Desktop application state
Export a captured application as an environment Desktop application export
Write and validate a task for an exported app Desktop application tasks
Drive a computer while building an environment Desktop build computer
Use CLI/MCP and retain evidence CLI, MCP contracts, agent prompts, obligation ledgers

For development, use testing, client verification, tool design, admission limits and recovery, and releasing. Reconstruction readiness describes a development conformance verifier. The 6.2 migration records that release's compatibility changes; the roadmap tracks future work.

REA inspecting a native binary in Hopper