9dde3fd6a4
* fix(artifacts): retain caller selection and applicable publication recovery * fix(artifacts): retain DMG producer failures and bound integrity recovery claims * fix(apk): classify malformed supported Zip64 records as input failures * fix(browser): compare script and tool facts without metadata identity churn * fix(environment): retain path segments counters and parent diagnostics * fix(discovery): retain Frida optional provider failure dispatch * test(native): share Swift context in vtable fixture admission * fix(native): narrow capability refusal before retaining its reason * fix(javascript): retain private receiver and iterative disposal effects * fix(native): preserve negative Mach-O admission identity * fix(javascript): bind Next page admission to source context * fix: preserve process filesystem scope and admission failures * fix(evidence): reject runtime locations for managed static facts * fix(hopper): bind ordinary executable opens to selected bytes * fix(browser): admit legacy capture uncertainty at retained input boundaries * fix(unknowns): distinguish rejected creation from committed mutation delivery * fix(evidence): preserve authentication failures and diagnose prior commitments * fix(cli): preserve explicit Evidence record pairing in bundle comparison * fix(artifacts): publish addressable inspection sources through both adapters * docs(evidence): define authentication and committed delivery recovery * fix(javascript): own reference roles and invocation result identities * fix(hopper): pass private X authority cookie through stdin * fix(ghidra): preserve catalog and metadata admission failures * fix(jeb): retain selected inputs and completed primary replies * fix(native): preserve literal environment map members * test: retain direct hash cleanup retainer contract * test: distinguish corrected port normalization commitment * fix: recheck attached worker policy after final artifacts * fix(javascript): share iteration and equality invocation facts * fix(artifacts): preserve typed resource limit diagnoses * fix(javascript): preserve semantic query identity and source coverage * docs(readme): align translated setup and analysis facts * fix(cli): reject surplus positional arguments before execution * fix(kuna): retain setting-specific doctor recovery * fix(setup): preserve semantic configuration refusal during uninstall * fix(setup): retain publication operation failures and recovery facts * fix(setup): distinguish Hopper inspection and archive staging failures * docs(managed): distinguish oracle conformance from host verification * docs(skill): keep one setup prerequisite policy * fix(firmware): preserve admission and extraction coverage outcomes * fix(contracts): preserve safe defaults and client literal guidance * fix(javascript): retain worker storage and projection failures * fix(evidence): preserve valid output paths near filesystem pathname limits * fix(cli): accept named native API selectors beginning with a dash * fix(artifacts): retain DMG carrier observations when child traversal is unavailable * fix(artifacts): retain dylib enumeration readers through failed cleanup * fix(browser): resolve empty storage-world origins from exact frame evidence * fix(browser): retain unknown popup storage initialization coverage * test(reconstruction): isolate derived surface ownership in fixtures * test(filesystem): probe actual permission denial before host assertions * test(managed): assert large issue retention without full-array diffs * fix(javascript): preserve source facts across graph projections * fix(javascript): preserve copied values and export publication lifetimes * fix(javascript): preserve per-field publication and provenance coverage * fix(javascript): retain initialized class self binding at body reads * fix(artifacts): retain permission omissions through JavaScript lookups * test(graph): narrow summary owner and complete PE fixture facts * test(javascript): supply source graph to native handoff checks * fix(sourcemaps): bind cleanup status to remaining codec owners * fix(browser): retain excluded source-map declaration coverage * test(javascript): preserve exact empty property keys in declarations * fix(browser): keep code absence unknown without worker inventory * fix(browser): preserve WebMCP optional fields and replay coverage gaps * fix(browser): publish executable examples with truthful capture coverage * fix(browser): preserve observed document invalidation and scope recovery * fix(native): share exact-name xref ambiguity resolution * fix(hopper): own bookmark API capability checks * fix(native): preserve procedure selector coordinate intent * test(discovery): select the declared GDB console contract * fix(ghidra): bind session refusal to retained cleanup owner * fix(apple): retain selected dylib identity after path removal * fix(apple): preserve asset failures and authored resource coverage * fix(apple): retain binary UID identity through archive projection * fix: retain completed historical replies through finalization * fix: retain unresolved browser secret declarations as input errors * test(browser): resolve network fixture secrets through typed input contract * fix(environment): distinguish destination refusal and write access failures * fix(artifacts): preserve exact ZIP and DMG caller cancellation reasons * fix(artifacts): require regular source-map target occurrences * fix(reference): separate local filesystem diagnostics from graph commitments * fix(setup): retain proven PATH aliases in installed registrations * test(package): join owned updater after registry fixture failure * fix(javascript): preserve recovery acquisition and cancellation failures * fix(session): retain cleanup blockers and snapshot request identity * fix(evidence): preserve format-owned JSON recovery diagnostics * test(evidence): cover BOM recovery across bundle commands * fix(tracing): retain caller reasons at traversal checkpoints * fix(inventory): require released cleanup before capability fallback * fix(hopper): drain retained publishers after current close failure * fix(native): preserve unknown Swift extension contexts * fix(apple): qualify unexamined nib content coverage * fix(frida): preserve session refusal and close execution effects * fix(rizin): retain cancellation and recover cleanup correlation * fix: retain Electron file admission facts across adapters * fix: preserve selected Electron display authorization * fix(javascript): retain unavailable HTML reference scopes * fix(javascript): preserve capture timing and detached receiver authority * fix(ida): preserve producer failure and caller abort outcomes * fix(cli): retain nested facts in Markdown tables * fix(cli): present argument guidance without validator cause dumps * docs(setup): define optional native update verification limits * docs(clients): distinguish discovery and schema recovery boundaries * docs(setup): explain npm workspace launcher failures * fix(verification): bind Copilot schema profile to observed inputs * fix(javascript): scope Next package admission by container identity * fix(apple): align asset allowance and category fixture types * fix(protocols): honor runtime queue and Frida identity types * test: parse Electron listing Evidence before comparison * fix(evidence): omit absent format recovery metadata * fix(contracts): validate historical source examples as exact JSON values * fix(javascript): consume per-field CommonJS publication facts * fix(gdb): correlate raw-output completion and retain read-only TTY proof * fix(native): retain completed LLDB facts across output-close cancellation * fix(hopper): retain failed private-display probe cleanup authority * style(lifecycle): format traversal and fallback edits * fix(apple): own ordered nib collections and registry parentage * fix(process): attribute trace omissions without changing shared successors * fix(cli): share builtin argument ownership with MCP routing * fix(cli): count emitted documents and normalize token windows * fix(inspector): retain captures through authorization cleanup failures * fix(artifacts): retain declared ASAR companion occurrence facts * fix(javascript): separate endpoint syntax correspondence from target identity * fix: distinguish native process exit from sampling failure * fix(javascript): retain selected-root access and filesystem failure facts * fix(browser): retain truthful cleanup facts and document request ownership * fix(native): share exact Objective-C class symbol interpretation * fix(go): retain completed artifact facts through finalization * fix(native): preserve seed analysis failures in value traces * fix(native): classify observed dSYM inspection refusal * test(apple): assert observed collection edge contract * fix(javascript): retain primary interruption through worker cleanup * fix(cutter): retain completion-read failures during cleanup retry * fix(cli): validate output windows and finish pending writes * fix(mcp): require absolute JavaScript application inputs * fix(capabilities): report missing navigation targets * fix(cli): support system Bash completion registration * fix(cli): retain narrowed token-count format handling * test(ida): preserve exact optional resource method shape * test(javascript): retain valid unknown endpoint coverage shape * fix(ghidra): try keg JDKs after failed PATH launchers * fix(browser): retain capacity refusal through terminal progress * fix(reference): require exact optional JSON diagnostics at the source schema * fix(apple): retain reader outcomes and cleanup ownership * fix(elf): qualify exports without dynamic symbol declarations * fix(mips): retain unexamined RELR declaration coverage * fix(metadata): preserve canonical PowerPC subject identity * fix(native): preserve LLDB discovery failure classifications * fix(native): report absent launch process before cleanup classification * fix(rizin): preserve primary outcomes across final cleanup * fix(browser): preserve admission failures and retain policy transport cleanup * fix(objdump): preserve input issues and provider launch failures * test(apple): attribute omitted edges to their node capacity limit * chore(metadata): synchronize packaged skill version * fix(cli): consume canonical output validation state * fix(views): preserve owning layout field diagnostics * test(pyinstaller): distinguish path and metadata allowance failures * fix(native): compose the selected command cause once * fix(setup): require HTTPS throughout Hopper download redirects * fix(ghidra): narrow fallback probe failures before projection * fix(native): require observed symbol origin for named identity * fix(javascript): retain unavailable source processing scopes * fix(cli): share declared output-error redaction * docs(windows): explain MCP registration launcher limits * fix(session): preserve binding commitments during restoration * fix(environment): retain primary facts through server cleanup failure * fix(pe): distinguish unsupported overlapping header layouts * fix(cli): keep positional admission placeholders omittable * test(cli): expose JavaScript progress workflow failure output * test(browser): match retained subframe limitations structurally * fix(javascript): preserve capture and property-key effect ownership * fix(ghidra): attribute import policy conflicts to settings * fix(native): validate Mach-O command framing before admission * docs(mcp): state plist inspection session prerequisite * fix(electron): separate script frame admission from declared source labels * test(environment): read asynchronous owner observations through contracts * test(javascript): distinguish resolver URLs from existing module targets * fix(ghidra): retain neutral recovery for observed SIGKILL * fix(hopper): preserve unknown relationship completeness * docs(native): clarify Darwin runtime breakpoint names * fix(browser): preserve unknown script ownership through reconciliation * fix(electron): keep optional provenance fields within JSON evidence values * fix(native): retain Mach-O architecture discriminant narrowing * test: give oversized registration groups semantic owners * test: group boundary registration by observed behavior * fix: normalize retained terminal observations with sampled identities * fix: identify missing Electron lineage ownership markers * fix(ida): retain registration constraints and identity refusal guidance * fix(kuna): retain published exports through staging cleanup failures * fix(nativeaot): charge only examined candidate table entries * docs: clarify batch decompilation retention limits * fix(javascript): distinguish deferred bootstrap installer writes * fix(native)!: preserve UI scalar facts and selection failures BREAKING CHANGE: Accessibility node value can also be a JSON number or boolean. Strings and null retain their prior meaning. * fix(javascript): retain activation order for captured scope exits * test(pyinstaller): use an absolute drive path for refusal coverage * fix(javascript): preserve route selection owners and uncertainty * fix(javascript): prove native URL constructor paths * refactor(tests): separate fixtures and registration groups * test(native): distinguish qualified symbol identity controls * fix(ida): preserve busy details across timeout attribution * fix(cli): unify builtin and global completion scope * test(ghidra): group exit-signal evidence controls * fix: retain narrowed terminal observation values * fix(cli): bind completion input to public registry type * fix(flutter): qualify unsupported unified snapshot profiles * test(native): bind origin comparison to containing entries * fix(cli): remove completion markers on system Bash * test(ida): preserve physical workspace traversal controls * fix(native): retain unknown UI executable identity * fix(native): unify LLDB discovery preparation failures * fix(evidence): preserve primary semantics during pending cleanup * fix(evidence): retain owner finalization reports across cleanup envelopes * test(browser): inspect provenance in owned graph observations * test(flutter): assert canonical unsupported profile error code * fix(javascript): capture primitive return values at evaluation * fix(mcp): own cancellation and raw input throughout startup * test(ghidra): construct exact import policy targets * fix(gdb): preserve configured executable launch recovery * test(ghidra): own fixed import target fixtures * docs(readme): align localized guide link occurrences * test(evidence): retain structured input issues through cleanup owners * test(mcp): await observed EOF before releasing startup * fix(electron): retain bounded source frame claims * fix(elf): validate declared file extents before provider admission * fix(elf): align metadata and admission fixture error types * test(wasm): place parsed interface comparison at provider boundary * test(ida): place capability composition at provider boundary * test(browser): place PNG contract execution at provider boundary * perf(test): share SDK catalog compilation across deferred clients * fix(cli): trim repeated selector discovery guidance * revert(test): remove unproven SDK compiler sharing This reverts commit 56eca648d. The equivalent completed two-client measurement increased elapsed and CPU time, so compiler sharing has not established a benefit. * refactor(managed): retain decoded metadata token facts * test(managed): scope cleanup failures to snapshot reads * test(cli): bound selector rejection cases by command * test(mips): distinguish damaged ELF admission from partial ABI evidence * test(reconstruction): declare authored function symbol identity * test(rizin): register terminal admission at provider boundary * test(process): align root admission fixture with observer allocation ownership * test(mips): project inspected ABI facts without undefined overrides * refactor(browser): remove obsolete web script reconciliation * refactor(javascript): remove obsolete in-process projection runner * refactor(managed): retain TypeDef row ownership through projections * test(process): assert canonical admission failure through cleanup envelopes * fix(managed): select types from retained definition records --------- Co-authored-by: morluto <76467478+morluto@users.noreply.github.com> Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Türkçe · Русский · Tiếng Việt · ไทย · Deutsch · Español · Français · Українська · Polski · Português (Brasil) · العربية · فارسی · Bahasa Indonesia · Italiano · Ελληνικά · മലയാളം · Roman Urdu
REA: Reverse Engineer Anything
One MCP for reverse engineering across binaries, applications, and runtime behavior.
See a feature you like. Understand how it works, down to the binary level.
Quick start · How REA works · What you can analyze · Showcases · FAQ · Documentation
npx rea-agents setup
Important
Get REA from morluto/rea, rea.tools, or the rea-agents npm package. Follow the installation and release links from these official sources. A similar repository name or copied README does not establish that a download is official.
See a feature in an app that you want in your own product? Ask your agent to investigate it with REA. It can inspect the app without its source code, explain how the feature works, show the evidence, and build a version for your project.
REA connects your agent to tools for inspecting native binaries, JavaScript and Electron apps, .NET assemblies, and websites. You can also use the same tools from your terminal. Analysis runs locally, and results include the evidence and limitations behind each conclusion.
Setup registers REA with your agent and installs matching workflow instructions. Native analysis can use an existing Hopper, Ghidra, or IDA installation; setup can optionally install Hopper with approval. Static JavaScript analysis needs no native analysis engine.
Visit the REA website for setup instructions, illustrated guides, and real case studies.
Quick start
On Linux, Ghidra, JADX, firmware tool launches and static JavaScript/Electron
analysis require a procps-compatible ps on REA's PATH for process ownership
checks. Recovery steps are in docs/installation.md under
"Linux owned-process prerequisite".
Set up your agent
With Node.js and npm installed, run:
npx rea-agents setup
Choose your agents, review the proposed changes, and approve them. Setup adds REA's MCP server and matching workflow instructions, with backups of existing configuration. Restart your agent afterward.
Setup supports Claude Code, Codex, Cursor, Gemini CLI, Grok Build and other agents. See installation and setup for provider configuration and manual MCP registration.
MCP uses compact input schemas by default to reduce context overhead. Set
REA_MCP_INPUT_SCHEMA_PROFILE=full in your MCP registration when you need the
complete advertised field guidance and nested validation details. Both profiles
keep the full tool set and canonical server validation. See
"Compact input schema profile" in the MCP contracts guide.
Ask your agent
Understand how search works in the Notes app, show me the evidence, and build a
similar feature for my project.
Replace Notes with your target app and the feature you want to understand.
Use the terminal
Inspect an extracted JavaScript/Electron app directory or ASAR:
npx -y rea-agents@latest analyze-javascript-application /absolute/path/to/app --json
The result includes modules, imports, Electron boundaries and their evidence.
Replace the path with your target, such as "D:/apps/example" on Windows.
To install the rea command for regular use:
npm install --global rea-agents
rea --help
For native analysis, configure a provider first. See the CLI and Evidence guide for native commands, provider selection, snapshots and scripting.
Update REA
REA changes quickly, and new releases include frequent bug fixes. Keep your installation up to date.
For a CLI installed with npm install --global or bun add --global:
rea update
rea --update is an alias for this verified workflow and accepts the same global
output flags. Use rea update when combining it with other command controls.
Updater commands retain at most 4 MiB of stdout and stderr combined. Oversized metadata replies are rejected after the command exits; verbose installs continue with bounded diagnostics. Human progress output respects terminal backpressure and waits for submitted writes to finish.
Bun global updates require Bun 1.2.17 or later. With an older Bun release,
upgrade Bun manually before running rea update.
To refresh your agent registrations and skill, run the setup command printed by the update.
If you use npx, update your agent setup with:
npx rea-agents@latest setup
Review the setup changes and restart your agent. For one-off CLI commands,
use npx rea-agents@latest followed by the command. With Bun, use
bunx rea-agents@latest in place of npx rea-agents@latest.
How REA works
Your agent calls REA through MCP to inspect the target and trace relevant code. REA returns findings with their evidence. The agent uses them to ask follow-up questions, explain the behavior, or write and test an implementation. CLI commands use the same workflows.
What you can analyze
REA requires Node.js 22.x (>=22.23.4), 24.x (>=24.22.1), or 26.12.1+, plus npm. Additional tools and host support depend on the target:
| Target | What REA returns | Requirements and guide |
|---|---|---|
| Desktop installations | Runtime candidates, supporting files, component markers and next probes | Built-in bounded directory/header inspection; desktop applications |
| Native binaries | Pseudocode, assembly, strings, symbols, calls and references | Hopper, Ghidra or IDA; native analysis |
| Offline ELF layout | Sections, segments, original symbols/relocations and static mitigation candidates | Caller-supplied pwntools on Linux x64; binary diagnostics |
| Go binaries | Embedded compiler version, modules, replacements and build settings | Built-in static ELF/PE/thin Mach-O inspection; no Go installation required |
| GPU code objects | CUDA/HIP targets, selected kernel parameters and resources, retained PTX text | Built-in static ELF/PE/fatbin/CUBIN/PTX inspection; GPU code objects |
| Model artifacts | GGUF / safetensors metadata, tensor declarations and derived totals | Built-in header inspection; optional full-file hash; model files |
| IL2CPP metadata | Unity global-metadata.dat assembly images, type and method names and index ranges | Built-in static decoding of versions 24, 27, 29, 31 and 39; no Unity required |
| Godot PCK | Archive inventory and extraction, original header/directory facts and selected content identities | Built-in static formats 2, 3 and 4; no Godot required |
| Rust binaries | Embedded cargo-auditable crate names, versions, sources and dependency edges | Built-in static ELF/PE/thin Mach-O inspection; Rust binaries |
| PE certificates | Authenticode WIN_CERTIFICATE entries and PKCS#7 signer/X.509 identity fields | Built-in static PE inspection; PE certificates |
| ELF notes | PT_NOTE/SHT_NOTE owners, types, GNU build-id and ABI-tag fields | Built-in static ELF inspection; ELF notes |
| Erlang BEAM | IFF chunks, atoms, exports, imports, lambdas and the Code header | Built-in static BEAM inspection; Erlang BEAM |
| WASM artifact | Validation, sections, exact import/export WAT forms and decoded WAT | Caller-supplied WABT 1.0.42; inspect_wasm_artifact |
| EVM bytecode | Dispatch selectors, byte offsets, inferred arguments and mutability | Local raw/hex carrier on Linux x64; offline EVM guide |
| SQLite databases | Tables, columns, indexes, views, triggers and selected ordinary-table rows | Local database/WAL snapshot; Node.js 24.x >=24.15 or 26+ with native SQLite limits |
| Recorded Linux crashes | Raw notes, every recorded thread's registers/signals and optional mapping candidates | Caller-supplied pwntools on Linux x64; optional GDB/pwndbg; recorded crashes |
| JavaScript / Electron | Modules, imports, source maps, routes, IPC and native add-on relationships | Node.js and npm; Linux: procps-compatible ps; application analysis |
| Websites | Page structure, scripts, network observations and requested screenshots | A Chrome-family browser; browser analysis |
| Saved network captures | Requests, responses, exposed payloads and source locations | HAR or Fiddler Everywhere SAZ; mitmdump on Linux for native mitmproxy; capture guide |
| .NET assemblies | Metadata, CIL instructions, declared native dependencies and build comparisons | None (static only); managed-code guide |
| Android APKs | Manifest declarations, classes, decompiled methods and references | Headless JADX and a full JDK on Linux/macOS/Windows x64; Android guide |
| APK signatures | v1/v2/v3/v3.1 signers, certificate fingerprints, key rotation and digest self-consistency | None (static only); inspect_apk_signature |
| Android devices | Devices, packages, processes, logs, dumps, screen captures, and APK/file transfers | Caller-supplied adb (emulator or hardware); ADB guide |
| JEB projects | Engine-backed project units, artifact digests and type/method pseudo-code | A caller-started JEB client serving MCP, selected with REA_JEB_MCP_URL; JEB guide |
| Android resources | Decoded manifest, string tables, locales and version facts | Caller-supplied Apktool launcher; resource guide |
| Flutter apps | Dart snapshot hash, per-ABI library digests and engine build provenance | None (static APK parsing); Flutter guide |
| Firmware | Regions, extraction results and native-analysis handoffs | Binwalk / Unblob on Linux; firmware guide |
| Recorded packets | Selected fields, repeated values, filters and decode-as rules | Linux: TShark 4.x + prlimit; capture guide |
| Packet summaries | Endpoints, DNS, TLS SNI, protocol distribution and HTTP requests | Caller-supplied tshark and capinfos (Linux-verified); pcap guide |
| Recorded logic signals | Decoder annotations, sample ranges and diagnostics | Linux: sigrok-cli 0.7.2 + prlimit; signal recordings |
| Packages and resources | File inventories, digests, plists, Apple bundle anatomy and extracted resources | Artifact and JavaScript guide, Apple applications |
| Process behavior | Terminal output, interactions, exit and filesystem observations, and run comparisons | Linux/macOS with a native PTY; process capture |
| PyInstaller executables | CArchive members, Python version, entry scripts and extracted bytecode | None (static only); Python packaged applications |
Static JavaScript and .NET inspection read the supplied files without running the application. Runtime capture runs or interacts with the selected target using your user permissions; each runtime guide describes its effects.
For offline native-binary inspection, REA also supports caller-supplied GNU objdump and Rizin. See the reverse-engineering tools guide for provider setup, CLI commands, and Evidence limitations. REA does not install or update either provider.
Native formats and host support vary by provider. See
Hopper and Ghidra setup, the
IDA guide (including an optional native MCP bridge), the
Kuna decompiler guide, and
experimental Windows Ghidra support.
Ghidra also supports 16-bit DOS analysis.
For large binaries, raise the provider's startup deadline with
REA_GHIDRA_STARTUP_TIMEOUT_MS or REA_HOPPER_STARTUP_TIMEOUT_MS.
For provider selection, see the CLI guide.
Check release availability
for features added since the latest npm release.
Showcases
DX-Ball: reconstruct a sound-pan calculation
Follow a sound call into its position-to-pan helper, inspect the instructions, and turn incomplete pseudocode into C. The reconstruction passes 3,205 original-x86 cases and reproduces all 63 compiled function bytes.
Read the case study · Reconstruction repository
Notion: trace the Electron clipboard bridge
Find the renderer's clipboard API, follow it through preload and IPC into the main process, and inspect the rich clipboard format.
TH04: recover a DOS bullet-ring calculation
Inspect the original PC-98 game's 16-bit instructions, recover the fixed and aimed angle calculations, and compare the reconstructed C++ with the historical compiler output.
Read the case study · Reconstruction repository
If you've used REA on something interesting, we'd love to see it. Share your case in an issue or a pull request, including the target, your question, how REA helped, and what you found.
FAQ
Which agents can use REA?
Any agent that supports local MCP servers. Setup configures the supported agents; other clients can use manual MCP registration.
Do I need Hopper, Ghidra or IDA?
Deep native analysis uses one of them. Static JavaScript and .NET inspection work without a native analysis engine. Setup can install Hopper after approval; Ghidra and IDA use your existing installations. See provider setup.
Do I need to start Hopper first?
REA starts Hopper when an operation needs it. On macOS, a first-run dialog may ask you to choose demo mode or activate your license. Complete that prompt in the same user session before your first CLI/MCP operation or unattended job. Open Hopper manually if needed. See Hopper startup and troubleshooting.
What does installing the skill from skills.sh do?
The skill supplies investigation instructions for your agent. Use npx rea-agents setup
to register REA's MCP server and install the matching instructions, then restart
your agent. See skill-only installation.
What code does REA return?
Native analysis returns pseudocode and assembly. JavaScript/Electron analysis recovers modules and their relationships. Your agent uses these findings to write and test an implementation; the showcases give worked examples.
Does REA upload my app?
REA analyzes targets locally. Your agent receives the tool results, and its model provider has its own data policy.
What should I do if I hit a bug?
Update first; a recent release may already fix it.
For a CLI installed with npm install --global or bun add --global:
rea update
For agent setup through npx:
npx rea-agents@latest setup
If you're using an agent, complete the setup refresh and restart it. Retry the same task. If the problem persists, open an issue with your REA version, target type, steps to reproduce and error output.
Documentation
Start with the website's worked guides. For exact options, prerequisites and result contracts:
- Installation and setup: agent registration, provider configuration, updates and uninstall.
- Readiness and troubleshooting: diagnose one agent or analysis engine.
- CLI and Evidence: commands, provider selection, snapshots, import/export and exit statuses.
- MCP contracts and agent prompts: tool results, sessions and guided investigations.
- Tool catalog: generated inventory of tools, providers and CLI commands.
- Roadmap: planned work and capability trackers.
Report vulnerabilities through SECURITY.md.
Star history
🎉 300,000 GitHub stars — thank you!
Thanks to everyone using REA, reporting bugs, requesting features, testing builds, and contributing fixes.
Disclaimer
See DISCLAIMER.md for responsible-use guidance.
The project's position on illegal or unauthorized use covers all REA versions, distribution channels, and platforms; each copy retains its applicable licenses.
REA is for lawful research, education, interoperability, software preservation, and analysis of software you own or are authorized to examine.
Contributing
We'd love your help with REA! Open an issue to report a bug or suggest a feature, or send a pull request to improve the code or docs.
See CONTRIBUTING.md for development setup and checks, testing for verification lanes, and the architecture map for selected layers and dependency paths.
License
REA-authored code is licensed under MIT. Third-party material retains its own licenses and copyright notices; see Third-party notices for the dependency inventory, preserved license texts, and external-tool terms.
You must legally obtain and be authorized to use commercial tools, including IDA Pro / Hex-Rays decompilers, Hopper, and JEB, under their applicable licenses. REA grants no tool license, key, or activation entitlement. Trials and demos remain subject to vendor terms, including user, feature, automation, and output sharing restrictions. Cracked copies, stolen keys, unauthorized key sharing, and bypassing license restrictions are not authorized. This guidance does not amend MIT or third-party licenses.