fd39977c32
* fix(desktop): keep a program word and a directory's neighbor The program after env stays the program even when a captured file sits in a folder of that name. A selected directory is not a database, so a neighboring file keeps the parent folder's spelling. * fix(desktop): record whether a selected path is a directory Capture stores the walked path's kind. A neighboring file of a selected directory keeps the parent folder's spelling even when that directory never changes and its children are not content roots. * fix(desktop): mark containing paths without a pairwise scan A recorded path marks its known ancestors as directories in one walk up the path, instead of comparing every recorded path with every other. * fix(desktop): keep a selected folder that is named like a database log A folder the caller selected stays a selected root when its name ends in -journal or -wal. A generated log beside a database file still does not. * fix(desktop): refuse a build command that exceeds the argument vector Splitting one argument still leaves the whole command under Linux's E2BIG limit. A request past that budget is refused before the process starts. * fix(desktop): remap a captured path in an env assignment The program word stays the program. A NAME=value assignment keeps its name and follows a captured path value when that path's spelling moves. * fix(desktop): keep oversized text out of draft guards A value or line longer than the draft's text bound is not copied into a guard, so one large frame cannot fill the task by itself. * docs(desktop): correct dconf and check-preview guidance A dconf version kept without its bytes is unreadable, not an empty key list. A values preview is copied into a check only when it is an uncut scalar. * fix(desktop): keep an empty env value empty An empty assignment is not a path. Resolving it named the working directory and rewrote the value when that directory's spelling moved. * fix(desktop): keep a run's font on the run, not the frame's text A formatting attribute such as Scribus FONT is not the document's words. Joining it across runs made a frame-wide text check of ItalicBold that failed when a run was split. The font stays a value check on its own run. * fix(desktop): do not pair JSON records by a selector-shaped field A field named @record_id matched the id suffix and became [@record_id=one], which reads an XML attribute. Records paired while their pointers matched nothing. Names that start with @ or > are not id fields. * fix(desktop): count a save-numbered id once when pairing members xml:id and draw:id values such as id123456 were both generated and numbered, so the same selector was counted twice and refused. A text edit of two elements keyed only by those ids now keeps its check. * fix(desktop): preserve selected state directory aliases * docs(desktop): explain tool and skill refresh prerequisites * fix(desktop): align nested state selections with aliases * fix(desktop): check build runtime export capability * fix(desktop): provide complete runtime repack command * fix(desktop): retain runtime probe failures * test(desktop): identify capture independently of schema preflight * fix(desktop): preserve document URLs and value formats * fix(desktop): bound added checks and omit noisy text guards * fix(desktop): exclude unseeded locks from task checks * fix(desktop): preserve draft bounds and launch URLs * fix(desktop): render draft values using their source format * fix(desktop): preserve launch URLs and JSON draft values * fix(desktop): recognize captured file URL documents * fix(desktop): render captured file URLs for runtime home * fix(desktop): distinguish phone numbers from save metadata * fix(desktop): preserve launch URLs and user text * fix(desktop): preserve captured URLs and user text * fix(desktop): preserve local file URL authority * fix(desktop): preserve local file URL authority * fix(desktop): preserve local file URL authority * fix(desktop): render captured file URLs at launch * fix(desktop): classify numeric timestamps using field context * fix(desktop): classify numeric timestamps using field context * fix(desktop): classify numeric timestamps using field context * fix(desktop): retain context for generated draft values * fix(desktop): retain context for generated draft values * fix(desktop): retain context for generated draft values * test(desktop): cover generated IDs in text guards * test(desktop): cover generated IDs in text guards * test(desktop): cover generated IDs in text guards * fix(desktop): isolate launcher URL encoding * fix(desktop): isolate launcher URL encoding * fix(desktop): isolate launcher URL encoding * fix(desktop): isolate launcher URL encoding * fix(desktop): retain clean text in noisy record fields * fix(desktop): classify added line values in one pass * fix(desktop): apply XML quote rules to text drafts * fix(desktop): distinguish XML attributes from quoted text * fix(desktop): preserve parsed XML line context * fix(desktop): retain partial XML syntax facts * fix(desktop): recognize markdown autolinks in drafts * fix(desktop): reuse export exclusions in task drafts * docs(desktop): clarify gzip scrub limits * style(desktop): format the noisy-record draft files with the pinned oxfmt Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> * test(desktop): move launch execution to boundary suite * fix(desktop): redact build schema failure output * refactor(desktop): normalize schema failure once * fix(desktop): omit unsafe schema parser snippets * fix(desktop): preserve draft change and selected path evidence * test(desktop): group retained dconf note regressions * fix(desktop): respect archive entry format in draft checks * test(desktop): separate unowned-file draft note cases * fix(desktop): preserve explicitly selected journal documents * fix(xml): avoid scanning selected ancestors per tag * fix(desktop): exclude covered text runs from draft counts * fix: preserve text when drafting desktop checks * fix: restore nested desktop state aliases * refactor: share UUID recognition across draft checks * fix: retain multiline XML attribute context * fix: retain relationship identifiers in task drafts * docs: clarify desktop draft identifier handling * test(desktop): type formatting run cases as pairs * test(desktop): separate markup boundary regression group * test(desktop): remove duplicate seed filename case * docs(desktop): clarify task checks before scratch export * fix(desktop): respell selected paths in file URLs * test(desktop): group captured document spelling cases * fix(desktop): bound draft preview serialization * fix(desktop): restore selected state aliases * fix(desktop): respect entry format in draft noise * test(desktop): match exported alias evidence at its JSON boundary * fix(desktop): retain app state logs in exported seeds * fix: align desktop numeric seed comparisons * test(desktop): keep one draft exclusion fixture import * test(desktop): retain log eligibility across draft test groups * style: fix desktop launch test formatting * style: format native command path schema * fix(desktop): map selected external launch paths * style(desktop): format seed document regressions * test(desktop): group launch URL regressions * fix(desktop): omit redundant nested state aliases * fix(desktop): compare added free text as a whole * fix(desktop): check recompressed seeds as shipped * docs(desktop): clarify recovered seed format * test(desktop): group shipped gzip seed checks * fix: retain quoted identifier text in task drafts * fix: recognize Unicode XML in desktop state readers * fix(desktop): bound nested draft checks * fix(desktop): explain missing arrays in truncated views * fix(desktop): find XML type references in archives * test(desktop): remove duplicated capture assertions * fix(desktop): retain nested omitted text boundaries * style(desktop): format draft value imports * test(desktop): group model and draft value checks * fix(desktop): map captured launch paths once * refactor: remove unused whole-text guard state * refactor: stop passing unused text children * test: align free-text checks with whole-note policy * fix: validate recompressed desktop archive seeds * style(desktop): format archive seed regression * fix(desktop): retain placed-item sibling guards * fix(desktop): redact runtime schema errors * fix(desktop): normalize captured file URLs * fix(desktop): report seeded files by capture path * fix(desktop): retain startup readiness failure stage * fix(desktop): retain JSON date checks * fix(desktop): preserve archive formatting checks * fix(desktop): preserve explicitly selected journal files * fix(desktop): report build command transport limits * docs(desktop): clarify unreadable dconf versions * test(desktop): remove duplicate history regression * fix(desktop): align XML names with exported reader * fix(desktop): scrub XML independently of reader compatibility * style(desktop): format review fixes * style(desktop): format capture review fixes --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: morluto <76467478+morluto@users.noreply.github.com> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
34 KiB
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 · Română · Български
REA: Reverse Engineer Anything
Binaries, applications aur runtime behavior ki reverse engineering ke liye ek MCP.
Koi feature pasand aaya? Samjhein ke woh kaise kaam karta hai, binary level tak.
Jaldi shuru karein · REA kaise kaam karta hai · Kya kuch analyze kar sakte hain · Amli misaalein · RL environments banayein · FAQ · Documentation
npx rea-agents setup
Important
REA morluto/rea, rea.tools ya rea-agents npm package se hasil karein. Installation aur release ke links inhi official sources se kholein. Sirf milta-julta repository naam ya copy kiya hua README kisi download ko official sabit nahi karta.
Kisi app mein aisa feature dekha jo aap apne product mein chahte hain? Apne agent se kahein ke REA ke zariye uski jaanch kare. Woh app ka source code mile baghair bhi use inspect kar sakta hai, feature kaam kaise karta hai samjha sakta hai, saboot dikha sakta hai aur aapke project ke liye uska ek version bana sakta hai.
REA aapke agent ko native binaries, JavaScript aur Electron apps, .NET assemblies aur websites inspect karne wale tools se jorta hai. Yehi tools terminal se bhi use kar sakte hain. Analysis local machine par hota hai, aur har natije ke saath uske saboot aur limitations bhi milti hain.
Setup REA ko aapke agent ke saath register karta hai aur uske mutabiq workflow instructions install karta hai. Native analysis ke liye pehle se installed Hopper, Ghidra, IDA ya Kuna use ho sakta hai; aapki approval par setup Hopper bhi install kar sakta hai. Static JavaScript analysis ke liye native analysis engine ki zaroorat nahi.
Setup instructions, tasveeron ke saath guides aur asli case studies ke liye REA ki website dekhein.
Jaldi shuru karein
Linux par Ghidra, JADX, firmware tools shuru karne aur static JavaScript/Electron
analysis ke liye REA ke PATH par procps-compatible ps hona chahiye, taake
process ownership check ho sake. Masla hal karne ke steps docs/getting-started/installation.md
ke "Linux owned-process prerequisite" section mein hain.
Apna agent setup karein
Node.js aur npm installed hon to yeh command chalayein:
npx rea-agents setup
Apne agents select karein, proposed changes dekhein aur approve karein. Setup REA ka MCP server aur matching workflow instructions add karta hai, aur existing configuration ke backups banata hai. Iske baad apna agent restart karein.
Setup Claude Code, Codex, Cursor, Gemini CLI, Grok Build aur doosre agents support karta hai. Provider configuration aur manual MCP registration ke liye installation aur setup dekhein.
Context overhead kam rakhne ke liye MCP default mein compact input schemas use
karta hai. Agar tamam advertised fields ki guidance aur nested validation details
chahiye hon to apni MCP registration mein REA_MCP_INPUT_SCHEMA_PROFILE=full
set karein. Dono profiles mein tamam tools aur canonical server validation
maujood rehte hain. MCP contracts guide ka "Compact input schema profile"
section dekhein.
Setup chuna hua runtime aur REA entry script seedha register karta hai. Package runner use karne par uski cache entry aur runtime barqarar rakhein; package target project se bahar kisi bharosemand directory se hasil karein. Installation guide dekhein.
Mukammal output schemas default mein advertise hote hain. Agar client tools/list ko limit karta hai to MCP registration mein REA_MCP_OUTPUT_SCHEMA_PROFILE=compact ya off set karein. Server validation aur structured results mukammal rehte hain. MCP contracts guide ka “Output schemas” section dekhein.
Apne agent se kahein
Samjho ke Notes app mein search kaise kaam karti hai, mujhe saboot dikhao aur
mere project ke liye aisa hi feature banao.
Notes ki jagah apni target app aur jis feature ko samajhna hai uska naam likhein.
Terminal se use karein
Extract ki hui JavaScript/Electron app directory ya ASAR inspect karein:
npx -y rea-agents@latest analyze-javascript-application /absolute/path/to/app --json
Natije mein modules, imports, Electron boundaries aur unke saboot milte hain.
Path ko apne target se badlein, jaise Windows par "D:/apps/example".
Rozmarra use ke liye rea command install karne ke liye:
npm install --global rea-agents
rea --help
Native analysis se pehle provider configure karein. Native commands, provider selection, snapshots aur scripting ke liye CLI aur Evidence guide dekhein.
REA update karein
REA mein tezi se changes aate hain aur naye releases mein aksar bug fixes hoti hain. Apni installation updated rakhein.
Agar CLI npm install --global ya bun add --global se install ki hai:
rea update
rea --update isi verified workflow ka alias hai aur wohi global output flags
accept karta hai. Doosre command controls ke saath use karte waqt rea update
likhein.
Updater commands stdout aur stderr mila kar zyada se zyada 4 MiB retain karti hain. Command khatam hone ke baad is had se bade metadata replies reject ho jate hain; verbose installs bounded diagnostics ke saath jari rehti hain. Insaan ke liye progress output terminal ki backpressure ka khayal rakhta hai aur bheji hui writes mukammal hone ka intezar karta hai.
Bun global updates ke liye Bun 1.2.17 ya naya version chahiye. Purana Bun ho
to rea update chalane se pehle Bun manually upgrade karein.
Agent registrations aur skill refresh karne ke liye update ke output mein di hui setup command chalayein.
Agar aap npx use karte hain to agent setup is tarah update karein:
npx rea-agents@latest setup
Setup changes review karein aur agent restart karein. Ek dafa chalane wali CLI
commands ke liye npx rea-agents@latest ke baad command likhein. Bun ke saath
npx rea-agents@latest ki jagah bunx rea-agents@latest use karein.
REA kaise kaam karta hai
Aapka agent MCP ke zariye REA ko call karta hai, taake target inspect kare aur relevant code trace kare. REA apni findings saboot ke saath wapas deta hai. Agent unki bunyaad par agle sawal poochta hai, behavior samjhata hai ya implementation likh kar test karta hai. CLI commands bhi yehi workflows use karti hain.
Puri size mein figure kholein.
Kya kuch analyze kar sakte hain
REA ke liye Node.js 22.x (>=22.23.4), 24.x (>=24.22.1) ya 26.12.1+, aur npm chahiye. Mazeed tools aur host support target par depend karte hain:
| Target | REA kya wapas deta hai | Zarooriyat aur guide |
|---|---|---|
| Desktop installations | Runtime candidates, supporting files, component markers aur agle probes | Built-in bounded directory/header inspection; desktop applications |
| Native binaries | Pseudocode, assembly, strings, symbols, calls aur references | Hopper, Ghidra, IDA ya Kuna; native analysis |
| Offline ELF layout | Sections, segments, original symbols/relocations aur static mitigation candidates | Linux x64 par aapka diya hua pwntools; binary diagnostics |
| Go binaries | Embedded compiler version, modules, replacements aur build settings | Built-in static ELF/PE/thin Mach-O inspection; Go install karna zaroori nahi |
| GPU code objects | CUDA/HIP targets, selected kernel parameters aur resources, retained PTX text | Built-in static ELF/PE/fatbin/CUBIN/PTX inspection; GPU code objects |
| Model artifacts | GGUF / safetensors metadata, tensor declarations aur unse nikale hue totals | Built-in header inspection; optional full-file hash; model files |
| IL2CPP metadata | Unity global-metadata.dat assembly images, type aur method names aur index ranges | Versions 24, 27, 29, 31 aur 39 ki built-in static decoding; Unity zaroori nahi |
| Godot PCK | Archive inventory aur extraction, original header/directory facts aur selected content identities | Built-in static formats 2, 3 aur 4; Godot zaroori nahi |
| Rust binaries | Embedded cargo-auditable crate names, versions, sources aur dependency edges | Built-in static ELF/PE/thin Mach-O inspection; Rust binaries |
| PE certificates | Authenticode WIN_CERTIFICATE entries aur PKCS#7 signer/X.509 identity fields | Built-in static PE inspection; PE certificates |
| PE imports | Import aur delay-load DLL names, ordinals, IAT RVAs aur pefile import hash | Built-in static PE inspection; PE imports |
| Windows shortcuts | Shell Link target, arguments, working dir, ExtraData and Tracker droid facts | Built-in static LNK inspection; Windows shortcuts |
| ELF notes | PT_NOTE/SHT_NOTE owners, types, GNU build-id aur ABI-tag fields | Built-in static ELF inspection; ELF notes |
| Binary hardening | PIE, NX, RELRO, CFG and related header flags for ELF, PE and Mach-O | Built-in static header inspection; binary hardening |
| Linux kernel modules | .modinfo keys, __versions CRCs, this_module presence, and signature trailer | Built-in static ELF inspection; kernel modules |
| Erlang BEAM | IFF chunks, atoms, exports, imports, lambdas aur Code header | Built-in static BEAM inspection; Erlang BEAM |
| WASM artifact | Validation, sections, exact import/export WAT forms aur decoded WAT | Aapka diya hua WABT 1.0.42; inspect_wasm_artifact |
| EVM bytecode | Dispatch selectors, byte offsets, inferred arguments aur mutability | Linux x64 par local raw/hex carrier; offline EVM guide |
| SQLite databases | Tables, columns, indexes, views, triggers aur selected ordinary-table rows | Local database/WAL snapshot; native SQLite limits ke saath Node.js 24.x >=24.15 ya 26+ |
| Apple IPS crash reports | Apple .ips metadata, threads, images aur crash classification | Built-in static JSON inspection; Apple IPS |
| Recorded Linux crashes | Raw notes, har recorded thread ke registers/signals aur optional mapping candidates | Linux x64 par aapka diya hua pwntools; optional GDB/pwndbg; recorded crashes |
| JavaScript / Electron | Modules, imports, source maps, routes, IPC aur native add-on relationships | Node.js aur npm; Linux: procps-compatible ps; application analysis |
| Websites | Page structure, scripts, network observations aur requested screenshots | Chrome-family browser; browser analysis |
| Saved network captures | Requests, responses, exposed payloads aur source locations | HAR ya Fiddler Everywhere SAZ; native mitmproxy ke liye Linux par mitmdump; capture guide |
| .NET assemblies | Metadata, CIL instructions, declared native dependencies aur build comparisons | Koi additional tool nahi (sirf static analysis); managed-code guide |
| Android APKs | Manifest declarations, classes, decompiled methods aur references | Linux/macOS/Windows x64 par headless JADX aur full JDK; Android guide |
| APK signatures | v1/v2/v3/v3.1 signers, certificate fingerprints, key rotation aur digest self-consistency | Koi additional tool nahi (sirf static analysis); inspect_apk_signature |
| Android devices | Devices, packages, processes, logs, dumps, screen captures aur APK/file transfers | Aapka diya hua adb (emulator ya hardware); ADB guide |
| JEB projects | Engine-backed project units, artifact digests aur type/method pseudo-code | Aapka shuru kiya hua JEB client jo MCP serve kar raha ho, REA_JEB_MCP_URL se select karein; JEB guide |
| Android resources | Decoded manifest, string tables, locales aur version facts | Aapka diya hua Apktool launcher; resource guide |
| Flutter apps | Dart snapshot hash, per-ABI library digests aur engine build provenance | Koi additional tool nahi (static APK parsing); Flutter guide |
| Firmware | Regions, extraction results aur native-analysis handoffs | Linux par Binwalk / Unblob; firmware guide |
| Recorded packets | Selected fields, repeated values, filters aur decode-as rules | Linux: TShark 4.x + prlimit; capture guide |
| Packet summaries | Endpoints, DNS, TLS SNI, protocol distribution aur HTTP requests | Aapke diye hue tshark aur capinfos (Linux par verified); pcap guide |
| Recorded logic signals | Decoder annotations, sample ranges aur diagnostics | Linux: sigrok-cli 0.7.2 + prlimit; signal recordings |
| Packages aur resources | File inventories, digests, plists, Apple bundle structure aur extracted resources | Artifact aur JavaScript guide, Apple applications |
| Process behavior | Terminal output, interactions, exit aur filesystem observations aur runs ka comparison | Native PTY ke saath Linux/macOS; process capture |
| PyInstaller executables | CArchive members, Python version, entry scripts aur extracted bytecode | Koi additional tool nahi (sirf static analysis); Python packaged applications |
| Deno compile binaries | Virtual files, entry point, recorded options, npm snapshot length | Static inspection; Deno compile executables |
Static JavaScript aur .NET inspection di hui files ko application chalaye baghair parhti hai. Runtime capture aapki user permissions se selected target ko chalata hai ya uske saath interact karta hai; har runtime guide apne effects batati hai.
Offline native-binary inspection ke liye REA aapke diye hue GNU objdump aur Rizin bhi support karta hai. Provider setup, CLI commands aur Evidence ki limitations ke liye reverse-engineering tools guide dekhein. REA in dono providers ko install ya update nahi karta.
Native formats aur host support har provider ke liye alag ho sakte hain.
Hopper aur Ghidra setup,
IDA guide (optional native MCP bridge samet),
Kuna decompiler guide aur
experimental Windows Ghidra support dekhein.
Ghidra 16-bit DOS analysis bhi support karta hai.
Badi binaries ke liye REA_GHIDRA_STARTUP_TIMEOUT_MS ya
REA_HOPPER_STARTUP_TIMEOUT_MS se provider ki startup deadline barhayein.
Provider select karne ke liye CLI guide dekhein.
Latest npm release ke baad add hone wale features ki
release availability check karein.
Amli misaalein
DX-Ball: sound-pan calculation dobara banayein
Sound call se uske position-to-pan helper tak jayein, instructions inspect karein aur adhoore pseudocode ko C mein badlein. Dobara banaya gaya code 3,205 original-x86 cases pass karta hai aur compiled function ke tamam 63 bytes dobara hasil karta hai.
Case study parhein · Reconstruction repository
Notion: Electron clipboard bridge trace karein
Renderer ki clipboard API dhoondein, preload aur IPC ke raste main process tak uska flow follow karein aur rich clipboard format inspect karein.
TH04: DOS bullet-ring calculation recover karein
Original PC-98 game ki 16-bit instructions inspect karein, fixed aur aimed angle calculations recover karein aur dobara banaye gaye C++ ko purane compiler ke output se compare karein.
Case study parhein · Reconstruction repository
REA se RL environments banayein
Web app session record karein, us ki API ko tools mein badlein aur AI agent ke liye environment export karein. AgentEnv ke saath chalayein, phir RL training ya evaluation ke liye tasks aur reward checks shamil karein.
Environment banane ki rehnumai · X par demo dekhein
Agar aapne REA se koi dilchasp kaam kiya hai to hum dekhna chahenge. Apna case issue ya pull request mein share karein. Target, apna sawal, REA ne kaise madad ki aur kya mila, yeh sab batayein.
RL environments banayein
AI agent ke liye local environment banayein jahan woh asal app chalaye baghair issue dhoondhne ya folder banane jaise kaam ki mashq kar sake. Ise reinforcement learning (RL) ya agent ke kaam poore karne ki salahiyat jaanchne ke liye istemal karein.
REA record kiye hue API requests aur responses ko aise tools mein badalta hai jinhein agent call kar sakta hai. Environment recorded data istemal karta hai aur sirf woh tabdeeliyan support karta hai jin ke asraat recording tasdeeq karti hai.
Agent mein REA setup karne ke baad neeche example URL aur folder tasks ko apne app ke mutabiq badlein:
Meri test web app se REA ke zariye RL environment banao:
http://127.0.0.1:3000
Folders ki list, creation, rename aur deletion cover karo. Test folders bana
aur hata sakte ho, lekin mojooda data tabdeel na karo.
my-env naam ke folder mein save karo, kaam karne wale operations check karo aur chalane ka tareeqa batao.
Command line istemal karein
Yeh commands tab istemal karein jab app ke browser requests aur responses ki recording pehle se file mein ho. Result chalane ke liye AgentEnv aur Docker bhi chahiye.
rea environment-build ./session.har ./my-env --name my-env --json
agent-env run ./my-env
REA chalne ke liye tayyar environment aur aik bunyadi test export karta hai jo us ka shuru hona aur jawab dena check karta hai. Apne RL framework ke saath task goals aur reward checks tay karein aur training chalayein.
Environment banane ki rehnumai · Environment reference · X par demo dekhein
Desktop app environments
REA Linux desktop app ka environment bhi bana sakta hai, jise agent screenshots, mouse aur keyboard se istemal karta hai. Aik line ki request se, jaise "Mere liye Gnote environment banao jis mein agent shopping list note mein olive oil shamil kare", aap ka agent app ko local build computer par install karta hai, task likhta hai, environment export karta hai aur naye computer par task check karta hai. Ise banane wali machine ko amd64 ya arm64 par Linux, Docker aur guide mein muqarrar agentenv framework version chahiye.
Desktop app environments setup karein
FAQ
Kaun se agents REA use kar sakte hain?
Har woh agent jo local MCP servers support karta ho. Setup supported agents configure karta hai; doosre clients manual MCP registration use kar sakte hain.
Kya mujhe Hopper, Ghidra, IDA ya Kuna chahiye?
Deep native analysis in mein se ek use karta hai. Static JavaScript aur .NET inspection native analysis engine ke baghair kaam karti hai. Approval ke baad setup Hopper install kar sakta hai; Ghidra, IDA aur Kuna ke liye aapki existing installations use hoti hain. Provider setup dekhein.
Kya pehle Hopper shuru karna hoga?
Jab kisi operation ko Hopper chahiye hota hai to REA use shuru karta hai. macOS par pehli dafa khulne wala dialog demo mode select karne ya license activate karne ko keh sakta hai. Pehle CLI/MCP operation ya unattended job se pehle usi user session mein yeh prompt complete karein. Zaroorat ho to Hopper manually kholein. Hopper startup aur troubleshooting dekhein.
skills.sh se skill install karne se kya hota hai?
Skill aapke agent ko jaanch karne ki instructions deti hai. REA ka MCP server
register karne aur matching instructions install karne ke liye
npx rea-agents setup use karein, phir agent restart karein.
Sirf skill ki installation dekhein.
REA kis tarah ka code wapas deta hai?
Native analysis pseudocode aur assembly wapas deta hai. JavaScript/Electron analysis modules aur unke relationships recover karta hai. Aapka agent in findings se implementation likhta aur test karta hai; amli misaalein iska tareeqa dikhati hain.
Kya REA meri app upload karta hai?
REA targets ko local machine par analyze karta hai. Aapke agent ko tool results milte hain, aur uske model provider ki apni data policy hoti hai.
Bug mile to kya karun?
Pehle update karein; ho sakta hai recent release mein masla hal ho chuka ho.
Agar CLI npm install --global ya bun add --global se install ki hai:
rea update
npx se agent setup ke liye:
npx rea-agents@latest setup
Agar agent use kar rahe hain to setup refresh complete karke agent restart karein. Wohi task dobara try karein. Masla phir bhi ho to REA version, target type, reproduce karne ke steps aur error output ke saath issue kholein.
Documentation
Website ki amli guides se shuru karein. Exact options, prerequisites aur result contracts ke liye:
- Installation aur setup: agent registration, provider configuration, updates aur uninstall.
- Readiness aur troubleshooting: ek agent ya analysis engine ka masla diagnose karein.
- CLI aur Evidence: commands, provider selection, snapshots, import/export aur exit statuses.
- MCP contracts aur agent prompts: tool results, sessions aur guided investigations.
- Tool catalog: tools, providers aur CLI commands ki generated inventory.
- Roadmap: planned work aur capability trackers.
Security vulnerabilities SECURITY.md ke zariye report karein.
Stars ki history
🎉 400,000 GitHub stars — shukriya!
REA use karne, bugs report karne, features suggest karne, builds test karne aur fixes contribute karne wale sab logon ka shukriya.
Zimmedarana istemal
Responsible-use guidance ke liye DISCLAIMER.md dekhein.
Ghair qanooni ya ghair ijazati istemal ke bare mein project ki position REA ke tamam versions, distribution channels aur platforms par lagu hoti hai; har copy par uske applicable licenses barqarar rehte hain.
REA qanooni research, taleem, interoperability, software preservation aur aise software ke analysis ke liye hai jo aapka apna ho ya jise examine karne ki aapko ijazat ho.
Hissa dalein
REA mein aapki madad ka khairmaqdam hai! Bug report karne ya feature suggest karne ke liye issue kholein, ya code aur docs behtar karne ke liye pull request bhejein.
Development setup aur checks ke liye CONTRIBUTING.md, verification lanes ke liye testing aur project structure ke liye architecture map dekhein.
License
REA ka apna likha hua code MIT ke tehat licensed hai. Third-party material ke apne licenses aur copyright notices barqarar rehte hain. Dependency inventory, preserved license texts aur external tools ki terms ke liye Third-party notices dekhein.
IDA Pro / Hex-Rays decompilers, Hopper aur JEB samet commercial tools qanooni tareeqe se hasil karna aur unke applicable licenses ke mutabiq use karne ki ijazat rakhna zaroori hai. REA koi tool license, key ya activation ka haq nahi deta. Trials aur demos vendor ki terms ke tehat rehte hain, jin mein user, feature, automation aur output sharing ki pabandiyan bhi shamil hain. Cracked copies, chori ki hui keys, ghair ijazati key sharing aur license restrictions bypass karne ki ijazat nahi. Yeh guidance MIT ya third-party licenses ko tabdeel nahi karti.