Skip to main content
Glama

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

Tensor: 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.

npm version MCP tool catalog Node.js requirements skills.sh MIT license Discord

Website · Guides · Showcases

Quick start · How Tensor works · What you can analyze · Showcases · Build RL environments · FAQ · Documentation

npx tensor-agents setup

IMPORTANT

Get Tensor fromtensor-9/tensor, tensor.tools, or the tensor-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 Tensor. It can inspect the app without its source code, explain how the feature works, show the evidence, and build a version for your project.

Tensor 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 Tensor with your agent and installs matching workflow instructions. Native analysis can use an existing Hopper, Ghidra, IDA or Kuna installation; setup can optionally install Hopper with approval. Static JavaScript analysis needs no native analysis engine.

Visit the Tensor 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 system ps for process ownership checks. Recovery steps are in docs/getting-started/installation.md under "Linux owned-process prerequisite".

Install

With Node.js and npm installed, run:

npm install --global tensor-agents
tensor setup

tensor setup configures your agents and installs matching workflow instructions. Prefer not to install globally? npx tensor-agents setup runs the same setup without a persistent install.

Set up your agent

Choose your agents, review the proposed changes, and approve them. Setup adds Tensor's MCP server and matching workflow instructions, with backups of existing configuration. Restart your agent afterward. Setup records the selected runtime and Tensor entry script directly. If acquired through a package runner, keep its cache entry available. Run package acquisition from a trusted directory outside the target project. Installation and recovery details are in the setup guide below.

Setup supports Claude Code, Codex, Cursor, Gemini CLI, Grok Build and other agents. See installation and setup for provider configuration, manual MCP registration, Claude Code/Codex plugins, and the Cursor Marketplace plugin.

MCP advertises compact input schemas to reduce context overhead; guidance a compact schema omits follows the tool description. The full tool set and canonical server validation are unchanged. See "Compact input schema profile" in the MCP contracts guide.

Output schemas are omitted from tools/list by default: no model API reads them, and Tensor validates every result itself. Set TENSOR_MCP_OUTPUT_SCHEMA_PROFILE=compact to advertise each output schema within a 4,096-byte budget. Both settings keep canonical server-side validation and complete structured results. See "Output schemas" 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 tensor-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 tensor command for regular use:

npm install --global tensor-agents
tensor --help

For native analysis, configure a provider first. See the CLI and Evidence guide for native commands, provider selection, snapshots and scripting.

Update Tensor

Tensor 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:

tensor update

tensor --update is an alias for this verified workflow and accepts the same global output flags. Use tensor 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 tensor 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 tensor-agents@latest setup

Review the setup changes and restart your agent. For one-off CLI commands, use npx tensor-agents@latest followed by the command. With Bun, use bunx tensor-agents@latest in place of npx tensor-agents@latest.

Related MCP server: REA

How Tensor works

Your agent calls Tensor through MCP to inspect the target and trace relevant code. Tensor 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.

Tensor investigation flow: your agent asks about a local target, Tensor inspects and traces it using analysis tools, and the agent uses the returned code, references and unknowns to explain, implement and test.

Open the full-size figure.

What you can analyze

Tensor 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 Tensor 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, IDA or Kuna; 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/WebAssembly module inspection; Rust binaries

PE certificates

Authenticode WIN_CERTIFICATE entries and PKCS#7 signer/X.509 identity fields

Built-in static PE inspection; PE certificates

PE imports

Import and delay-load DLL names, ordinals, IAT RVAs and 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, and supported note metadata

Built-in static ELF inspection; ELF notes

DWARF compile units

Compile-unit name, directory, producer, language, and dwo_name

Built-in static ELF, Mach-O, and PE inspection; DWARF compile units

ELF dependencies

DT_NEEDED, SONAME, RPATH/RUNPATH, GNU versions, and undefined imports

Built-in static ELF inspection; ELF dependencies

Binary hardening

PIE, NX, RELRO, CFG and related header flags for ELF, PE and Mach-O

Built-in static header inspection; binary hardening

Apple IPS crashes

.ips metadata, threads, images, registers and documented crash classes

Built-in static JSON inspection; Apple IPS

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 and the Code header

Built-in static BEAM inspection; Erlang BEAM

NuGet packages

Package identity, dependency groups, license, repository and ZIP contents

Built-in static .nupkg inspection; NuGet packages

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, native add-ons, tensor audit-release-exposure

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 TENSOR_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

Bundled UEFI/NVAR; external 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

Deno compile binaries

Virtual files, entry point, recorded options, npm snapshot length

None (static only); Deno compile executables

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, Tensor also supports caller-supplied GNU objdump and Rizin. See the reverse-engineering tools guide for provider setup, CLI commands, and Evidence limitations. Tensor 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 TENSOR_GHIDRA_STARTUP_TIMEOUT_MS or TENSOR_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.

Read the case study

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

Build RL environments with Tensor

Record a web app session, turn its API into tools, and export an environment an AI agent can use. Run it with AgentEnv, then add tasks and reward checks for RL training or evaluation.

Read the guide · Watch the video

If you've used Tensor 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 Tensor helped, and what you found.

Build RL environments

Give an AI agent a local environment to practice tasks such as finding an issue or creating a folder, without running the original app. Use it for reinforcement learning (RL) or to test how well an agent completes tasks.

Tensor turns recorded API requests and responses into tools the agent can call. The environment uses the recorded data and supports changes only when the recording confirms their effects.

With Tensor set up in your agent, replace the example URL and folder tasks below with your own:

Use Tensor to build an RL environment from my test web app at
http://127.0.0.1:3000.
Cover listing, creating, renaming, and deleting folders. You may create and
remove test folders. Leave existing data unchanged.
Save it in a folder named my-env. Check which operations work and tell me
how to run it.

Use these commands if you already have a file containing the app’s recorded browser requests and responses. Running the result also requires AgentEnv and Docker.

tensor environment-build ./session.har ./my-env --name my-env --json
agent-env run ./my-env

Tensor exports a runnable environment with a basic test to check that it starts and responds. Use it with your RL framework to define task goals, add reward checks, and run training.

Build an environment · Environment reference · Watch the demo on X

Desktop app environments

Tensor can also build an environment of a Linux desktop app, which an agent uses through screenshots, the mouse and the keyboard. From a one-line request, such as "Build me a Gnote environment where the agent adds olive oil to the shopping list note", your agent installs the app on a local build computer, writes the task, exports the environment and checks the task in a fresh computer. The machine that builds it needs Linux on amd64 or arm64, Docker and the agentenv framework version the guide pins.

Set up desktop app environments

FAQ

Any agent that supports local MCP servers. Setup configures the supported agents; other clients can use manual MCP registration.

Deep native analysis uses Hopper, Ghidra, IDA or Kuna, depending on the target and operation. Static JavaScript and .NET inspection work without a native analysis engine. Setup can install Hopper after approval; Ghidra, IDA and Kuna use your existing installations. See provider setup for the options and their supported targets.

Tensor 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.

The skill supplies investigation instructions for your agent. Use npx tensor-agents setup to register Tensor's MCP server and install the matching instructions, then restart your agent. See skill-only installation.

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.

Tensor analyzes targets locally. Your agent receives the tool results, and its model provider has its own data policy.

Update first; a recent release may already fix it.

For a CLI installed with npm install --global or bun add --global:

tensor update

For agent setup through npx:

npx tensor-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 Tensor version, target type, steps to reproduce and error output.

Documentation

Start with the website's worked guides. For exact options, prerequisites and result contracts:

Report vulnerabilities through SECURITY.md.

Star history

🎉 400,000 GitHub stars — thank you!

Thanks to everyone using Tensor, 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 Tensor versions, distribution channels, and platforms; each copy retains its applicable licenses.

Tensor 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 Tensor! 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. See the testing guide for verification lanes.

License

MIT

Tensor-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. Tensor 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.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Connects AI agents and CLI users to local analysis tooling that inspects native binaries, JavaScript/Electron apps, .NET assemblies, websites, and saved network captures, returning evidence-backed findings with their limitations. This lets users understand how an existing app feature works and rebuild a similar version in their own project.
      129 npm
      6
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Connects AI agents to local analysis tools that inspect native binaries, JavaScript/Electron apps, .NET assemblies, and websites without source code, so features can be explained, traced, and rebuilt. Every finding is returned with its supporting evidence and stated limitations.
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Lets agents inspect native binaries, JavaScript/Electron applications, .NET assemblies, websites, and runtime behavior, returning evidence-backed findings and limitations for understanding and reimplementing features.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Connects coding agents to local analysis tools that inspect native binaries, JavaScript/Electron apps, .NET assemblies, and websites, returning findings with supporting evidence and stated limitations. This lets an agent explain how an existing feature works without source code and then build an equivalent implementation for the user's own project.
      MIT