qybaihe/bla has 4,916 GitHub stars and 589 forks. GitHot measured +2,888 in 7 days. Last checked 2026-11-10 18:13 UTC. Last push 2026-11-02.
So werden diese Zahlen gemessen
🛡️ BLA (Blind LLM Agents) ist ein Schutzschild zur Abwehr von KI-Agenten für Reverse Engineering wie REA. Es schützt Binärdateien, Electron-Apps, JS-Bundles, Python und WebAssembly. Vergiften -> Erschöpfen -> Halluzinationen auslösen.
Gemessener Sternzuwachs
- in 24h
- Aktualisierung verzögert
- in 7 days
- +2.888
- in 15 days
- Verlauf wird gesammelt
- in 1 month
- Verlauf wird gesammelt
Nettoänderungen in überlappenden Zeiträumen, keine Tagessummen. Fehlende Messwerte bleiben leer. Sterne zeigen Interesse, nicht Qualität.
docs/readme/README_de.md
OriginalEnglish · 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
BLA: Blind LLM Agents
Ein MCP zum Schutz von Binärdateien, Anwendungen und Laufzeitverhalten gegen KI-gestütztes Reverse Engineering.
Schützen Sie Ihre Features. Machen Sie KI-Agenten bis auf die Binärebene blind.
Schnellstart · Wie BLA funktioniert · Was Sie schützen können · Showcases & Benchmarks · Häufige Fragen (FAQ) · Dokumentation
npx bla-agents setup · npx bla-agents defend ./dist --manifest
[!IMPORTANT] Get BLA from qybaihe/bla or the bla-agents npm package.
Befürchten Sie, dass jemand REA auf Ihre ausgelieferte App ansetzt und Ihre Kernlogik in Sekunden klont? Härten Sie Ihren Build mit BLA (Poison → Exhaust → Hallucinate).
BLA verbindet Ihren Agenten mit Schutzwerkzeugen für native Binärdateien, JavaScript- und Electron-Apps, WebAssembly, Python-Bytecode, SQLite-Datenbanken und KI-Modelle – 100 % lokal und ohne Laufzeiteinbußen.
Schnellstart
Agent einrichten
npx bla-agents setup
Agenten beauftragen
- 1. Audit (
Pre-flight REA Audit):Audit my ./dist directory against REA, show me every exposed module and IPC channel, and estimate how much it would cost Claude to reconstruct it. - 2. Protect (
Poison + Exhaust + Hallucinate):Protect ./dist/app.asar with BLA at bankrupt intensity, inject enclave chaff and algorithmic tarpits, and output to ./dist/app.shielded.asar. - 3. Verify (
Verify Defense & Token Burn):Verify ./dist/app.shielded.asar against the original ./dist/app.asar and confirm that REA's examination degrades to limited status.
Terminal verwenden
# 1. Audit exposure
npx -y bla-agents@latest audit /absolute/path/to/app --json
# 2. Protect artifact
npx -y bla-agents@latest protect /absolute/path/to/app -o /absolute/path/to/app.shielded --intensity bankrupt
# 3. Verify Counter-REA resistance
npx -y bla-agents@latest verify /absolute/path/to/app.shielded /absolute/path/to/app
# 4. Run 8-target Counter-REA benchmark
npx -y bla-agents@latest benchmark
# 5. Emit compile-time C/C++, Rust, or Go defense headers
npx -y bla-agents@latest emit-headers --lang c -o ./include/bla_shield.h
# Install globally
npm install --global bla-agents
bla --help
Im Bundler verwenden
import { defineConfig } from "vite";
import { blaVitePlugin } from "bla-agents/bundler";
export default defineConfig({
plugins: [blaVitePlugin({ intensity: "bankrupt", enableHoneySourceMaps: true })],
});
BLA aktualisieren
bla update
npx bla-agents@latest setup
Wie BLA funktioniert
- Poison (
Architectural Chaff & Honey Assets): Embeds hardware enclave delegation manifests (SGX/TPM2/Secure Enclave), VLQ v3 Honey Source Maps (enclave://tee-runtime/), honey WASM"name"sections, and honey SQLite tables. - Exhaust (
Semantic Budget Breakers & Algorithmic Tarpits): TripsREA's internal analyzer limits (primitive-candidates > 256,alias-selections > 512,getter-expansion > 512,primitive-bytes > 1 MiB,maximum_rustc_hashes > 64,maximumSentinelsPerSlice > 32) and weaves 14–36 Fake XRef state machines. - Hallucinate (
Anti-CDP Runtime Deception & Fuse Hardening): Hardens Electron V1 fuse wires (RunAsNode=0,EnableNodeCliInspectArguments=0) and serves synthetic enclave telemetry to CDP/Inspector/Frida probes.
Was Sie schützen können
| Target | What BLA injects & how REA fails | Command / prompt & requirements |
|---|---|---|
| JavaScript / TypeScript | Trips primitive-candidates > 256, alias-selections > 512, getter-expansion > 512 + 36 tarpits |
bla protect app.js · Built-in Babel AST engine |
Electron .asar apps |
De-literalizes IPC channels (channel: null), adds duplicate decoy IPC handlers & shadow module |
bla protect app.asar · Built-in Chromium Pickle .asar unpacker & SHA-256 repacker |
| Electron binary fuses | Hardens real V1 fuses (RunAsNode=0, Inspect=0) + injects 34 > 32 decoy fuse sentinels |
bla protect ElectronApp · Trips ElectronFuseResourceFailure (maximumSentinelsPerSlice = 32) |
| Native / Rust / Go | Injects 68 > 64 /rustc/<40-hex>/ paths, decoy .dep-v0 crate graph & Go dep\t lines |
bla protect daemon.elf · Built-in ELF64, Mach-O, and PE/COFF shield |
| Flutter / Dart AOT | Injects 66 > 64 Dart snapshot headers (0xf5f5dcdc) + 6 > 4 LLVM toolchain lines |
bla protect libapp.so · Trips SnapshotHashScanner (capped: true) |
| WASM artifacts | Strips debug sections; injects honey "name" section (tee_hardware_enclave_stub) + custom chaff |
bla protect core.wasm · Built-in LEB128 binary parser; 100% WebAssembly.validate |
Python & .pyc |
Injects Python tarpit state machines into .py & TYPE_ASCII marshal chaff into .pyc pools |
bla protect module.pyc · Built-in CPython 3.7–3.14 .pyc marshal shield |
| SQLite databases | Injects 3 enclave honey tables with GENERATED ALWAYS AS (bla_enclave_unseal(...)) VIRTUAL traps |
bla protect data.sqlite · Trips SqliteColumnEvaluationFailure on REA preview |
| Model artifacts | Injects 35 > 32 nested JSON/ARRAY headers into .safetensors and .gguf model headers |
bla protect weights.safetensors · Trips ModelFormatFailure (json-nesting / metadata-nesting > 32) |
| Android DEX & IL2CPP | Injects Lcom/enclave/sgx/... decoy classes into classes.dex (valid SHA-1/Adler32) & Il2Cpp |
bla protect classes.dex or global-metadata.dat · Pollutes JADX/JEB & IL2CPP recovery |
Showcases & Benchmarks
| Showcase Target | Before BLA (REA Alone) | After npx bla-agents protect |
Token Burn | Runtime Check |
|---|---|---|---|---|
1. DX-Ball Sound-Pan Calculation (.js) |
84/100 · 4,800 tok · $0.20 (COMPLETE) |
2/100 · 10,182,068 tok · $160.64 (LIMITED) |
2,121.3x | ✅ 100% Exact |
2. Notion Electron Clipboard Bridge (.asar) |
98/100 · 9,132 tok · $0.34 (COMPLETE) |
2/100 · 23,125,000 tok · $358.28 (LIMITED) |
2,532.3x | ✅ 100% Exact |
3. Enterprise Offline License Validator (.ts) |
84/100 · 4,800 tok · $0.20 (COMPLETE) |
2/100 · 10,182,169 tok · $160.64 (LIMITED) |
2,121.3x | ✅ 100% Exact |
4. WebAssembly Crypto Kernel (.wasm) |
81/100 · 4,800 tok · $0.20 (COMPLETE) |
6/100 · 1,807,067 tok · $29.88 (LIMITED) |
376.5x | ✅ 100% Exact |
| 5. Native ELF64 Binary (Rust / Go / Fuse / Dart) | 81/100 · 9,278 tok · $0.35 (COMPLETE) |
2/100 · 3,698,135 tok · $59.72 (LIMITED) |
398.6x | ✅ 100% Exact |
6. Local SQLite Entitlement Database (.sqlite) |
81/100 · 10,568 tok · $0.29 (COMPLETE) |
7/100 · 1,711,235 tok · $28.36 (LIMITED) |
161.9x | ✅ 100% Exact |
7. Proprietary Edge AI Weights (.safetensors) |
81/100 · 4,800 tok · $0.20 (COMPLETE) |
6/100 · 1,807,073 tok · $29.88 (LIMITED) |
376.5x | ✅ 100% Exact |
8. Android Dalvik Bytecode (classes.dex) |
81/100 · 8,900 tok · $0.34 (COMPLETE) |
7/100 · 2,786,285 tok · $45.09 (LIMITED) |
313.1x | ✅ 100% Exact |
Häufige Fragen (FAQ)
Which agents can use BLA?
Any agent that supports local MCP servers or SKILL.md workflows (Claude Code, Cursor, Codex, Gemini CLI, Windsurf, Google Antigravity, OpenCode, VS Code, and GitHub Copilot CLI). Run npx bla-agents setup.
Does BLA slow down my app or change its runtime output?
No. All semantic budget breakers and tarpits are guarded by $O(1)$ number-theoretic opaque predicates ($7x^2 - 1 \neq y^2 \pmod 7$) and preserve 100% input/output equivalence.
Do I need Hopper, Ghidra, IDA, or WABT installed?
No. All 19 format shields are built directly into bla-agents with zero external dependencies.
Does BLA upload my source code or binaries anywhere?
Never. All operations run 100% locally on your machine.
Dokumentation
Ähnliche Projekte entdecken
affaan-m/ECC
System zur Leistungsoptimierung für das Ausführungs- und Steuerungsframework von Agenten. Es bietet Skills, Instinkte, Memory, Sicherheit und forschungsorientierte Entwicklung für Claude Code, Codex, Opencode, Cursor und darüber hinaus.
300,771 SterneNousResearch/hermes-agent
Der Agent, der mit dir wächst
262,431 Sternemultica-ai/andrej-karpathy-skills
Eine einzelne CLAUDE.md-Datei zur Verbesserung des Verhaltens von Claude Code, abgeleitet aus Andrej Karpathys Beobachtungen zu Fallstricken beim Programmieren mit LLMs.
231,848 Sternefirecrawl/firecrawl
Stärke deine KI-Agenten mit Daten aus dem Web und darüber hinaus. Wir bauen die Bibliothek für Superintelligenz. 🔥
200,444 Sterne