awesome-repositories.com
Blog
awesome-repositories.com

Découvrez les meilleurs dépôts open-source grâce à notre recherche par IA.

ExplorerRecherches sélectionnéesAlternatives open sourceLogiciels auto-hébergésBlogPlan du site
ProjetÀ proposNotre méthodologiePresseServeur MCP
Mentions légalesConfidentialitéConditions d'utilisation
© 2026 Bringes Technology SRL·VAT RO45896025·hello@awesome-repositories.com
·
lintsinghua avatar

lintsinghua/DeepAudit

0
View on GitHub↗
4,668 stars·544 forks·Python·agpl-3.0·3 vues

DeepAudit

DeepAudit is a privacy-preserving code audit platform that combines multiple specialized AI agents to identify and verify security vulnerabilities in source code. It functions as a local LLM vulnerability scanner, an automated security report generator, and a sandboxed exploit verifier, all operating entirely within an internal network to keep sensitive code and data on premises.

What distinguishes DeepAudit is its multi-agent cooperative approach: teams of AI agents jointly plan, analyze, and cross-check findings across the codebase, moving beyond single-pass scanning. The platform also sandbox-confirms exploitability by running proof-of-concept scripts in an isolated environment, reducing false positives while validating real-world risk. All analysis runs locally using on-premises large language models, ensuring no data leaves the internal network.

DeepAudit complements these differentiators with configurable audit scopes — allowing teams to target specific directories and file patterns — and rule-based vulnerability matching against known patterns. After analysis, it automatically produces a structured report with severity levels and remediation steps.

Features

  • Cooperative AI Auditors - Teams of specialized AI agents cooperatively plan, analyze, and verify vulnerabilities across the codebase.
  • Security Audit Reports - Aggregates findings, severity levels, and remediation steps into a structured report automatically after analysis.
  • Local Model Runtimes - Perform analysis locally using internal-network models to ensure data never leaves the premises.
  • Local Inference Engines - Runs large language models entirely within the internal network for analysis, ensuring data never leaves the premises.
  • Privacy-Preserving Code Auditors - Runs entirely within the internal network, ensuring source code and analysis remain on premises.
  • Sandboxed Exploit Verifiers - Executes PoC exploit scripts in a controlled sandbox to confirm vulnerability exploitability without risk.
  • Security and Vulnerability Scanning - Scan source code and configuration files for security vulnerabilities using rule-based analysis and known databases.
  • Vulnerability Detection - Compare code against known vulnerability patterns to detect security flaws and misconfigurations.
  • Security Report Generation - Producing a comprehensive report with findings, severity levels, and remediation steps automatically after the audit completes.
  • LLM-Orchestrated Scanners - Automates vulnerability scanning by orchestrating local large language models for private code analysis.
  • Source Code Vulnerability Scanning - Scanning source code and configuration files for known security vulnerabilities using rule-based pattern matching and vulnerability databases.
  • Audit Scope Configurations - Specify which directories and file patterns the audit scans to focus analysis on relevant code.
  • Vulnerability Matching - Scans code by comparing against a database of known vulnerability patterns and signature rules.

Historique des stars

Graphique de l'historique des stars pour lintsinghua/deepauditGraphique de l'historique des stars pour lintsinghua/deepaudit

Recherche par IA

Explorez plus de dépôts awesome

Décrivez vos besoins en langage naturel — l'IA classe des milliers de projets open source sélectionnés par pertinence.

Start searching with AI

Questions fréquentes

Que fait lintsinghua/deepaudit ?

DeepAudit is a privacy-preserving code audit platform that combines multiple specialized AI agents to identify and verify security vulnerabilities in source code. It functions as a local LLM vulnerability scanner, an automated security report generator, and a sandboxed exploit verifier, all operating entirely within an internal network to keep sensitive code and data on premises.

Quelles sont les fonctionnalités principales de lintsinghua/deepaudit ?

Les fonctionnalités principales de lintsinghua/deepaudit sont : Cooperative AI Auditors, Security Audit Reports, Local Model Runtimes, Local Inference Engines, Privacy-Preserving Code Auditors, Sandboxed Exploit Verifiers, Security and Vulnerability Scanning, Vulnerability Detection.

Quelles sont les alternatives open-source à lintsinghua/deepaudit ?

Les alternatives open-source à lintsinghua/deepaudit incluent : securego/gosec — gosec is a static analysis security tool designed to scan Go source code for vulnerabilities and common coding flaws.… crytic/slither. pycqa/bandit — Bandit is a static analysis security testing tool and vulnerability detection scanner for Python source code. It… snyk/cli — The Snyk CLI is a command-line security scanner that detects known vulnerabilities across open-source dependencies,… ajinabraham/nodejsscan — nodejsscan is a static analysis security tool and vulnerability detection engine designed to scan Node.js source code… bearer/bearer — Bearer is a static analysis security testing tool and privacy compliance auditor. It identifies security…

Alternatives open source à DeepAudit

Projets open source similaires, classés selon le nombre de fonctionnalités partagées avec DeepAudit.
  • securego/gosecAvatar de securego

    securego/gosec

    8,866Voir sur GitHub↗

    gosec is a static analysis security tool designed to scan Go source code for vulnerabilities and common coding flaws. It functions as a security analyzer that inspects the abstract syntax tree to identify insecure function calls, API usage, and potential security risks. The tool distinguishes itself by mapping detected vulnerabilities to Common Weakness Enumeration identifiers for standardized reporting and integrating with external AI models to suggest code fixes for identified issues. Its capabilities cover the detection of injection vulnerabilities, hardcoded credentials, weak cryptograph

    Go
    Voir sur GitHub↗8,866
  • crytic/slitherAvatar de crytic

    crytic/slither

    6,141Voir sur GitHub↗
    Pythonethereumsoliditystatic-analysis
    Voir sur GitHub↗6,141
  • pycqa/banditAvatar de PyCQA

    PyCQA/bandit

    8,092Voir sur GitHub↗

    Bandit is a static analysis security testing tool and vulnerability detection scanner for Python source code. It functions as a security-focused linter and static analyzer that identifies common vulnerabilities and architectural flaws without executing the program. The tool utilizes an abstract syntax tree to analyze code patterns and identifies risky function calls or insecure configurations. It employs a plugin-based rule engine to decouple scanning logic from individual security checks and supports configuration-driven filtering to exclude specific files or ignore certain warnings. The sy

    Pythonbanditlinterpython
    Voir sur GitHub↗8,092
  • snyk/cliAvatar de snyk

    snyk/cli

    5,428Voir sur GitHub↗

    The Snyk CLI is a command-line security scanner that detects known vulnerabilities across open-source dependencies, proprietary application code, container images, and infrastructure-as-code configuration files. It also serves as a platform management tool, allowing users to configure organizations, users, SSO, and reporting from the terminal rather than the web dashboard. The CLI integrates directly into development workflows, enabling scanning within IDEs, build pipelines, and version control systems. It implements static analysis with interfile data flow analysis to find complex security f

    TypeScriptmonitorsecuritysnyk
    Voir sur GitHub↗5,428
Voir les 30 alternatives à DeepAudit→