finite-monkey-engine
starsforks
How to install finite-monkey-engine?
bradmoonuestc/finite-monkey-engine
$git clone https://github.com/BradMoonUESTC/finite-monkey-engineSecurity analysis pipeline for code auditing: Planning → Reasoning → Validation. Results are persisted to PostgreSQL and can be exported as reports.
README.md
| 1 | # Finite Monkey Engine v3.0 |
| 2 | |
| 3 | Security analysis pipeline for code auditing: **Planning → Reasoning → Validation**. |
| 4 | Results are persisted to PostgreSQL and can be exported as reports. |
| 5 | |
| 6 | ## v3.0 Updates |
| 7 | |
| 8 | - **Planning**: removes RAG / chunks / call graph / call tree. Keeps tree-sitter function parsing and uses Codex CLI to extract business flows (Gi/Fi). Tasks persisted as **Fi × checklist (rule_key)**. |
| 9 | - **Reasoning**: switches the main scan execution to **Codex CLI** (input: `business_flow_code + prompt`). Output remains the original **multi-vulnerability JSON**, then split into `project_finding` (unchanged downstream logic). |
| 10 | - **Validation**: Codex-based confirmation for `project_finding` and write-back to `validation_status` / `validation_record`. |
| 11 | - **Workspace restriction**: Codex always runs with `--cd <project_root>` derived from `src/dataset/agent-v1-c4/datasets.json[project_id].path`. |
| 12 | - **Design docs**: moved into `docs/`. |
| 13 | |
| 14 | ## 🚀 v2.0 Major Upgrades |
| 15 | |
| 16 | **Finite Monkey Engine v2.0** brings significant architectural upgrades and feature enhancements: |
| 17 | |
| 18 | ### 🔥 Core Upgrades |
| 19 | - **🎯 Precision Language Support**: Focus on 4 core languages (Solidity/Rust/C++/Move) for optimal analysis experience |
| 20 | - **🧠 RAG Architecture Optimization**: New LanceDB merged 2-table architecture with 300% query efficiency improvement |
| 21 | - **📊 Intelligent Context Understanding**: Multi-dimensional embedding technology, significantly enhanced code comprehension |
| 22 | - **⚡ Performance Optimization**: Unified storage strategy, 50% memory reduction, improved concurrent processing |
| 23 | - **🔍 Deep Business Analysis**: Enhanced business flow visualization and cross-contract dependency analysis |
| 24 | |
| 25 | ## 🎯 Overview |
| 26 | |
| 27 | Finite Monkey Engine is an advanced AI-driven code security analysis platform **focused on blockchain and system-level code security auditing**. By integrating multiple AI models and advanced static analysis techniques, it provides comprehensive, intelligent security auditing solutions for core programming language projects. |
| 28 | |
| 29 | ### 🌍 Multi-Language Support |
| 30 | |
| 31 | Built on Tree-sitter parsing engine and function-level analysis architecture, **v2.0 focuses on 4 core languages** for optimal analysis experience: |
| 32 | |
| 33 | **✅ Currently Fully Supported Languages:** |
| 34 | - **Solidity** (.sol) - Ethereum smart contracts with complete Tree-sitter support |
| 35 | - **Rust** (.rs) - Solana ecosystem, Substrate, system-level programming |
| 36 | - **C/C++** (.c/.cpp/.cxx/.cc/.C/.h/.hpp/.hxx) - Blockchain core, node clients |
| 37 | - **Move** (.move) - Aptos, Sui blockchain language |
| 38 | - **Go** (.go) - Blockchain infrastructure, TEE projects~~ |
| 39 | |
| 40 | **🔄 Planned Support (Future Versions):** |
| 41 | - ~~**Cairo** (.cairo) - StarkNet smart contract language~~ |
| 42 | - ~~**Tact** (.tact) - TON blockchain smart contracts~~ |
| 43 | - ~~**FunC** (.fc/.func) - TON blockchain native language~~ |
| 44 | - ~~**FA** (.fr) - Functional smart contract language~~ |
| 45 | - ~~**Python** (.py) - Web3, DeFi backend projects~~ |
| 46 | - ~~**JavaScript/TypeScript** (.js/.ts) - Web3 frontend, Node.js projects~~ |
| 47 | - ~~**Java** (.java) - Enterprise blockchain applications~~ |
| 48 | |
| 49 | > 💡 **v2.0 Design Philosophy**: Focus on core languages to provide deeply optimized analysis capabilities. Based on function-granularity code analysis architecture, theoretically extensible to any programming language. Future versions will gradually support more languages. |
| 50 | |
| 51 | ## 🚀 v2.0 Key Features |
| 52 | |
| 53 | ### 🧠 Enhanced AI-Powered Analysis |
| 54 | - **Multi-Model Collaboration**: Claude-4 Sonnet, GPT-4 and other AI models working intelligently together |
| 55 | - **RAG-Enhanced Understanding**: Multi-dimensional context-aware technology based on LanceDB |
| 56 | - **Deep Business Logic Analysis**: Deep understanding of DeFi protocols, governance mechanisms, and tokenomics |
| 57 | - **Intelligent Vulnerability Discovery**: AI-assisted complex vulnerability pattern recognition |
| 58 | |
| 59 | ### 🔍 Comprehensive Security Detection System |
| 60 | - **Precision Vulnerability Detection**: Focus on core languages for more accurate vulnerability identification |
| 61 | - **Cross-Contract Deep Analysis**: |
People who liked this also viewed
6 picksType
- Resk-LLM Resk is a robust Python library designed to enhance security and manage context when interacting with LLMs. It provides a protective layer for API calls, safeguarding against common vulnerabilities and ensuring optimal performance. And safe layer again Prompt Injection. PromptsJun 2026
- agentic-ai-prompt-researchResearch into how agentic AI coding assistants work. Reconstructed prompt patterns, agent coordination, and security classificationPromptsMar 2026
- promptmapa security scanner for custom LLM applicationsPromptsDec 2025
- prompt-hacker-collectionsprompt attack-defense, prompt Injection, reverse engineering notes and examples | 提示词对抗、破解例子与笔记 PromptsFeb 2025
- acipThe Advanced Cognitive Inoculation PromptPromptsMar 2026
- ToolEmu[ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool usePromptsMar 2024
