Developer Tools●●Solid
RedDragon, LLM-assisted IR analysis of code across languages
LLM-assisted compiler frontend for 15 languages, but unclear if it outperforms static AST analysis alone.
Big BrainWizardryNiche Gem
armorer
103mo ago
Back to browse
GitHub Repository
Multi-language code execution through a simple IR and deterministic VM with LLM repair / patching
10 starsPython
RedDragon, LLM-assisted IR analysis of code across languages
by armorer·Mar 5, 2026·2 points·1 comment
AI Analysis
●●●BangerWizardryBig BrainNiche Gem
LLM-assisted IR repair for decompiled and incomplete code across 15 languages.
Strengths
- •Novel constraint: deterministic parsing + LLM only at true information boundaries
- •Universal 27-opcode IR with source location traceability bridges languages elegantly
- •Handles real-world mess (missing deps, unresolved imports) via speculative VM execution
Weaknesses
- •Narrow audience (reverse engineering, binary analysis, legacy migration)
- •LLM repair robustness unclear; no public benchmarks on real decompiled binaries
Category
Target Audience
Security researchers, binary analysis engineers, legacy system maintainers
Similar To
Ghidra · RetDec · Radare2
Similar Projects
Security●●Solid
Reverse Engineering Tools MCP Server
Sandboxed MCP server lets LLMs run Ghidra and Radare2 without blowing up your host.
Niche GemShip It
dclavijo
102mo ago
Developer Tools●Mid
I built Formax to explore how Claude Code-style assistants work
Claude Code clone for learning, but explicitly not production-ready yet.
Ship It
zhangdawei
202mo ago
AI/ML●●Solid
OpenFable – Open-source RAG engine using tree-structured indexes
LLM-identified discourse boundaries beat fixed-size chunking for complex queries.
Big BrainNiche Gem
alainbrown
502mo ago
Developer Tools●●Solid
IDAssist – AI augmented reverse engineering for IDA Pro
Third in a series (GhidrAssist, BinAssist, IDAssist) — fills the IDA gap competently.
Niche GemWizardry
jtang613
403mo ago
AI/ML●●Solid
NeuralForge – Fine-Tune LLMs on Your Mac Using Apple Neural Engine
Fine-tune LLMs on Apple Neural Engine using reverse-engineered private frameworks — genuinely novel approach.
WizardryBig BrainNiche Gem
khaeldur
113mo ago