Developer Tools●Mid
ECD++ 2026.3.10 Is Released
Eclipse decompiler plugin with automated updates when other plugins exist.
Cozy
nbauma109
1024d ago
Back to browse
GitHub Repository
Decompile Minecraft using Vineflower, reconstruct the code using LLM
4 starsShell
LLM-assisted reconstruction of partially decompiled Minecraft 26.1.2
by stevefan1999·Apr 29, 2026·8 points·0 comments
AI Analysis
●●●BangerWizardryBig BrainNiche Gem
LLM agents repair decompiled Java until bytecode hashes match the original.
Strengths
- •Bytecode equivalence verification ensures reconstructed source produces identical binaries to original.
- •Legal safeguards keep copyrighted artifacts local while sharing the reconstruction logic.
- •Orchestrates Vineflower, Gradle, and LLMs into a deterministic repair feedback loop.
Weaknesses
- •Requires users to supply their own Minecraft JAR, adding friction to setup.
- •Niche applicability limits utility outside Java reverse engineering or modding contexts.
Category
Target Audience
Java reverse engineers, Minecraft mod developers, Security researchers
Similar To
Vineflower · Ghidra · Fernflower
Similar Projects
Developer Tools●●Solid
Partial-zod – streaming JSON parser for LLMs (zero deps, Zod-native)
Zero-dependency Zod streaming parser when zod-stream requires ecosystem buy-in.
SlickNiche Gem
millerjoe
101mo ago
AI/ML●●Solid
AgentKeeper – Cross-model memory for AI agents
Recovers 95% critical facts when switching GPT-4 ↔ Claude with real benchmarks.
Solve My ProblemBig Brain
thinklanceai
103mo ago
AI/ML●●Solid
AgentKeeper – cognitive persistence layer for AI agents
Cross-provider agent memory is clever, but LLM context windows keep growing and RAG is already standard.
Solve My ProblemShip ItBig Brain
thinklanceai
303mo ago
Gaming●●Solid
A Minecraft builder skill for coding agents
Minecraft builds from agent prompts with interactive preview before placing.
Niche GemCozy
mattzh1314
504d ago
AI/ML●●Solid
Local Voice Assistant
This repo bundles a complete local audio loop — client captures audio, backend transcribes with Parakeet, queries a quantized Mistral LLM via Ollama, then renders speech with Kokoro or Qwen3-TTS for cloning — and reports ~1s round-trip on an RTX5070. It’s a practical, take-it-home demo for running privacy-first voice agents, though it’s still a demo: requires specific tooling (Ollama, GPU headroom), has obvious TODOs (VAD, better warmup for cloning), and isn’t reinventing the architecture.
WizardryNiche Gem
armcat
203mo ago