llnl / llnl/OGhidra

Configurable decompiler/tool backends

Open
#8 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
440
Forks
48
Avg merge
28m
Merged PRs (30d)
1

Description

Currently GhidraMCP is the primary way OGhidra gets information on binaries. This should be refactored so that the backend used for the tool calls can be implemented using other methods.

Several areas where this would be useful:
* a pyghidra backend that enables using a headless Ghidra instance, simplifies initial setup/installation (no GhidraMCP extension to install), and removes limitations related to binding sockets that is associated with using GhidraMCP
* using other decompilers like Binary Ninja, IDA Pro, or rev.ng
* supporting bytecode decompilation using tools specifically for those ecosystems, such as ILSpy for .NET/CLR, uncompyle6 for Python, JADX for Java, etc

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue does not name files or tests. Start by tracing how OGhidra currently uses GhidraMCP for tool calls, then determine the backend boundary needed for alternate implementations such as pyghidra or other decompilers. Done should include a defined approach for configurable backends, but the issue does not specify acceptance tests or a complete scope.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
reverse-engineering, tooling
Issue type
Refactor
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.