morluto/rea

Fork 0

mirror of https://github.com/morluto/rea.git synced 2026-11-05 06:45:22 +00:00

[GH-ISSUE #4867] [Feature] Add support llama.cpp #3024

New issue

Open

opened 2026-10-31 00:35:01 +00:00 by bsakaguchi · 4 comments

bsakaguchi commented

2026-10-31 00:35:01 +00:00

Owner

Originally created by @maksmanus on GitHub (Oct 17, 2026).
Original GitHub issue: https://github.com/morluto/rea/issues/4867

Before submitting

I searched the open and closed issues and pull requests for a related proposal.
I understand the contribution scope must be reviewed before integration; open questions are welcome here.
This request does not include credentials, private samples, or sensitive target data.

Area

Setup, packaging, or upgrade

Current limitation

Add please support llama.cpp for easy using and installing. I using local models for reverse engeneering and i very watns try this tool in my local models

Use cases

No response

Desired outcome and success criteria

Users can use tool with llama.cpp

Expected interaction with targets

Launch or attach to a process

Target and scope details (optional)

No response

Verification available so far

Idea only; I need help defining checks

Verification details (optional)

No response

Alternatives considered

No response

Possible direction

No response

References

No response

Originally created by @maksmanus on GitHub (Oct 17, 2026). Original GitHub issue: https://github.com/morluto/rea/issues/4867 ### Before submitting - [x] I searched the open and closed issues and pull requests for a related proposal. - [x] I understand the [contribution scope](https://github.com/morluto/rea/blob/main/CONTRIBUTING.md#contribution-scope) must be reviewed before integration; open questions are welcome here. - [x] This request does not include credentials, private samples, or sensitive target data. ### Area Setup, packaging, or upgrade ### Current limitation Add please support llama.cpp for easy using and installing. I using local models for reverse engeneering and i very watns try this tool in my local models ### Use cases _No response_ ### Desired outcome and success criteria Users can use tool with llama.cpp ### Expected interaction with targets Launch or attach to a process ### Target and scope details (optional) _No response_ ### Verification available so far Idea only; I need help defining checks ### Verification details (optional) _No response_ ### Alternatives considered _No response_ ### Possible direction _No response_ ### References _No response_

bsakaguchi added the

triage

enhancement

labels

2026-10-31 00:35:01 +00:00

bsakaguchi commented

2026-10-31 00:35:02 +00:00

Author

Owner

@panditshivam commented on GitHub (Oct 17, 2026):

Added a tested llama.cpp setup guide in #4878. It uses llama-server's existing MCP support to connect REA to local models.

The guide covers project-local installation, optional global installation, the JSON config, startup command and provider timeouts. Checks covered all 207 tools and actual JavaScript analysis for both install options. It also explains cases where a model connects but returns text instead of calling a tool.

The PR is open for review.

@panditshivam commented on GitHub (Oct 17, 2026): Added a tested llama.cpp setup guide in #4878. It uses llama-server's existing MCP support to connect REA to local models. The guide covers project-local installation, optional global installation, the JSON config, startup command and provider timeouts. Checks covered all 207 tools and actual JavaScript analysis for both install options. It also explains cases where a model connects but returns text instead of calling a tool. The PR is open for review.

bsakaguchi commented

2026-10-31 00:35:02 +00:00

Author

Owner

@matbrgz commented on GitHub (Oct 17, 2026):

Direct duplicate of canonical proposal #3668 ([Feature] Local LLM runtime reverse engineering: llama.cpp, Ollama, MLX, ONNX Runtime, ExecuTorch and OpenVINO inference reconstruction), opened on October 14, 2026, which established the roadmap for local LLM runtime support (including llama.cpp, Ollama, and local model inference workflows).

Recommend closing this issue in favor of #3668. @morluto

Indexed under Section 1 (Direct Duplicates) in consolidation tracker #4330.

@matbrgz commented on GitHub (Oct 17, 2026): Direct duplicate of canonical proposal #3668 (`[Feature] Local LLM runtime reverse engineering: llama.cpp, Ollama, MLX, ONNX Runtime, ExecuTorch and OpenVINO inference reconstruction`), opened on October 14, 2026, which established the roadmap for local LLM runtime support (including llama.cpp, Ollama, and local model inference workflows). Recommend closing this issue in favor of #3668. @morluto Indexed under Section 1 (Direct Duplicates) in consolidation tracker #4330.

bsakaguchi commented

2026-10-31 00:35:02 +00:00

Author

Owner

@XinwangTao commented on GitHub (Oct 18, 2026):

Agree with matbrgz that this is a direct duplicate of #3668 (which already covers llama.cpp as part of the local LLM runtime roadmap) — closing in favor of it is the right consolidation move.

That said, #4878 (documented llama.cpp MCP setup) is still valuable as an immediate, tested path: it lets users wire local models via llama-server's MCP support today without waiting for full runtime integration, and the note about "model connects but returns text instead of calling tools" is a real gotcha worth keeping in the docs. Worth merging that guide under the umbrella of #3668 either way.

@XinwangTao commented on GitHub (Oct 18, 2026): Agree with matbrgz that this is a direct duplicate of #3668 (which already covers llama.cpp as part of the local LLM runtime roadmap) — closing in favor of it is the right consolidation move. That said, #4878 (documented llama.cpp MCP setup) is still valuable as an immediate, tested path: it lets users wire local models via llama-server's MCP support today without waiting for full runtime integration, and the note about "model connects but returns text instead of calling tools" is a real gotcha worth keeping in the docs. Worth merging that guide under the umbrella of #3668 either way.

bsakaguchi commented

2026-10-31 00:35:03 +00:00

Author

Owner

@morluto commented on GitHub (Oct 26, 2026):

Thanks for the request and the related links. I am keeping this open: the reported use case is using REA with a local llama.cpp model, whereas #3668 proposes analyzing applications that embed inference runtimes. Those are different workflows despite the shared name. #4878 proposes setup guidance for this use case and remains open; its eventual outcome can be assessed against this request without treating the runtime-analysis proposal as a duplicate.

@morluto commented on GitHub (Oct 26, 2026): Thanks for the request and the related links. I am keeping this open: the reported use case is using REA with a local llama.cpp model, whereas #3668 proposes analyzing applications that embed inference runtimes. Those are different workflows despite the shared name. #4878 proposes setup guidance for this use case and remains open; its eventual outcome can be assessed against this request without treating the runtime-analysis proposal as a duplicate.

bsakaguchi referenced this issue

2026-10-31 00:36:56 +00:00

[GH-ISSUE #5088] [Bug] inspect_evm_interface loses detail field guidance and advertised default #3126

bsakaguchi referenced this issue

2026-10-31 00:40:20 +00:00

[GH-ISSUE #5654] [Tracker] Open PRs that can't merge yet: conflicts and red CI (October 2026) #3425

bsakaguchi referenced this issue

2026-10-31 01:07:36 +00:00

[PR #3024] feat(evm): inspect exact Solidity compiler artifacts #5563