v0.8.0 should support OpenRouter as well as local models. It was easy.
Could you please give it a shot when you have some spare time?
mudasobwa
Creator of Cure
mudasobwa
Creator of Cure
Thanks for providing the correct answer 
I also explicitly added the restriction to use my code connecting to OpenAI/Agnostic/Google models to LICENSE.
1
mudasobwa
Creator of Cure
Kevo
There are options short of suit that might be problematic.
I see now it looks like you’ve changed the name. I think that’s a good decision.
In any case, good luck with it.
1
mudasobwa
Creator of Cure
The transparency is what yoke is after. Erlang is a joy to use mostly because of the toolchain, including but not limited to :observer, core dump viewer, :os_mon etc.
In the latest version yoke got the exlorer for its internal ./.yoke directory. Enjoy.
1
webofbits
This looks pretty.
I was testing Yoke the other day (still DSH on my machine) and had Ragex running for really long time - still couldn’t have it completed. Maybe code graph/indexing could be optional or run in background? Just an idea.
1
mudasobwa
Creator of Cure
Maybe, once I figure out how to properly do that. Basically, AST-based embeddings are a killer feature alongside with AST-based analysis. It’s incremental and should be very long only once and only on CPU. In the meanwhile you might compile yoke yourself with custom configs:
1. How to Disable Models / Embeddings
• Config Option (:skip_bumblebee): Set config :ragex, skip_bumblebee: true in yoke’s application configuration. This skips starting bumblebee.ex and vector_store.ex, saving GPU memory and ~500MB+ RAM.
• Analysis Option: When running directory analysis or SCIP ingestion, pass generate_embeddings: false (or skip_embeddings: true).
• Automatic Fallback for Light Builds: If ML dependencies (bumblebee, nx, exla) are omitted from the build (e.g. for standalone CLI binaries or mix escript.build), Ragex automatically detects that BumblebeeEmbeddings.available?() is false and gracefully bypasses vector store startup without crashing.
2. Features That Work WITHOUT Models / Embeddings
The majority of Ragex’s code analysis and navigation tools function completely independently of vector embeddings:
• Precise Code Navigation (SCIP): Symbol resolution, go-to-definition, and caller lookup (find_callers).
• Graph & Topology Analysis: Structural graph queries (query_graph), path finding (find_paths), centrality analysis (betweenness_centrality, closeness_centrality), and community detection (detect_communities).
• MetaAST Pattern Search: Cross-language structural AST pattern matching (find_metaast_pattern, metaast_search).
• Code Quality & Code Smell Detection: detect_smells, find_dead_code, analyze_quality, quality_report, coupling_report, find_circular_dependencies.
• Security & Secret Scanning: scan_security, check_secrets, security_audit.
• Git & History Analysis: git_blame, git_history, co_change_analysis, and file watcher auto-reindexing.
• Refactoring & Editing: edit_file, validate_edit, rollback_edit, refactor_code, preview_refactor.
3. Impacted Features:
• semantic_search: Requires vector embeddings. If embeddings are disabled, calling semantic_search will return a message indicating the embedding model is not active.
• hybrid_search: Combines vector similarity with graph traversal. When running without embeddings, search relies on structural AST lookups (metaast_search)
and direct SCIP graph queries instead.
2
tmbb
Justo to give you some feedback: I’ve tried to install it, I have gotten multiple errors related to Bumblebee and Openrouter auth, but I don’t have time to debug them currently… Once I find out how to do it I’ll submit a PR
1
mudasobwa
Creator of Cure