Benchmark tasks for evaluating AI coding agents on large codebases (1GB+) with Sourcegraph MCP
-
Updated
Jan 31, 2026 - Shell
#
large-codebases
Here are 2 public repositories matching this topic...
Fast, fully-local code search & navigation for large codebases — cuts the tokens an AI coding agent spends finding code. Lexical + symbolic + semantic, memory-mapped, no GPU, no cloud.
code-navigation tree-sitter csharp cpp roslyn dotnet mcp code-search codex local-first semantic-code-search llm-tools model-context-protocol mcp-server claude-code ai-coding-agent incremental-indexing trigram-index large-codebases
-
Updated
Oct 8, 2026 - C
Add this topic to your repo
To associate your repository with the large-codebases topic, visit your repo's landing page and select "manage topics."