codegraph

codegraph copied to clipboard

## Problem When using **git worktree**, each worktree is an independent working directory. Currently, CodeGraph requires running `codegraph init -i` in each worktree directory separately. This creates friction for developers...

JonasGao

I saw that local embeddings / vector search were removed because of package size, model downloads, WASM / ONNX memory pressure, and reliability issues. Would you consider bringing vector search...

stupidloud

Implemented project configuration to disable certain MCP tools to spare tokens with the initial schema in the context

kecsap

Codex / Cursor support

4

Why does it force claude usage by writing to a claude folder? That's extremely limiting. Needs global support for the agent whatever the agent is.

atrofimov-sc

feat: index files inside git submodules

1

## Summary `git ls-files` (used for both the initial scan and incremental sync) doesn't enter submodules — they appear as gitlink entries with their contents invisible. Both file-discovery paths now...

andreinknv

I'd open this as a discussion but since this project only has issues -- I'm *extremely* interested in using this for our team and I think - at the individual...

codinronan

Merge-order guide for the open PR backlog (4 refactor PRs unblock the rest)

6

# Maintainer guide: how to merge the open PR backlog with minimal friction > **Update — April 28, 2026:** 14 of my PRs have been pre-rebased onto the post-refactor patterns....

andreinknv

## Summary When a query matches many symbols in a single file, current ranking returns the matching class plus 9 of its members from the same file. The first hit...

andreinknv

feat: LLM symbol summaries, semantic search, RAG Q&A, dir/role/dead-code/naming + agent-as-LLM bridge

1

> **🔄 Rebased onto post-refactor patterns + empirically validated against a real local LLM (qwen2.5-coder:32b via Ollama)** > > See [Validation results](#validation) below. tl;dr: 787/787 tests pass, agent-bridge tier works...

andreinknv

feat(mcp): codegraph_review_context — structured PR-review context from a diff

1

> **🔄 Rebased onto post-refactor patterns (review-context MCP tool)** > This PR has been rebased to use the per-thing file layout established by refactor PRs #116/#117/#118/#119. Behavior shipped is identical...

andreinknv