codebase-memory-mcp vs Graft

Side-by-side comparison of two AI agent tools

High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries

G
Graftopen-source

Turbocharge Claude Code, Cursor, Codex, Gemini & every coding agent: faster, cheaper, with contextual understanding specific to your codebase.

Metrics

codebase-memory-mcpGraft
Stars45.6k9.4k
Star velocity /mo3.8k786.0833333333334
Commits (90d)2.1k512
Releases (6m)100
Overall score0.9122981237739860.6442866086474068

FAQ

Which is more popular, codebase-memory-mcp or Graft?
codebase-memory-mcp has more GitHub stars (45,551 vs 9,433).
Which is more actively developed, codebase-memory-mcp or Graft?
codebase-memory-mcp had more commits in the last 90 days (2,093 vs 512).
Should I use codebase-memory-mcp or Graft?
Compare their capabilities, limitations and "best for" notes above. Both are open source, so trying each on a small task is the fastest way to decide.
codebase-memory-mcp vs Graft (2026): GitHub Stats, Features & Which to Choose