Back to browse
GitHub Repository

Persistent structural memory for AI coding agents. Turns your repo into a fast, MCP-native knowledge graph so assistants stop grepping and start querying.

1 starsRust

Graphenium, persistent repo memory for AI coding assistants

by Graphenium·Jun 24, 2026·1 point·0 comments

AI Analysis

●●SolidBig BrainNiche Gem

Persistent graph memory via MCP beats grep-and-trace for 5000+ file repos.

Strengths
  • MCP server integration means any compatible assistant gets structural memory automatically.
  • Twenty millisecond query time stays fast regardless of repository size growth.
  • Architecture summary provides 30-second codebase orientation before reading files.
Weaknesses
  • Codebase understanding for AI assistants is a heavily funded competitive space.
  • Only one GitHub star suggests very early stage with limited real-world validation.
Target Audience

Developers working with large codebases or monorepos

Similar To

Sourcegraph · Cursor · Continue

Similar Projects

Developer Tools●●●Banger

Mindpm – persistent project/task memory for AI coding assistants (MCP)

MCP-native persistent memory prevents re-explaining projects to Claude every session.

Solve My ProblemBig Brain
ukavala
104mo ago
Developer Tools●●Solid

Vibe-coded – Rust CLI to discover LLM-assisted Git repositories

Handy CLI that actually pulls a repo and runs a battery of concrete heuristics — repo age, README keywords/emoji counts, commit velocity, presence of LLM-tool files, and simple commit-statistics — to guess whether code was prompt-expanded. The rule set is intentionally arbitrary and extensible, which makes this a useful starting point for audits or CI checks, but expect false positives and plan to tune or add rules for your context.

Niche GemShip It
xlii
104mo ago
Developer Tools●●Solid

Gortex – MCP server for cross-repo code intelligence

49 MCP tools and 94% token reduction, but 'chat with codebase' is a crowded category.

Big BrainNiche Gem
zzet
302mo ago