ProjectAtlas MCP Server
styler-ai/ProjectAtlas
[](https://agentrank-ai.com/tool/styler-ai--ProjectAtlas/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Every file not opened. Every folder not explored. Tokens saved. ProjectAtlas guides coding agents with purpose metadata and an intelligent code graph, reducing token costs by over 90%.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
styler-ai/ProjectAtlas is a Rust tool licensed under MIT. Every file not opened. Every folder not explored. Tokens saved. ProjectAtlas guides coding agents with purpose metadata and an intelligent code graph, reducing token costs by over 90%. Topics: claude-code, code-intelligence, codex, coding-agents, developer-tools, mcp, opencode, repository-map, rust, sqlite.
Ranked #457 out of 24849 indexed tools.
In the top 2% of all indexed tools.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
438 stars → growing community
Last commit today → actively maintained
280/297 issues closed → responsive maintainer
2 contributors → solo project
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Matched Queries
From the README
# ProjectAtlas
<p align="center">
<a href="docs/design/ani-mascot-reference.png" title="Open Ani's versioned mascot reference">
</a>
</p>
<p align="center">
<strong>Rust-native, high-performance local repository intelligence for coding agents and large codebases.</strong><br>
A persistent SQLite map guides Codex, Claude Code, OpenCode, and other MCP-capable agents to the right code before they spend context reading the wrong files.
</p>
<p align="center">
<a href="https://github.com/styler-ai/ProjectAtlas/actions/workflows/ci.yml"></a>
<a href="https://github.com/styler-ai/ProjectAtlas/releases/tag/v0.4.5"></a>
</p>
## About
Every file not opened. Every folder not explored. ProjectAtlas guides coding agents with purpose metadata and an intelligent code graph, reducing token costs by over 90%.
The "over 90%" figure is a workload-specific local estimate from the published audit, not a universal savings guarantee or provider-billing result; see [One Large-Appl Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.