Avazbek22/DevProjex

Overview

Local-first tool for generating codebase context for LLMs and coding agents. Provides GUI, TUI, CLI, and a read-only MCP server. Includes Smart Ignore, secret/PII redaction, Git scopes, and code compression to keep context token-efficient.

Best for

Best for
Developers who need safe, token-efficient codebase context for LLM workflows.

Use cases

• Generate compact codebase context for AI chat sessions
• Redact secrets and PII before sending context to external models
• Scope context to specific Git changes or branches

How to use

Tools exposed

• Tracked-files-only

Tested with

Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, ChatGPT

Notes

Local-first tool for generating codebase context for LLMs and coding agents. Provides GUI, TUI, CLI, and a read-only MCP server. Includes Smart Ignore, secret/PII redaction, Git scopes, and code compression to keep context token-efficient.

24 stars on GitHub. Last updated 2026-09-16. Licensed Apache-2.0.

Use cases

• Generate compact codebase context for AI chat sessions
• Redact secrets and PII before sending context to external models
• Scope context to specific Git changes or branches

Pros

• Local-first, keeps code on the machine
• Multiple interfaces: GUI, TUI, CLI, and MCP server
• Token-efficient through compression and ignore rules

Cons

• Small community with only 24 stars
• C# codebase may limit potential contributors
• MCP server is read-only, so no write operations

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.