Avazbek22/DevProjex
by Various
Build safe, token-efficient codebase context for LLMs, AI chats, and coding agents — local-first GUI, TUI, CLI, and a read-only MCP server with Smart Ignore, secret/PII redaction,
MCP
Avazbek22/DevProjex
Added 16 Sept 2026
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
Clients listed in this record (not verified here)
Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, ChatGPT
Notes
24 stars on GitHub. Last updated 2026-09-16. Licensed Apache-2.0.
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
Open-source & AI alternatives
Swap-in tools that solve the same job. Weigh the trade-offs before you commit.
oraios/serena
Various
A powerful MCP toolkit for coding, providing semantic retrieval and editing capabilities - the IDE for your agent
repowise-dev/repowise
Various
Codebase intelligence for AI and humans: code health scores, auto-generated docs, git analytics, dead code detection, and architectural decisions via MCP.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.