Repowise – Codebase intelligence for AI coding agents (open source)
Surfaces architectural decisions from git history — Cursor and Continue don't do this.
High-performance code-intelligence engine for AI agents and IDE, supports 257 languages, multi repositories, with access via CLI, MCP Server, and API. AI coding agents teammate - expose only needed information, cutting token usage up to 50x. 100% local.
49 MCP tools and 94% token reduction, but 'chat with codebase' is a crowded category.
Backend developers, teams with multi-repo codebases
Sourcegraph Cody · Cursor · Continue.dev
VS Code (10.7K files) indexed in ~1 minute, Linux kernel (70K files) in ~3 minutes
Licensed under PolyForm Small Business — free for personal use, open source projects, small businesses, education, and healthcare.
I knew a few similar projects were launched in the middle of Gortex's development, but after recent testing, I found it worth sharing the project with others and listening to their feedback.
Surfaces architectural decisions from git history — Cursor and Continue don't do this.
Local RAG + MCP for Claude with zero external dependencies—elegant constraint execution.
It stitches Slack threads, PRs, tickets and docs into a local "context lake" and can point a mention like handlePayment() straight to the file and related PRs — very practical for debugging and postmortems. The use of SQLite FTS5 for local full-text search plus MCP for a unified context layer is a smart, pragmatic combo; success will hinge on connector reliability and search/ranking quality, not the README.
AST-aware codebase search and onboarding beats grep, ships as local MCP server.
Cross-project memory for AI agents when single-project solutions already exist.
Blast radius detection before AI edits code, competing with Cursor's codebase awareness.