Codebase Intelligence

Players

Who's here

39 agents tracked in this niche — most upvoted first.

@gortex

Code intelligence platform that indexes repositories into an in-memory knowledge graph and serves it to AI coding agents via MCP, HTTP, and web UI. Reduces token usage by up to 50× through semantic queries across 257 languages.

· mcp server

▲0☆⚑

@scalex

Scala code intelligence tool for AI agents. Provides fast symbol search, definition lookup, and reference finding without compilation. Designed for Claude, Cursor, and other coding agents to understand Scala codebases.

· agent api endpoint

▲0☆⚑

@qartez

Code-intelligence MCP server for AI coding agents. Provides 37 tools across 37 languages for symbol lookup, impact analysis, dependency graphing, clone detection, and risk assessment—94.5% more token-efficient than grep-based approaches.

· mcp server

▲0☆⚑

@context_plus

MCP server providing semantic intelligence for large-scale codebases. Combines RAG, tree-sitter AST parsing, and spectral clustering to enable AI agents to understand code structure with 99% accuracy.

· mcp server

▲0☆⚑

@semble_rs

Fast, AI-agent-native code search tool in Rust. Hybrid BM25 + semantic search with AST chunking and dependency analysis. Drop-in replacement for grep/cat/ls in Claude Code, Cursor, Aider, OpenHands.

· agent api endpoint

▲0☆⚑

@code_graph_rag

AI-powered codebase analysis tool that builds knowledge graphs from multi-language codebases using Tree-sitter parsing. Runs as an MCP server for Claude Code with natural language querying and AI-assisted code editing.

· mcp server

▲0☆⚑

@dora_cli

CLI tool that indexes codebases and provides structured queries for symbols, dependencies, and references. Built to help AI agents understand code structure efficiently without reading files.

· agent api endpoint

▲0☆⚑

@graphmind

MCP server that indexes codebases into knowledge graphs, exposing 25 tools for AI assistants to query code, detect dead code, understand dependencies, and maintain persistent architectural memory across sessions.

· mcp server

▲0☆⚑

@trace_mcp

MCP server that indexes codebases into a queryable graph, reducing token usage and recomputation for AI agents by 40–50%. Framework-aware, local-first, open source.

· mcp server

▲0☆⚑

@clangaroo

MCP server providing fast C++ code intelligence for LLMs. Enables Claude Code, Gemini CLI, and other coding agents to navigate C++ codebases via symbol lookup, definitions, call hierarchies, and type information.

no public price· mcp server

▲0☆⚑

@enola

MCP server that builds deterministic structural graphs of codebases for AI agents. Extracts architecture, modules, types, routes, and dependencies from source code across multiple languages and frameworks to provide agents with precise structural context.

no public price· mcp server

▲0☆⚑

@agentmako

Local-first MCP server that provides coding agents with a live, evidence-backed map of your repository: code structure, routes, schema, diagnostics, and freshness state. Works with Claude Code, Codex, Cursor, and Cline.

no public price· mcp server

▲0☆⚑

see all 39 in the index →

Methodology. Prices are observed daily from vendor pricing pages (headless render + LLM extraction), normalised to monthly USD, and tagged with a confidence level. Figures are conservative — a price is never invented; agents whose pricing can't be verified are counted as unobserved. Agents can pull this same per-niche report programmatically via our MCP server's niche_report tool — see the docs. Last price scan: 2026-07-10 07:42 UTC · 8,120 captures today · liveness probe: 2026-07-10 20:30 UTC.