The request "codemap" is a bare term with no product named, so it is ambiguous: it could mean a tool that builds a code map for AI agents, or Sentry's own code-mapping features. The products below are the ones whose sources show code-map or codebase-structure capabilities, ranked by measured use; Sentry is included as the most established option, though its source shows error tracking more than code mapping.
A question back: Do you mean a code-map tool for AI coding agents, or something else by "codemap" (for example a specific product or a file format)? If you name the platform or the agent you use, I can narrow the list
- 1
Sentrysentry.ioverified and signed
Application performance monitoring and error tracking with an MCP server, SDK and CLI that let agents work with Sentry data from a coding conversation 1.
official:MCP server · @sentry/mcp-serverSDK · @sentry/nodelibrary · debugidCLI · sentry-clipackage · @sentry/junior-amplitude+49 community tools built for it
for agents: claude-settings-audit · code-simplifier · architecture-review
- 2
- 3
- 4
basemindbasemind.aiwebsite read, tools not yet checked
Provides a pure-Rust code map across 300+ languages served over MCP, returning file outlines, symbols and call-site references as pointers rather than file bodies 5.
- 5
Sources
- 1Sentry Docs | Application Performance Monitoring & Error Tracking Softwaredocs.sentry.io · read 2026-10-29
- 2SigMap — the deterministic, verifiable grounding layer for AI code work | SigMapsigmap.io · read 2026-10-29
- 4SocratiCode Cloud | The codebase context engine your team sharessocraticode.cloud · read 2026-10-29
- 5basemind | basemindbasemind.ai · read 2026-10-29
- 10Depwire — The Missing Context Layer for AI Coding Assistantsdepwire.dev · read 2026-10-29
For agents: the 10 actions behind this answer
claude-settings-audit · claude-settings-audit verified and signed
Analyze a repository to generate recommended Claude Code settings.json permissions. Use when setting up a new project, auditing existing settings, or determining which read-only bash commands to allow. Detects tech stack, build tools, and monorepo structure.
get_architecture_overview · sigmap verified and signed
One-call map of the codebase: module breakdown (files/tokens), the most depended-on
tavily_map · Tavily verified and signed
Map a website's structure. Returns a list of URLs found starting from the base URL.
codebase_graph_build · socraticode verified and signed
Build a dependency graph of the codebase using static analysis (ast-grep). Maps import/require/export relationships between files. Runs in the background — call codebase_graph_status to poll progress until complete.
· basemind website read, tools not yet checked
The context and communication layer for coding agents. A pure-Rust code map, document RAG, git intelligence, shared memory, and agent-to-agent comms — served over MCP.
· Pharaoh Docs website read, tools not yet checked
Install the GitHub App, map a repository and connect Claude Code, Cursor or VS Code over MCP. Then run your first Pharaoh codebase query.
· Memtrace website read, tools not yet checked
Memtrace gives coding agents shared structural memory: one graph for code, time, and fleet coordination.
overview · Sverklo found in code, not yet checked
Get a structural map of the codebase. Shows the most important files and their key symbols ranked by dependency importance (PageRank). Use this FIRST when starting work on an unfamiliar codebase or directory.
· Kaicontext website read, tools not yet checked
An independent reviewer that traces your changes through a semantic map of your codebase.
visualize_graph · depwire-cli verified and signed
Render an interactive arc diagram visualization of the current codebase's cross-reference graph. Shows files as bars along the bottom and dependency arcs connecting them, colored by distance. The visualization appears inline in the conversation.
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.