sniffly vs AI-Engineering-Coach
AI coding assistant usage dashboards compared
sniffly and AI-Engineering-Coach analyze coding-assistant activity and present insights in dashboards. sniffly focuses on Claude Code logs, while AI-Engineering-Coach supports logs across multiple harnesses and is delivered as a VS Code extension, with a GitHub Copilot app canvas option.
sniffly: Analyze Claude Code Usage and Errors
Sniffly turns local Claude Code logs into a dashboard for usage patterns, errors, and message history. It suits developers who want to review their own workflows or share selected project insights with coworkers.
AI-Engineering-Coach: Analyze AI Coding Sessions
AI Engineer Coach is a TypeScript VS Code extension, also available as a GitHub Copilot app canvas, that analyzes local AI coding sessions across harnesses. It turns session logs into practice, output, and context insights without sending data off your machine.
| sniffly | AI-Engineering-Coach | |
|---|---|---|
| Language | Python | TypeScript |
| License | MIT | MIT |
| Stars | 1.3k | 4.3k |
| Forks | 118 | 603 |
| Last analyzed | Oct 8, 2026 | Oct 20, 2026 |
Key differences
- sniffly focuses specifically on Claude Code usage, errors, and message history; AI-Engineering-Coach also analyzes activity, generated code, prompts, and workspace context across supported harnesses.
- sniffly offers a local browser dashboard and optional sharing links; AI-Engineering-Coach is a VS Code extension with a GitHub Copilot app canvas option.
- sniffly is written in Python and requires Python 3.10 or newer; AI-Engineering-Coach is written in TypeScript and requires VS Code 1.115 or later for the extension.
- sniffly supports private-link and public-gallery sharing, with a setting for including command text; AI-Engineering-Coach offers shareable summaries and describes session analysis as local and read-only.
- Both projects use the MIT license. AI-Engineering-Coach has more listed stars and forks than sniffly.
- AI-Engineering-Coach requires users to build a VSIX because it is not published to a marketplace or Releases page; sniffly provides configurable server and cache settings through its CLI.
Choose sniffly if you…
- want to review Claude Code usage, recurring errors, and message history in a local dashboard.
- need optional dashboard sharing controls, including visibility and command-text settings.
- prefer a Python project with CLI settings for the server and cache.
Choose AI-Engineering-Coach if you…
- want to analyze activity across supported AI coding harnesses in one dashboard.
- need features such as editable anti-pattern rules, generated-code breakdowns, or instruction-file audits.
- prefer a VS Code extension and can build its VSIX locally.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.