ai-engineering-from-scratch vs CrbonFree: Features, Pricing & Which Is Better (2026)
A side-by-side comparison of ai-engineering-from-scratch and CrbonFree — features, pricing, and ideal use cases — to help you decide which AI tool fits your workflow.
a
ai-engineering-from-scratch
rohitg00
Free, open-source curriculum of 500+ hands-on lessons across 20 phases to learn and build AI engineering from math to agents.
Key features
- 523 lessons in 20 phases: A structured curriculum of about 342 hours from setup and math to LLM and agent engineering
- Multi-language code: Lessons implemented in Python, TypeScript, Rust and Julia
- Reusable artifacts: Every lesson ships a prompt, skill, agent or MCP server you can reuse
- Goal-based paths: Learning paths for coding agents, MCP, Agent Skills and product delivery
- Evidence-based workflow: Learners record the command, output and changes for each lesson
- Placement tutor skill: A start-learning skill helps decide where to begin
- Certification onboarding: Guides for Claude certification and the MCP Associate track
- Translations: Landing pages available in a dozen languages
Best for
- A developer new to AI follows Phase 0 and the math foundations to build a base
- An engineer builds production LLM applications using the LLM Engineering phase
- A team learns to write and ship Agent Skills and MCP servers through the tools and protocols phase
- A coding-agent user follows the agent-assisted engineering path to work on real repositories
- A learner prepares for the MCP Associate certification using the onboarding guide
CrbonFree
Crbon Labs Inc.
CrbonFree meters the energy and carbon of every AI token across providers, with published factors, uncertainty bands and audit-ready retirement receipts.
Key features
- Per-Token Carbon Metering: Counts every token by model and provider and converts it to energy, CO2e and water using versioned, published factors.
- Multi-Provider Coverage: Connects OpenAI, Anthropic, OpenRouter, AWS Bedrock, Google Vertex AI, Azure Foundry, Vercel and Cloudflare AI Gateways into one report.
- Many Ingestion Surfaces: Read-only provider keys, TypeScript and Python SDKs, an OAuth-secured remote MCP server, a CLI for local coding agents and a Chrome/Edge extension for ChatGPT, Gemini and Claude.
- Layered Methodology with Uncertainty: Reports model energy, data-centre overhead and embodied hardware/training carbon separately, each with a ±28.3% uncertainty band.
- Metadata-Only Privacy: Receives only model, token counts and timestamps — prompt and completion content never leaves your systems.
- Signed Retirement Receipts: Paid plans issue receipts listing credit serial numbers on the American Carbon Registry or BCarbon Registry, publicly verifiable.
- Monthly Audit Packs: Zip exports with a manifest hash plus badges and certificates to back published climate claims.
- Dashboard & REST API: One view of tokens, cost and carbon across projects with CSV/JSON export and twelve read endpoints with an OpenAPI spec.
Best for
- Scope 3 Reporting: Sustainability teams produce defensible AI emissions figures for disclosures instead of spend-based guesses.
- Engineering Carbon Visibility: Track the footprint of coding agents like Claude Code across a dev team via the CLI.
- Model Selection by Footprint: Compare energy and carbon per provider and model tier when choosing models for production workloads.
- Carbon Offsetting with Proof: Retire credits against measured AI usage and share verifiable receipts with auditors or customers.
- Board and Auditor Requests: Hand auditors monthly audit packs with verifiable hashes when asked for AI emissions data.
- Personal Chat Usage Tracking: Individuals estimate the footprint of their ChatGPT, Gemini and Claude sessions with the browser extension.