📖 The AI Tool Bible

Cursor vs LLM by Datasette

A side-by-side look at pricing, capabilities, pros, cons, and our editorial scores.

 
Cursor
Coding
LLM by Datasette
Coding
TaglineAI-first VS Code fork — chat, edit, and agentic coding in one IDE.A CLI and Python library for running prompts against any LLM provider and logging everything to SQLite.
CategoryCodingCoding
PricingFreemium· Free hobby; Pro $20/mo; Business $40/moFree· Free and open source (Apache 2.0); pay underlying model providers separately
ModelClaude / GPT (configurable)Multi-model
Editorial score9.5 / 107.2 / 10
Use cases
codingrefactorsagentic editsIDE
cli-promptingprompt-loggingembeddingsstructured-extractionlocal-modelstool-use
Pros
  • Best-in-class multi-file edits
  • Choice of underlying models
  • Composer agent is genuinely useful
  • Tab completion is faster than Copilot
  • One CLI for OpenAI, Anthropic, Gemini, Llama and local models via plugins
  • Every prompt and response logged to queryable SQLite
  • Composes well with Unix pipes for scripting and batch jobs
  • Apache-2.0 open source with an active plugin ecosystem
  • Supports multi-modal input, schemas, embeddings and tool use
Cons
  • Heavier than vanilla VS Code
  • Pricing creeping up
  • Some extensions lag VS Code
  • Command-line only — no GUI or hosted dashboard
  • Requires bringing your own API keys and managing provider costs
  • Learning curve for plugin install and template syntax
Websitecursor.comllm.datasette.io
Pick Cursor if
  • ✅ Best-in-class multi-file edits
  • ✅ Choice of underlying models
  • ✅ Composer agent is genuinely useful
  • ✅ Tab completion is faster than Copilot
Pick LLM by Datasette if
  • ✅ One CLI for OpenAI, Anthropic, Gemini, Llama and local models via plugins
  • ✅ Every prompt and response logged to queryable SQLite
  • ✅ Composes well with Unix pipes for scripting and batch jobs
  • ✅ Apache-2.0 open source with an active plugin ecosystem
Compare a different pair →