Guides
Decision pages built from the catalog: which tools fit a job, how they compare, and the command to install each. Every fact comes from the tool entries, and every guide says how it chose.
- MCP servers for coding agents, picked by job
MCP servers for Claude Code, Cursor and Codex, grouped by job, with the install command from each project's docs, what each needs, license and GitHub data.
- Open-source coding agents compared
OpenCode, Codex CLI, Gemini CLI, Aider, Cline, goose, OpenHands, Kilo Code and Qwen Code side by side: license, where each runs, which models it can use.
- Claude Code alternatives, by what you need instead
When Claude Code does not fit: alternatives for an open license, another model vendor, an editor-first workflow, agents on your own server or your own app.
- AI agent frameworks compared
LangGraph, CrewAI, OpenAI Agents SDK, Pydantic AI, Google ADK, Microsoft Agent Framework, Mastra and more by language, control model, owner and license.
- Agent observability and eval tools
Langfuse, LangSmith, Arize Phoenix, Opik, DeepEval, Promptfoo and Inspect: what each traces or tests, whether you can self-host it, license and install.