A terminal-based AI coding agent for inspecting, editing, and running projects
TagCode is an open-source terminal coding agent that can inspect repositories, edit files, run shell commands, and search the web. It supports hosted model providers as well as local models through Ollama, with saved sessions and configurable approval behavior.
Agenticness = how independently a tool can take action, scored across 9 dimensions. Scored independently by David Kooi, Skylark Creations — see full rubric → Last re-evaluated 25 October 2026.
Is this your tool? Claim this listing to manage your content and analytics.
Ask about TagCode
Get answers based on TagCode's actual documentation
Try asking:
About
TagCode (tgc) is an open-source AI coding agent for developers who prefer to work from the terminal. It is designed to take on multi-step repository tasks: it reads project instructions, plans work, uses development tools, and reports the outcome....
The tool has the ingredients of an agentic coding workflow: it can make file changes, execute commands, inspect Git state, search the web, retain work in saved sessions, and delegate focused tasks to subagents. Its permission modes are an important...
Handles domain-specific workflows independently with dynamic replanning.
Dimension Breakdown
Categories
Ask about TagCode
Try asking:
- Free / open source — full functionality available at no cost.
When TagCode changes its pricing, we catch it the next morning
We recrawl every tool in this directory daily. AI Insider is the 3-minute brief on what actually changed — pricing, features, score moves on our 36-point rubric — often before any press coverage. Sent daily. Skipped when nothing happened.