Anthropic
Terminal agent that edits the repo you point it at.
Anthropic's coding agent. It runs in the terminal against a project and can use tools you connect.
Provisional seed scores. Method seed-v0-provisional, confidence low, not hands-on tested. The band around a number is a ±8 display label, not a measured interval. Ordering uses the point estimate.
The dollar amount is not a score. Rankings do not read it.
API flag: not marked. MCP flag: seed says yes. These flags are notes, not an audit.
No public affiliate program was recorded for this tool in the Oct 14, 2026 research, or it was not checked. Absence of a program does not change any score.
We may earn a commission if a tracking link is connected and you buy through it. It never changes ranks. In this v1 seed, tracking URLs are empty, so “Open site” goes to the vendor. Sponsorship rules.
AI code editor / agent · role rank 2
Strongest terminal agent with subagents and headless mode.
83
75–91 · low confidence
AI code editor / agent · role rank 1
Terminal agent that handles Expo and native project layouts well.
82
74–90 · low confidence
AI code editor / agent · role rank 1
Native MCP client to test against.
82
74–90 · low confidence
AI code editor / agent · role rank 1
Handles manifest, content scripts, and background workers.
82
74–90 · low confidence
AI code editor / agent · role rank 2
Terminal agent for the same repo.
81
73–89 · low confidence
AI code editor / agent · role rank 2
Strong terminal agent when you want the diff, not a chat panel.
81
73–89 · low confidence
81
73–89 · low confidence
No release on file. That is not the same as stale.
No score revisions on file. These seed scores have not been through the pipeline.