The Continuity Layer
← Claude Code, every test with the source
Alternatives · Coding agents

Claude Code alternatives, graded

thecontinuitylayer.com/alternatives/claude-code

Claude Code scores highest on its shelf, 7½ of 8 (grade A), so every alternative below scores the same or lower: OpenAI Codex (7, A−), Cline (7, A−), Windsurf (now Devin Desktop) (6½, B+) lead the ranking. Every grade is read from the maker's own page, checked 3 November 2026, never from a review.

A
Claude Code · 7½ of 8
7
coding agents to compare
0
score higher
3 November 2026
Makers' pages checked

Every coding agent on the record, ranked

Claude Code’s own row is shaded. The five columns are the tests a person switching asks about first; each product page has every test, with the maker’s line and the source. Where the test is about training, no is the good answer and is colored as such.

coding agentGradeRemembersYour filePortableTrainingPrice
Claude Code#1 · Anthropic · this oneA7½/8
OpenAI Codex#2 · OpenAIA−7/8
Cline#3 · Cline Bot Inc.A−7/8
Windsurf (now Devin Desktop)#4 · CognitionB+6½/8
Gemini CLI#5 · GoogleB+6½/8
Aider#6 · Aider-AIB+6½/8
Cursor#7 · AnysphereB6/8
GitHub Copilot#8 · GitHub (Microsoft)B6/8
  • Remembers · Does it remember across sessions?
  • Your file · Does it keep memory in a file you own?
  • Portable · Does it read a format other tools read?
  • Training · Does it use your code for training by default?
  • Price · What does it cost?

Claude Code alternatives, by what matters

5 coding agents that keep memory in a file you own

  1. A− OpenAI Codex
  2. A− Cline
  3. B+ Windsurf (now Devin Desktop)
  4. B+ Gemini CLI
  5. B+ Aider

Claude Code passes this test too.

The one coding agent that don't use your code for training by default

  1. B+ Aider

Claude Code's grade on this test: partly.

6 coding agents that read a format other tools read

  1. A− OpenAI Codex
  2. A− Cline
  3. B+ Windsurf (now Devin Desktop)
  4. B+ Gemini CLI
  5. B Cursor
  6. B GitHub Copilot

Claude Code passes this test too.

What Anthropic changed lately

  1. Since 3 November 2026, text generated by Claude Mythos 5, Claude Opus 4.7 and Claude Sonnet 4.6 carries Anthropic's text watermark on the platforms Anthropic lists; on Sonnet 4.6 a request that sets temperature, top_p or top_k to a non-default value might not carry it. The Decoder reported on 4 November that a notice to API customers extends the watermark to Claude Opus 4.6, Opus 4.5, Sonnet 4.5 and Haiku 4.5 from 16 November 2026, a few days later on Amazon Bedrock, with the same caveat, and that customers cannot turn it off.

    source

  2. The pricing page lists a new Ultra plan at $200 a month and Max at $100 a month only; on 23 October 2026 it listed Max in two tiers, the higher one priced only on a help page. The usage-limits page says verified Ultra accounts have no five-hour session limit. Neither page dates the change.

    source

  3. Anthropic deprecated fast mode for Claude Opus 4.8 on 30 October 2026, with removal on 30 November 2026. After that, API requests to claude-opus-4-8 that set speed to fast return an error; Anthropic points people who want fast mode to Claude Opus 5.5.

    source

Every change from Anthropic, dated →

Alternatives to the others

The whole shelf: Coding agents. How the grades are made: How we grade. No maker pays for a place or a grade.