The best alternatives to Claude Code
Claude Code might not be the right fit: the price, a missing feature or a payment model you don't like. These are the closest alternatives in our catalog, ordered by rating, with the full review of each one.
Why look for a Claude Code alternative
A week of big announcements and an unresolved controversy. On 7 August Anthropic confirmed that from 14 August auto mode becomes the default permission setting on Pro, Max and Team plans, backed by its own study, 89% of simulated dangerous actions blocked against 13.6% caught by human review. The same week brought cross-session messaging and self-hosted environments. But the problem already visible last week, safety filters blocking legitimate coding work, is still alive even in the newest release, and one user automated the reporting and opened 49 issues in a single day. The price has not moved, $17 a month paying the year up front and $20 a month on its own.
What its own users repeat in the August 10, 2026 sweep:
- Safety filters still block legitimate coding work and it remains unresolved: even in the newest release, 2.1.226, there are reports dated this week, and one user automated the reporting with their own tool and opened 49 issues in a single day with the same pattern. Anthropic offers a cyber verification programme as an appeals route, but the block itself keeps happening (strong theme)
- Over 5,000 open issues in its repository, with recent cases such as a permission classifier that non-deterministically blocks commands it used to allow (strong theme)
- From 14 August auto mode will be the default permission setting on Pro, Max and Team, so the already known tendency to keep deciding rather than stop and ask stops being a setting and becomes the factory default (present theme)
- It sends a lot of context before reading your request, the comparison against lighter agents has been coming up for months and this sweep found nothing to contradict it (present theme)
- There is no free working plan: it requires a paid subscription or a console account billed per token (present theme)
Best alternatives to Claude Code
OpenAI's coding agent, included with ChatGPT: local in your terminal or in the cloud.
The code editor built around AI, with agents inside the IDE.
Google's terminal agent, open source with a generous free tier.
What the internet says about each alternative
OpenAI Codex 4/5 · Free + from $8
The official pricing page confirms today the same figures as always: Free at $0, Go at $8. Release pace was high this week: version 0.147.0 on 7 August adds Cursor skill imports and an Agent Plugins catalogue, plus redacting secrets and tokens from the on-screen history, and 0.146.1 on 5 August applies stricter automatic reviews for cyber-capable models. Neither fixes what the sensitive-files exclusion request is asking for, which remains administratively closed since June with a duplicate request still open. July's case of a private repository pushed without permission to OpenAI infrastructure remains the only documented one, with no second occurrence this week.
Where it wins: Entry stays cheap, confirmed today on the official site: a Free plan at $0 a month and a Go at $8 with Codex access, without having to go through the $20 Plus tier Where it slips: The issue asking to exclude sensitive files was closed administratively on 29 June 2026 without the repository showing any new feature or changelog entry to back it up, and a duplicate request remains open asking for the same thing. The on-screen secret redaction that shipped on 7 August hides the display, it does not stop the model from reading the file
Cursor 4/5 · Free + from $20
A quiet week, and today the official site's JSON-LD confirms the same price again: Hobby free, Pro at $20. No dated fact this week clears the bar to move any axis: the removal of dollar-cost figures from the usage page still has not been reverted (the forum thread runs through 9 August with no new official reply), the SpaceX purchase remains unclosed with no public news, and no second vulnerability has surfaced since July's. There were three short incidents on the official status page between 5 and 7 August, all resolved the same day, which do not meet the bar for a sustained outage.
Where it wins: Composer 2.5 has become the daily driver for much of the community, described as fast and cheap for 80% of tasks Where it slips: Vulnerability CVE-2026-63093 was published in July 2026 through full disclosure after the December 2025 private report went unanswered, and the thread telling the story passed 450 points
Gemini CLI 3.3/5 · Free
Nothing structural has changed: the 18 June 2026 cutoff still stands, with no requests served to the free plan nor to Google AI Pro and Ultra, replaced by Antigravity CLI. The repository is not abandoned, it still ships nightly builds nearly daily and keeps its Apache 2.0 licence. What this sweep adds is that Google's own pages do not even agree with each other: the quota documentation states 250 daily requests for the free API key, while the repository README and the geminicli.com homepage still advertise the 60 requests per minute and 1,000 per day plan that is no longer served to individual accounts, six weeks after the shutdown.
Where it wins: The code stays open under Apache 2.0 and the repository ships nightly builds nearly daily, with no archive or read-only notice Where it slips: The free path for individual developers is gone: since 18 June 2026 it serves no requests for the free plan nor for Google AI Pro and Ultra
Comparison table
| Tool | Price | Free trial | Platforms | Rating | Link |
|---|---|---|---|---|---|
| Claude Code | From $17 | No | Web, macOS, Windows | VisitClaude Code (opens in a new tab) | |
| OpenAI Codex | Free + from $8 | No | Web, macOS, Windows | VisitOpenAI Codex (opens in a new tab) | |
| Cursor | Free + from $20 | No | macOS, Windows | VisitCursor (opens in a new tab) | |
| Gemini CLI | Free | No | macOS, Windows | VisitGemini CLI (opens in a new tab) |
Still unsure? Read the full review of Claude Code?