Cline
Latest release v4.1.26 on 2026-10-26 · Actively maintained · 15 releases in 90 days
Autonomous coding agent as an SDK, IDE extension, or CLI assistant.
| Latest release | v4.1.26 on 2026-10-26 |
|---|---|
| Maintenance | Actively maintained — pushed within the last 14 days, with 3 or more releases in 90 days |
| Stars | 71,020 (+108 since yesterday) |
| Releases in 90 days | 15 |
| Last commit | 2026-10-29 |
| Repository | cline/cline |
| Licence | Apache-2.0 |
| Open issues | 1,727 |
Cline release notes and changelog
v4.1.26 2026-10-26
What's new
- Cloud tasks: Settings > API Configuration has a Local | Cloud toggle when cloud sessions are…
- Starting or resuming a cloud sandbox shows a progress card with the repo, branch and steps…
Fixed
- GPT-6 models (such as gpt-6-sol and gpt-6.1-sol) work on OpenAI and Azure OpenAI-compatible…
- Gemini API keys (the gemini provider) no longer send native Google Search. Free-tier keys…
- Toggling Plan/Act while a task is starting no longer drops your first prompt, and the session…
- Disabled rules stay disabled
Changed
- Cloud sessions hide the Plan/Act toggle and the auto-approve bar instead of showing them…
- With no model chosen, the Cline provider uses Claude Sonnet 5.5 again, which is back at the…
- Model requests retry at most 3 times instead of 5
- Kimi K3 now gets max reasoning for Extra High and Max, instead of an xhigh setting it rejects
sdk/sdk/v0.2.0 2026-10-26
Starting a session that already has a run in progress now reattaches to the live session instead of replacing its runtime. Before, the original run…
desktop-v0.0.49 2026-10-26
What's new
- New Cloud chats start on your local Cline or ClinePass model. If Cloud doesn't offer that…
Other coding agents we track
- OpenClaw · v2026.10.10-beta.4
- Hermes · v0.22.5
- OpenCode · v2.2.1
- AutoGPT · preview-seed-fixture
- Claude Code · v2.1.312
- Codex · rust-v0.166.0-alpha.6
- Browser Use · 0.13.14
- Pi · v1.4.0
Maintenance status is derived from public repository activity — release cadence and commit recency. It is not a review, an endorsement, or a security assessment. Star counts measure attention, not quality.