Skip to content
DevAgentRadarDevAgentRadar
Sign in
Assistants/Cline

Cline

Cline · ide agent · free

Open-source autonomous coding agent in the IDE with plan/act workflows and MCP.

open-sourceagentmcpvscodecli
Website ↗Docs ↗
Is this coverage useful?

Helps prioritize which assistants and sources we maintain. Anonymous · one vote per visitor.

Config files Cline has changed

Config you own — hooks, permission rules, MCP servers, settings — that releases below state a change to. Counted from the release notes we track, newest change first. How a harness is layered.

MCP server config8 changes · 24 releases touched it · latest Oct 7, 2026 · SDK 0.0.91 ↗
skills and plugins8 changes · 22 releases touched it · latest Oct 16, 2026 · CLI 3.0.72 ↗
background and headless runs4 changes · 13 releases touched it · latest Sep 30, 2026 · SDK 0.0.88 ↗
hooks3 changes · 16 releases touched it · latest Sep 22, 2026 · v4.1.20 ↗
slash commands2 changes · 4 releases touched it · latest Sep 25, 2026 · Desktop 0.0.36 ↗
context and compaction settings1 change · 5 releases touched it · latest Sep 24, 2026 · SDK 0.0.86 ↗
subagent definitions1 change · 3 releases touched it · latest Sep 22, 2026 · SDK 0.0.84 ↗

Security advisories

3 published for Cline CLI, from the GitHub Advisory Database.

Release signals

Cline3.81.0Jul 26, 2026

Add GPT-5.5 model support for OpenAI Codex subscription users.

  • Remove hardcoded "What’s New" fallback items in webview; only remote-configured welcome banners are shown.
  • Improve cline-core memory diagnostics used by the extension runtime:
  • enable near-heap-limit heap snapshots
  • add periodic memory usage logging
  • log discovered heap snapshots on abnormal exits for easier OOM debugging
Primary source ↗
Cline3.80.0Jul 26, 2026

Wire up remote `globalSkills` from enterprise remote config with full UI, toggle support, and system prompt integration — enterprise-managed skills now appear under a dedicated "Enterprise Skills" section and support `alwaysEnabled` enforcement

  • Onboarding flow now uses dynamically fetched recommended models instead of a hardcoded list, with a fallback to the welcome view on failure
  • Add dedicated "Quota Exceeded" error message in the chat error UI when Cline account spend caps are hit
  • +5 more changes
Read the full release note

Added

  • Wire up remote globalSkills from enterprise remote config with full UI, toggle support, and system prompt integration — enterprise-managed skills now appear under a dedicated "Enterprise Skills" section and support alwaysEnabled enforcement
  • Onboarding flow now uses dynamically fetched recommended models instead of a hardcoded list, with a fallback to the welcome view on failure
  • Add dedicated "Quota Exceeded" error message in the chat error UI when Cline account spend caps are hit

Fixed

  • Fix OOM crashes during long conversations by setting --max-old-space-size=8192 for the cline-core Node.js process (was defaulting to ~2 GB)
  • Show detailed error information in the chat error row instead of a generic caught error message
  • Update axios to 1.15.0 across all packages

Changed

  • Remove foreground terminal mode — all task command execution now defaults to background mode, removing the VS Code integrated terminal dependency and related settings UI
  • Remove old hardcoded announcement banners
Primary source ↗
Cline3.79.0Jul 26, 2026

Add Claude Opus 4.7 model support

  • Add Azure Blob Storage as a storage provider
  • Add `globalSkills` to remote config
  • Inline value reuse in user-level remote-config discovery
  • Fix cache reflection for Cline and Vercel API handlers
  • Fix stuck `command_output` ask when terminal command ends unexpectedly
  • Add `use_subagents` to system prompt for GLM, Hermes, and XS models
  • Fix action injection security risk
  • Remove deprecated evals tool
Primary source ↗
Cline3.76.0Jul 26, 2026

Add Cline Kanban launch modal in webview;

  • CLI now launches Kanban by default with a migration view
  • Add toggle to disable feature tips in chat
  • Add repeated tool call loop detection to prevent infinite loops wasting tokens
  • Fix CLI Kanban spawn on Windows by enabling shell mode for `npx.cmd`
Primary source ↗
Cline3.74.0Jul 26, 2026

Implement dynamic free model detection for Cline API

  • Add file read deduplication cache to prevent repeated reads
  • Add feature tips tooltip during thinking state
  • Replace error message when not logged in to Cline
  • Align ClineRulesToggleModal padding with ServersToggleModal
  • Skip WebP for GLM and Devstral models running through llama.cpp
  • Respect user-configured context window in LiteLLM getModel()
  • Honor explicit model IDs outside static catalog in W&B provider
  • Add missing Fireworks serverless models and pricing
Primary source ↗
Cline3.73.0Jul 26, 2026

Added W&B Inference by CoreWeave as a new API provider with 17 models

  • Improved parallel tool calling support for OpenRouter and Cline providers
  • Claude Code Provider: handle rate limit events, empty content arrays, error results, and unknown content types without crashing
  • Tool handlers (`read_file`, `list_files`, `list_code_definition_names`, `search_files`) now return graceful errors instead of crashing
Primary source ↗
Cline3.72.0Jul 26, 2026

Added Anthropic Opus 4.6 fast mode variants

  • Resolved native tool placeholder interpolation in prompts
  • Gemini: capped Flash output tokens to 8192 across providers
  • Fixed Windows unit test path normalization
  • Fixed flaky hooks tests on Windows
  • Bedrock: handle thinking and redacted_thinking blocks correctly in message conversion and streaming
  • Prevent crash when `list_files` or `list_code_definition_names` receives a file path
  • Updated Jupyter Notebook GIFs
  • Markdown image loading now requires user consent
  • Added `.github/copilot-instructions.md` for coding agents
  • +1 more change
Primary source ↗
Cline3.70.0Jul 26, 2026

New Cline API docs: Getting Started, Auth, Chat Completions, Models, Errors, and SDK Examples

  • Hook payloads now include `model.provider` and `model.slug`
  • Token/cost updates now happen immediately as usage chunks arrive, not after tool execution
  • Improve subagent context compaction logic
  • Subagent stream retry delay increased to reduce noise from transient failures
  • State serialization errors are now caught and logged instead of crashing
  • Removed incorrect `max_tokens` from OpenRouter requests
  • Windows test cleanup now retries on locked files and applies per-test timeouts
  • +1 more change
Primary source ↗
Cline3.69.0Jul 26, 2026

Add `User-Agent` header to requests sent to the Cline backend

  • Add default auto-tag workflow for publish release flow
  • Show Cline SDK docs on the Cline page
  • Retry nested git restore and prevent silent `.git_disabled` leftovers in checkpoints
  • Prevent Chinese filename escaping in diff view
  • Trigger auto-compaction on OpenRouter context overflow errors
  • Restore GPT-OSS native file editing on OpenAI-compatible models
  • Update Cline SDK docs
  • Improve hooks support for Windows PowerShell
Primary source ↗
Cline3.68.0Jul 26, 2026

Add dynamic Cline provider model fetching from Cline endpoint

  • Add additional Markdown formatting in CLI
  • Add focus indicator on action buttons in extension
  • Clear all OCA secrets on auth refresh failure to prevent re-auth loops
  • Resolve "Could not find the file context" error in Explain Changes
  • Use `JSON_SCHEMA` for `yaml.load` to prevent unsafe deserialization
  • Fetch model info from API in CLI headless auth for Cline and Vercel providers
  • Generate commit message from staged changes only when staging exists
  • +3 more changes
Read the full release note

Added

  • Add dynamic Cline provider model fetching from Cline endpoint
  • Add additional Markdown formatting in CLI
  • Add focus indicator on action buttons in extension

Fixed

  • Clear all OCA secrets on auth refresh failure to prevent re-auth loops
  • Resolve "Could not find the file context" error in Explain Changes
  • Use JSON_SCHEMA for yaml.load to prevent unsafe deserialization
  • Fetch model info from API in CLI headless auth for Cline and Vercel providers
  • Generate commit message from staged changes only when staging exists
  • Update stale maxTokens values for Claude 3.7+ models across Anthropic, Bedrock, Vertex, and SAP AI Core
  • Use model.info.maxTokens for OpenRouter instead of hardcoded 8192

Changed

  • Increase timeout for a flaky test to reduce short-term test instability
Primary source ↗

Polled sources

[docs-site] Cline Docs

Product page · not polled

https://docs.cline.bot

[github-releases] GitHub Releases

GitHub Releases · last read Oct 24, 2026

https://github.com/cline/cline/releases

[changelog-md] CHANGELOG.md

Changelog · last read Oct 24, 2026

https://raw.githubusercontent.com/cline/cline/main/CHANGELOG.md