Cline

The agent runs terminal commands and reacts to their output, calls MCP servers the developer adds, drives a Chromium browser, and connects to Slack, Discord, Telegram and Linear for conversation and to GitHub Actions and GitLab for headless runs.

Sourcecline.bot and docs.cline.bot (MCP overview)read 2026-09-29

Multi agent teams let coordinator agents delegate to specialist agents with their own tools, agent teams coordinate from the CLI, and a Kanban board runs several coding agents in parallel in isolated git worktrees.

Sourcecline.bot and docs.cline.bot (Kanban, agent teams)read 2026-09-29

The agent reads the project as it works, with.clinerules for standards, @git and @terminal mentions and MCP servers for outside sources. Cline states it avoids indexing the customer's code, so context is assembled per run and no persistent index, graph or embeddings layer exists.

Sourcedocs.cline.bot enterprise overview and cline.botread 2026-09-29

Plan mode aligns on a strategy before execution, and in Act mode the developer approves every step by default, with auto approve an opt in that can be scoped per action type, plus diffs, checkpoints and one click undo.

Sourcecline.bot and docs.cline.bot (plan and act, auto approve)read 2026-09-29

Enterprise adds SSO, role based access control with Member, Admin and Owner roles, remote configuration, limits on inference providers, MCP controls and authentication logs, and the client side architecture keeps code in the customer's environment. No SOC 2 or other attestation is named on the enterprise pages.

Sourcedocs.cline.bot enterprise overview, cline.bot/enterprise and cline.bot/pricingread 2026-09-29

OpenTelemetry export sends per action events to the customer's Datadog, Grafana or Splunk: task.tool_used with tool name, success, duration and whether it was auto approved, MCP tool calls with server and status, terminal executions, and accepted and rejected edits, alongside task lifecycle and token events.

Sourcedocs.cline.bot/enterprise-solutions/monitoring/opentelemetry-eventsread 2026-09-29

Checkpoints capture workspace state during a task for rollback, and the Memory Bank is a documented method the user sets up through custom instructions, with Cline updating markdown files it reads across sessions. The Memory Bank is not a built in memory layer and states no lifetime or purge path, and rules and mode preferences are instructions and settings.

Sourcedocs.cline.bot memory bank and checkpointsread 2026-09-29

Enterprise runs in the customer's VPC, on premises or air gapped, the client side architecture sends inference straight to the customer's own Bedrock, Vertex, Azure OpenAI or local models without passing through Cline's servers, and the open source agent runs in the developer's editor or terminal.

Sourcecline.bot/enterprise and cline.botread 2026-09-29

An MCP Marketplace ships in the open source product as a catalog of servers installable in one click, and modular Skills package instruction sets for specific tasks.

Sourcecline.bot/pricing and docs.cline.bot (skills, MCP overview)read 2026-09-29

The CLI runs agents on cron schedules through its hub, unattended and persisting across restarts, for work such as daily summaries and dependency checks, and agents also run headlessly in CI and answer from Slack, Discord, Telegram and Linear, so work reaches the agent without a person starting it.

Sourcedocs.cline.bot/cli/scheduling and cline.botread 2026-09-29

Works with every major provider on the customer's own key, Claude, GPT, Gemini, local Ollama or LM Studio and any OpenAI compatible endpoint, with enterprise connections to Bedrock, Vertex and Azure OpenAI and admin limits on which providers teams may use.

Sourcecline.bot and cline.bot/enterpriseread 2026-09-29

The Cline SDK publishes TypeScript packages for embedding Cline's agent runtime in other applications, and the CLI runs headless for scripts and pipelines.

Sourcedocs.cline.bot/sdk/overview and CLI overviewread 2026-09-29

The agent makes linter aware fixes, runs tests and checks UI work in a real browser, and checkpoints let a failed attempt be rolled back; these check the agent's own output, and no harness to evaluate or regression test agent behavior is documented.

Sourcecline.bot and docs.cline.botread 2026-09-29

A browser action tool drives a Chromium browser the agent navigates, clicks, types and scrolls in, reading a screenshot and console logs after each action, and remote browser support reuses an existing Chrome session's logins.

Sourcedocs.cline.bot and cline.botread 2026-09-29