Cline (harness)

https://cline.bot

OSS VS Code extension that runs as a fully agentic coding assistant — plan/act modes, file ops, shell exec, browser-use, MCP. Originally "Claude Dev" (2024); rebranded Cline 2024-Q4. Multi-model: Anthropic, OpenAI, OpenRouter, Bedrock, Vertex. Memory layer = .clinerules and Memory Bank pattern (distinct rows in catalog).

At a glance

Type
VS Code agentic coding extension (OSS, formerly Claude Dev)
Tier
T2
Created
2024-07
Latest release
Cline 3.x (2025-2026 rolling)
License
Apache-2.0
Pricing
Free (OSS) + paid Pro
Funding
Cline Inc. — Series A reported (2025; HQ undisclosed)

Taxonomy

storage
file
retrieval
injection
persistence
cross-session
update
hybrid
unit
document
governance
inspectable
conflict
human-arbitrate

When to use

Optimised for: Plan/Act loop with explicit human approval gates

Anti-fit: VS Code-only; cost-per-run can spike on long sessions

Pros & cons

Pros

Strongest plan-then-act safety pattern in the OSS coding-agent set; Memory Bank pattern (.cline-memory-bank/) influenced wider "memory in markdown" practice.

Cons

VS Code only (no JetBrains, no terminal); per-token costs surprise users on long autonomous runs.

Claims & capabilities

~45k★ GH; one of the most-installed agentic VS Code extensions; multi-model via standard OpenAI-compatible APIs.

Technical surface

API surface
VS Code extension
Backend storage
local workspace + .clinerules
Deployment
VS Code extension (desktop) + Pro cloud
Embedding model
not applicable — not a memory product
Multi-tenancy
per-user; Pro per-org
MCP
native — Cline is an MCP client
A2A
searched not found
OpenTelemetry
searched not found

Similar systems

Other agent ides & coding harnesses in the catalog, ranked by inbound references.

  • Bedrock AgentCore (AWS) T2

    AWS Bedrock AgentCore — managed runtime to deploy + scale + observe agents. Multi-component: Runtime, Identity, Memory, Gateway, Browser, Code Interpreter, Observability. Distinct from Bedrock Agents (older fixed-config product); AgentCore is the 2025 framework-agnostic runtime for any agent (LangGraph, CrewAI, Strands, OpenAI Agents SDK).

  • Claude Code (Anthropic) T1

    Anthropic's official agentic coding CLI — runs Claude as a long-running coding agent in the developer's terminal. Memory layer = CLAUDE.md (project + user scoped), agent skills, MCP servers. Released GA October 2024; widely adopted as the reference harness for Claude-as-coder. Plan Mode and Compute Use surfaces extend it from coding to broader desktop automation.

  • GitHub Copilot (Agent Mode) T1

    The original AI coding assistant (Copilot in editor; 2021). 2025 evolved into a full agentic surface: chat, completions, Agent Mode (multi-step), and Copilot Workspace. Backed by Microsoft. Distinct row from Workspace — this row covers the everyday in-editor + agent mode product, Workspace covers the hosted spec-driven workflow.

  • Aider (harness) T2

    OSS terminal coding agent by Paul Gauthier — one of the original AI-pair-programmer CLIs (2023). Architect/Editor modes; repo-map for context; uses any LiteLLM-compatible model. Memory via CONVENTIONS.md and .aider.conf.yml — author-edited markdown. Distinct from the separate Aider memory-row in "Coding-agent memory"; this row characterises the harness itself.

  • Amazon Q Developer T1

    Amazon's developer-focused agent — formerly CodeWhisperer (renamed 2024-Q4). Available as IDE plugins (VS Code, JetBrains, Visual Studio, Eclipse), in AWS Console, and CLI. Strong AWS-tooling integration: Q can read CloudWatch, troubleshoot IAM, suggest AWS-SDK code. Companion to Kiro for spec-driven flows.

  • Anthropic Computer Use T1

    Anthropic's API-surface capability that lets Claude control a virtual desktop — see screenshots, type, click. Launched 2024-10 as a public beta. Not a finished IDE itself; it's the substrate that other harnesses (and Anthropic's own Claude apps) use to operate a computer.

Related systems

References (2)

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.