# Best AI coding agents for Terminal Workflows (2026)

> The best AI coding agents platforms for terminal workflows: Cline leads, for developers who live in the shell: an agent that runs as a cli, executes commands.

For terminal workflows, **Cline** is our pick: Where the agent runs matters most for shell-first developers. Developers who live in the shell: an agent that runs as a CLI, executes commands with sensible approval controls, and works over SSH or in CI as well as on a laptop. Below is the full ranking and the tradeoffs, or read [how we score](https://www.versusref.com/methodology/).

## What matters for terminal workflows

Weight ×5 = decisive, ×1 = relevant.

| Fact | Weight | Cline | Kiro | Claude Code | Augment Code | Gemini CLI |
| --- | --- | --- | --- | --- | --- | --- |
| Where it runs | ×5 | VS Code extension, JetBrains plugin, CLI/TUI +3 more (Oct 2) | IDE, CLI, web (Kiro Web), mobile (iOS, preview) +2 more (Oct 2) | Terminal CLI +9 more (Oct 2) | Cosmos (cloud agents, web UI), Auggie CLI +6 more (Oct 2) | CLI, GitHub Action +1 more (Oct 2) |
| Runs terminal commands | ×4 | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) |
| Background / cloud agents | ×3 | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) | ✗  No (Oct 2) |
| MCP support | ×2 | ✓  true (MCP Marketplace) (Oct 2) | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) |
| Project rules files | ×2 | .clinerules/, .cline/rules/, AGENTS.md, .cursorrules +4 more (Oct 2) | Steering files: workspace .kiro/steering/ +5 more (Oct 2) | CLAUDE.md (user/project/local, nested) +6 more (Oct 2) | CLAUDE.md, AGENTS.md (hierarchical) +4 more (Oct 2) | GEMINI.md context files (Oct 2) |

- ×5 **Where it runs:** The page is for agents with a real command-line interface; an IDE-only tool cannot win it.
- ×4 **Runs terminal commands:** Running tests, builds and git from the agent loop is the point of a terminal agent; approval modes decide how safely it does so.
- ×3 **Background / cloud agents:** Headless or cloud runs let the same agent work in CI or while you do something else.
- ×2 **MCP support:** MCP connects the agent to your issue tracker, docs and databases without custom glue.
- ×2 **Project rules files:** Project rules files (AGENTS.md and friends) carry your conventions into every session without re-prompting.

## The ranking, tool by tool

| Rank | Tool | Verdict | Score | Price |
| --- | --- | --- | --- | --- |
| 1 | [Cline](https://www.versusref.com/coding-agents/tools/cline/) (OSS) | Where the agent runs matters most for shell-first developers. | 3 of 4 points · 2 matchups | See pricing |
| 2 | [Kiro](https://www.versusref.com/coding-agents/tools/kiro/) | Where the agent runs matters most for shell users, and Kiro names a CLI among its surfaces alongside its IDE, web app and mobile preview. | 3 of 4 points · 2 matchups | See pricing |
| 3 | [Claude Code](https://www.versusref.com/coding-agents/tools/claude-code/) | Both run as a command-line tool and both execute terminal commands, so the core shell workflow is covered either way. | 25 of 38 points · 19 matchups | See pricing |
| 4 | [Augment Code](https://www.versusref.com/coding-agents/tools/augment-code/) | Where the agent runs matters most for shell-first work. | 1 of 2 points · 1 matchup | See pricing |
| 5 | [Gemini CLI](https://www.versusref.com/coding-agents/tools/gemini-cli/) (OSS) | Where the agent runs matters most here. | 1 of 2 points · 1 matchup | See pricing |
| 6 | [GitLab Duo Agent Platform](https://www.versusref.com/coding-agents/tools/gitlab-duo-agent-platform/) | Where the agent runs matters most for shell users. | 1 of 2 points · 1 matchup | See pricing |
| 7 | [gptme](https://www.versusref.com/coding-agents/tools/gptme/) (OSS) | Both run as a CLI: Aider lists the CLI/terminal plus IDE use via watch-mode code comments, and gptme lists a CLI, web UI, desktop app and a server with a REST API. | 1 of 2 points · 1 matchup | See pricing |
| 8 | [Tabnine](https://www.versusref.com/coding-agents/tools/tabnine/) | Where the agent runs matters most for shell-first developers. | 1 of 2 points · 1 matchup | See pricing |
| 9 | [OpenCode](https://www.versusref.com/coding-agents/tools/opencode/) (OSS) | For shell-first developers, where the agent runs matters most. | 2.5 of 6 points · 3 matchups | See pricing |
| 10 | [Cursor](https://www.versusref.com/coding-agents/tools/cursor/) | Where the agent runs matters most for shell-first developers. | 7 of 22 points · 11 matchups | See pricing |
| 11 | [GitHub Copilot](https://www.versusref.com/coding-agents/tools/github-copilot/) | Where the agent runs matters most for shell-centric work. | 5 of 16 points · 8 matchups | See pricing |
| 12 | [Devin](https://www.versusref.com/coding-agents/tools/devin/) | Both work from the shell: Cosine runs as a CLI called cos plus cloud and desktop apps, and Devin runs as a CLI, a cloud web app and Devin Desktop, plus four more surfaces. | 2 of 8 points · 4 matchups | See pricing |
| 13 | [Crush](https://www.versusref.com/coding-agents/tools/crush/) (OSS) | Source-available (FSL, converts to MIT after 2 years) BYO-model terminal agent; optional Charm-hosted 'Hyper' inference subscription. | 0.5 of 2 points · 1 matchup | See pricing |
| 14 | [Factory](https://www.versusref.com/coding-agents/tools/factory/) | Agent-native dev platform; Droids work locally or as background/cloud agents. Secondary segment: terminal_agent (Droid CLI). Domain moved from factory.ai to factory.com (factory.ai 307-redirects). | 0.5 of 2 points · 1 matchup | See pricing |
| 15 | [OpenHands](https://www.versusref.com/coding-agents/tools/openhands/) (OSS) | MIT-licensed, model-agnostic agent platform; self-host or use OpenHands Cloud (free individual SaaS, enterprise VPC). Also a cloud/async agent. | 0.5 of 2 points · 1 matchup | See pricing |
| 16 | [Aider](https://www.versusref.com/coding-agents/tools/aider/) (OSS) | Aider is a terminal tool first: its surfaces lead with the CLI, plus IDE use through watch-mode code comments. | 1 of 6 points · 3 matchups | See pricing |
| 17 | [Google Antigravity](https://www.versusref.com/coding-agents/tools/google-antigravity/) | For shell-first developers, where the agent runs matters most. | 1 of 6 points · 3 matchups | See pricing |
| 18 | [Amp](https://www.versusref.com/coding-agents/tools/amp/) | Frontier multi-model agent + cloud dev environments (orbs); also terminal_agent (Amp CLI, connects to VS Code/Cursor/Windsurf/Zed/Neovim). OWNERSHIP: no longer branded as Sourcegraph - operated by "Amp Frontier Corporation" (privacy policy, modified Sep 10, 2026); about page: "We are an independent agent research lab"; CLI npm package moved from @sourcegraph/amp to @ampcode/cli (May 14, 2026 changelog). Free Hobby tier with BYOK/ChatGPT-sub since Sep 13, 2026. | 0 of 2 points · 1 matchup | See pricing |
| 19 | [Command Code](https://www.versusref.com/coding-agents/tools/command-code/) | Coding agent for open models (DeepSeek, Kimi, GLM, Qwen, MiniMax) with taste learning; CLI + desktop + ACP for Zed; cheap $1-$20 plans with published $ rolling windows. | 0 of 2 points · 1 matchup | See pricing |
| 20 | [Cosine](https://www.versusref.com/coding-agents/tools/cosine/) | "The Sovereign AI Lab": coding agent + own post-trained Lumen models, pitched at regulated/air-gapped orgs and niche languages (COBOL, Fortran, Verilog). Formerly branded Genie (Genie CLI introduced Q2 2025). Secondary segment: terminal_agent (cos CLI). | 0 of 2 points · 1 matchup | See pricing |
| 21 | [DeepSeek Harness (dsh)](https://www.versusref.com/coding-agents/tools/deepseek-harness/) (OSS) | 'Everything is a Plugin' (Cordis) agent harness from DeepSeek; developer preview with breaking changes; general-purpose, not coding-only. | 0 of 2 points · 1 matchup | See pricing |
| 22 | [Devin Desktop (formerly Windsurf)](https://www.versusref.com/coding-agents/tools/devin-desktop/) | Agentic AI IDE (ex-Windsurf) inside the Devin family; shares plans with Devin Cloud and Devin CLI. | 0 of 6 points · 3 matchups | See pricing |
| 23 | [Freebuff](https://www.versusref.com/coding-agents/tools/freebuff/) (OSS) | Ad-funded free coding agent on curated low-cost models. History: launched as Codebuff (YC); repo and operator (Freebuff, Inc., legal docs effective 2026-09-02) now present Freebuff, built on the Codebuff open multi-agent framework; codebuff.com still sells the premium-model Codebuff CLI ($100-$500/mo). Also desktop, web builder, cloud IDE. | 0 of 2 points · 1 matchup | See pricing |
| 24 | [Goose](https://www.versusref.com/coding-agents/tools/goose/) (OSS) | Local, BYO-model general-purpose agent; also a native desktop app (Rust). Donated by Block to the Linux Foundation's Agentic AI Foundation in 2026. | 0 of 2 points · 1 matchup | See pricing |
| 25 | [Grok Build](https://www.versusref.com/coding-agents/tools/grok-build/) (OSS) | Subscription-bundled vendor terminal agent (SuperGrok / X Premium+), open-sourced Apache-2.0; also embeds in editors via ACP. | 0 of 2 points · 1 matchup | See pricing |
| 26 | [JetBrains Junie](https://www.versusref.com/coding-agents/tools/junie/) | JetBrains IDE agent, now also a terminal agent (Junie CLI) and runs in JetBrains Air; metered in JetBrains AI Credits ($1 each) with BYOK at provider rates, zero markup. | 0 of 2 points · 1 matchup | See pricing |
| 27 | [Kilo Code](https://www.versusref.com/coding-agents/tools/kilo-code/) (OSS) | OSS multi-surface agent; zero-markup inference gateway + Kilo Pass credit bundles; started as a Roo Code fork, now built on the OpenCode core (also terminal_agent, cloud_agent). | 0 of 4 points · 2 matchups | See pricing |
| 28 | [Kimi Code](https://www.versusref.com/coding-agents/tools/kimi-code/) (OSS) | Open-weight model vendor's agent, included with Kimi membership; MIT CLI also takes other providers. | 0 of 2 points · 1 matchup | See pricing |
| 29 | [Letta Code](https://www.versusref.com/coding-agents/tools/letta-code/) (OSS) | Persistent-memory coding agent (Apache-2.0); CLI + desktop + browser + Slack/Telegram/Discord channels; optional Letta Cloud ($20/mo Pro). | 0 of 2 points · 1 matchup | See pricing |
| 30 | [Mistral Vibe](https://www.versusref.com/coding-agents/tools/mistral-vibe/) (OSS) | European vendor agent with open-weight local models and self-hosting; also IDE extension and cloud_agent (remote agents, teleport). | 0 of 2 points · 1 matchup | See pricing |
| 31 | [OpenAI Codex](https://www.versusref.com/coding-agents/tools/openai-codex/) | Coding agent across CLI (Apache-2.0), IDE extension, Codex Cloud (cloud_agent) and ChatGPT desktop app; usage shared with ChatGPT Work. The standalone Codex app merged into the ChatGPT desktop app on 2026-07-09. | 0 of 8 points · 4 matchups | See pricing |
| 32 | [Pi](https://www.versusref.com/coding-agents/tools/pi/) (OSS) | Minimal-by-design harness: no built-in subagents, plan mode or permission popups; extend via packages, skills and SDK. | 0 of 2 points · 1 matchup | See pricing |
| 33 | [Qwen Code](https://www.versusref.com/coding-agents/tools/qwen-code/) (OSS) | Open-source multi-provider agent from an open-weight model lab; also desktop app, web UI and VS Code/JetBrains/Zed plugins. | 0 of 2 points · 1 matchup | See pricing |
| 34 | [Tabby](https://www.versusref.com/coding-agents/tools/tabby/) (OSS) | Self-hosted completion server + IDE plugins; low activity in 2026 (chat/knowledge features sunset Jan 2026, vendor focus shifted to its Pochi agent). | 0 of 2 points · 1 matchup | See pricing |
| 35 | [Trae](https://www.versusref.com/coding-agents/tools/trae/) | Low-priced AI IDE (Free/Lite/Pro/Pro+/Ultra); product family now split into TraeCode (IDE) and TraeWork (web/desktop/mobile workspace built on SOLO). Owner per brief: ByteDance - the legal entity could not be read from a primary source (privacy policy/ToS are client-rendered); enterprise page cites Douyin as a customer. Chats may be used for training unless Privacy Mode is on. | 0 of 2 points · 1 matchup | See pricing |
| 36 | [Verdent](https://www.versusref.com/coding-agents/tools/verdent/) | Plan-Code-Verify multi-model agent; desktop app (primary, most changelog activity), VS Code/JetBrains plugins, Slack/Telegram control; increasingly pitched as an 'AI technical cofounder' with app deployment. | 0 of 2 points · 1 matchup | See pricing |
| 37 | [Warp](https://www.versusref.com/coding-agents/tools/warp/) | Agentic terminal / ADE with credit-metered agents and cloud agent orchestration ("Warp Factories"). Secondary segment: cloud_agent. Client source available under AGPL-3.0. | 0 of 2 points · 1 matchup | See pricing |
| 38 | [Zed](https://www.versusref.com/coding-agents/tools/zed/) (OSS) | Fast OSS editor with agentic features; free with your own keys or external agents, Pro $10/mo adds $5 of hosted-model tokens at list +10%. Also oss_self_hosted-adjacent (GPL editor, local models). | 0 of 2 points · 1 matchup | See pricing |

### 1. Cline

Where the agent runs matters most for shell-first developers. [Full Cline vs Cursor verdict](https://www.versusref.com/coding-agents/cline-vs-cursor/)

Both tools ship beyond the editor: Cline runs as a VS Code extension, JetBrains plugin and CLI/TUI, and Kilo Code as a VS Code extension, JetBrains plugin and CLI. [Full Cline vs Kilo Code verdict](https://www.versusref.com/coding-agents/cline-vs-kilo-code/)

### 2. Kiro

Where the agent runs matters most for shell users, and Kiro names a CLI among its surfaces alongside its IDE, web app and mobile preview. [Full Kiro vs Cursor verdict](https://www.versusref.com/coding-agents/cursor-vs-kiro/)

Where the agent runs matters most for shell-first developers. [Full Kiro vs Devin Desktop (formerly Windsurf) verdict](https://www.versusref.com/coding-agents/devin-desktop-vs-kiro/)

### 3. Claude Code

Both run as a command-line tool and both execute terminal commands, so the core shell workflow is covered either way. [Full Claude Code vs Kimi Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-kimi-code/)

For shell-first developers, where the agent runs is the deciding factor. [Full Claude Code vs OpenAI Codex verdict](https://www.versusref.com/coding-agents/claude-code-vs-openai-codex/)

Claude Code is built around the shell: its surfaces start with a terminal CLI, plus nine more, while GitHub Copilot's lead with IDE extensions and GitHub.com chat and agents. [Full Claude Code vs GitHub Copilot verdict](https://www.versusref.com/coding-agents/claude-code-vs-github-copilot/)

Where the agent runs matters most for shell-first work. [Full Claude Code vs Google Antigravity verdict](https://www.versusref.com/coding-agents/claude-code-vs-google-antigravity/)

For shell-first developers, where the agent runs matters most, and both have a CLI. [Full Claude Code vs Devin verdict](https://www.versusref.com/coding-agents/claude-code-vs-devin/)

For shell-first developers, where the agent runs matters most. [Full Claude Code vs Amp verdict](https://www.versusref.com/coding-agents/amp-vs-claude-code/)

Both tools are built around the shell, so this is close. [Full Claude Code vs Warp verdict](https://www.versusref.com/coding-agents/claude-code-vs-warp/)

Both run as a CLI: Claude Code lists a terminal CLI plus nine more surfaces, and Mistral Vibe lists a CLI, VS Code, JetBrains, Zed, the web and one more. [Full Claude Code vs Mistral Vibe verdict](https://www.versusref.com/coding-agents/claude-code-vs-mistral-vibe/)

Both are built for the shell: Claude Code lists a terminal CLI among ten surfaces, and OpenCode lists a terminal TUI and a CLI among seven. [Full Claude Code vs OpenCode verdict](https://www.versusref.com/coding-agents/claude-code-vs-opencode/)

Both tools run as terminal CLIs and both execute terminal commands, so the shell basics are covered either way. [Full Claude Code vs Aider verdict](https://www.versusref.com/coding-agents/aider-vs-claude-code/)

Both run as a CLI: Claude Code lists a terminal CLI plus nine more surfaces, and Goose lists desktop, CLI and API. [Full Claude Code vs Goose verdict](https://www.versusref.com/coding-agents/claude-code-vs-goose/)

Both are built for the shell: Claude Code lists a terminal CLI plus nine more surfaces, and Qwen Code lists a CLI, a desktop app and three more. [Full Claude Code vs Qwen Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-qwen-code/)

Both are built for the shell. [Full Claude Code vs Pi verdict](https://www.versusref.com/coding-agents/claude-code-vs-pi/)

Both are true shell tools. [Full Claude Code vs Grok Build verdict](https://www.versusref.com/coding-agents/claude-code-vs-grok-build/)

Both are shell-first. [Full Claude Code vs Command Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-command-code/)

Both tools run as a CLI: Claude Code lists a terminal CLI plus nine more surfaces, and Letta Code offers a CLI, desktop and web plus one more. [Full Claude Code vs Letta Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-letta-code/)

Where the agent runs matters most for shell work. [Full Claude Code vs DeepSeek Harness (dsh) verdict](https://www.versusref.com/coding-agents/claude-code-vs-deepseek-harness/)

For shell-first developers, where the agent runs is the deciding factor. [Full Claude Code vs Cursor verdict](https://www.versusref.com/coding-agents/claude-code-vs-cursor/)

Both run in the shell: Claude Code lists a terminal CLI among ten surfaces, and Freebuff lists a CLI alongside desktop, web, cloud and chat. [Full Claude Code vs Freebuff verdict](https://www.versusref.com/coding-agents/claude-code-vs-freebuff/)

### 4. Augment Code

Where the agent runs matters most for shell-first work. [Full Augment Code vs Cursor verdict](https://www.versusref.com/coding-agents/augment-code-vs-cursor/)

### 5. Gemini CLI

Where the agent runs matters most here. [Full Gemini CLI vs Google Antigravity verdict](https://www.versusref.com/coding-agents/gemini-cli-vs-google-antigravity/)

### 6. GitLab Duo Agent Platform

Where the agent runs matters most for shell users. [Full GitLab Duo Agent Platform vs GitHub Copilot verdict](https://www.versusref.com/coding-agents/github-copilot-vs-gitlab-duo-agent-platform/)

### 7. gptme

Both run as a CLI: Aider lists the CLI/terminal plus IDE use via watch-mode code comments, and gptme lists a CLI, web UI, desktop app and a server with a REST API. [Full gptme vs Aider verdict](https://www.versusref.com/coding-agents/aider-vs-gptme/)

### 8. Tabnine

Where the agent runs matters most for shell-first developers. [Full Tabnine vs GitHub Copilot verdict](https://www.versusref.com/coding-agents/github-copilot-vs-tabnine/)

### 9. OpenCode

For shell-first developers, where the agent runs matters most. [Full OpenCode vs Kilo Code verdict](https://www.versusref.com/coding-agents/kilo-code-vs-opencode/)

### 10. Cursor

Where the agent runs matters most for shell-first developers. [Full Cursor vs GitHub Copilot verdict](https://www.versusref.com/coding-agents/cursor-vs-github-copilot/)

For shell-first developers, where the agent runs matters most. [Full Cursor vs Devin Desktop (formerly Windsurf) verdict](https://www.versusref.com/coding-agents/cursor-vs-devin-desktop/)

Where the agent runs matters most for shell-first developers. [Full Cursor vs OpenAI Codex verdict](https://www.versusref.com/coding-agents/cursor-vs-openai-codex/)

Where the agent runs matters most for shell users. [Full Cursor vs Zed verdict](https://www.versusref.com/coding-agents/cursor-vs-zed/)

For shell-first developers, where the agent runs matters most. [Full Cursor vs Trae verdict](https://www.versusref.com/coding-agents/cursor-vs-trae/)

For shell-first developers, where the agent runs matters most. [Full Cursor vs Verdent verdict](https://www.versusref.com/coding-agents/cursor-vs-verdent/)

### 11. GitHub Copilot

Where the agent runs matters most for shell-centric work. [Full GitHub Copilot vs Devin Desktop (formerly Windsurf) verdict](https://www.versusref.com/coding-agents/devin-desktop-vs-github-copilot/)

Where the agent runs is the deciding factor for shell-first work. [Full GitHub Copilot vs OpenAI Codex verdict](https://www.versusref.com/coding-agents/github-copilot-vs-openai-codex/)

Neither tool leads with a standalone CLI. [Full GitHub Copilot vs JetBrains Junie verdict](https://www.versusref.com/coding-agents/github-copilot-vs-junie/)

Shell-first developers need to know where the agent runs and whether it executes commands. [Full GitHub Copilot vs Tabby verdict](https://www.versusref.com/coding-agents/github-copilot-vs-tabby/)

### 12. Devin

Both work from the shell: Cosine runs as a CLI called cos plus cloud and desktop apps, and Devin runs as a CLI, a cloud web app and Devin Desktop, plus four more surfaces. [Full Devin vs Cosine verdict](https://www.versusref.com/coding-agents/cosine-vs-devin/)

### 13. Crush

Source-available (FSL, converts to MIT after 2 years) BYO-model terminal agent; optional Charm-hosted 'Hyper' inference subscription. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 14. Factory

Agent-native dev platform; Droids work locally or as background/cloud agents. Secondary segment: terminal_agent (Droid CLI). Domain moved from factory.ai to factory.com (factory.ai 307-redirects). No won verdicts for this use case yet; it ranks on ties and near-misses.

### 15. OpenHands

MIT-licensed, model-agnostic agent platform; self-host or use OpenHands Cloud (free individual SaaS, enterprise VPC). Also a cloud/async agent. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 16. Aider

Aider is a terminal tool first: its surfaces lead with the CLI, plus IDE use through watch-mode code comments. [Full Aider vs OpenAI Codex verdict](https://www.versusref.com/coding-agents/aider-vs-openai-codex/)

### 17. Google Antigravity

For shell-first developers, where the agent runs matters most. [Full Google Antigravity vs Cursor verdict](https://www.versusref.com/coding-agents/cursor-vs-google-antigravity/)

### 18. Amp

Frontier multi-model agent + cloud dev environments (orbs); also terminal_agent (Amp CLI, connects to VS Code/Cursor/Windsurf/Zed/Neovim). OWNERSHIP: no longer branded as Sourcegraph - operated by "Amp Frontier Corporation" (privacy policy, modified Sep 10, 2026); about page: "We are an independent agent research lab"; CLI npm package moved from @sourcegraph/amp to @ampcode/cli (May 14, 2026 changelog). Free Hobby tier with BYOK/ChatGPT-sub since Sep 13, 2026. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 19. Command Code

Coding agent for open models (DeepSeek, Kimi, GLM, Qwen, MiniMax) with taste learning; CLI + desktop + ACP for Zed; cheap $1-$20 plans with published $ rolling windows. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 20. Cosine

"The Sovereign AI Lab": coding agent + own post-trained Lumen models, pitched at regulated/air-gapped orgs and niche languages (COBOL, Fortran, Verilog). Formerly branded Genie (Genie CLI introduced Q2 2025). Secondary segment: terminal_agent (cos CLI). No won verdicts for this use case yet; it ranks on ties and near-misses.

### 21. DeepSeek Harness (dsh)

'Everything is a Plugin' (Cordis) agent harness from DeepSeek; developer preview with breaking changes; general-purpose, not coding-only. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 22. Devin Desktop (formerly Windsurf)

Agentic AI IDE (ex-Windsurf) inside the Devin family; shares plans with Devin Cloud and Devin CLI. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 23. Freebuff

Ad-funded free coding agent on curated low-cost models. History: launched as Codebuff (YC); repo and operator (Freebuff, Inc., legal docs effective 2026-09-02) now present Freebuff, built on the Codebuff open multi-agent framework; codebuff.com still sells the premium-model Codebuff CLI ($100-$500/mo). Also desktop, web builder, cloud IDE. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 24. Goose

Local, BYO-model general-purpose agent; also a native desktop app (Rust). Donated by Block to the Linux Foundation's Agentic AI Foundation in 2026. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 25. Grok Build

Subscription-bundled vendor terminal agent (SuperGrok / X Premium+), open-sourced Apache-2.0; also embeds in editors via ACP. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 26. JetBrains Junie

JetBrains IDE agent, now also a terminal agent (Junie CLI) and runs in JetBrains Air; metered in JetBrains AI Credits ($1 each) with BYOK at provider rates, zero markup. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 27. Kilo Code

OSS multi-surface agent; zero-markup inference gateway + Kilo Pass credit bundles; started as a Roo Code fork, now built on the OpenCode core (also terminal_agent, cloud_agent). No won verdicts for this use case yet; it ranks on ties and near-misses.

### 28. Kimi Code

Open-weight model vendor's agent, included with Kimi membership; MIT CLI also takes other providers. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 29. Letta Code

Persistent-memory coding agent (Apache-2.0); CLI + desktop + browser + Slack/Telegram/Discord channels; optional Letta Cloud ($20/mo Pro). No won verdicts for this use case yet; it ranks on ties and near-misses.

### 30. Mistral Vibe

European vendor agent with open-weight local models and self-hosting; also IDE extension and cloud_agent (remote agents, teleport). No won verdicts for this use case yet; it ranks on ties and near-misses.

### 31. OpenAI Codex

Coding agent across CLI (Apache-2.0), IDE extension, Codex Cloud (cloud_agent) and ChatGPT desktop app; usage shared with ChatGPT Work. The standalone Codex app merged into the ChatGPT desktop app on 2026-07-09. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 32. Pi

Minimal-by-design harness: no built-in subagents, plan mode or permission popups; extend via packages, skills and SDK. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 33. Qwen Code

Open-source multi-provider agent from an open-weight model lab; also desktop app, web UI and VS Code/JetBrains/Zed plugins. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 34. Tabby

Self-hosted completion server + IDE plugins; low activity in 2026 (chat/knowledge features sunset Jan 2026, vendor focus shifted to its Pochi agent). No won verdicts for this use case yet; it ranks on ties and near-misses.

### 35. Trae

Low-priced AI IDE (Free/Lite/Pro/Pro+/Ultra); product family now split into TraeCode (IDE) and TraeWork (web/desktop/mobile workspace built on SOLO). Owner per brief: ByteDance - the legal entity could not be read from a primary source (privacy policy/ToS are client-rendered); enterprise page cites Douyin as a customer. Chats may be used for training unless Privacy Mode is on. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 36. Verdent

Plan-Code-Verify multi-model agent; desktop app (primary, most changelog activity), VS Code/JetBrains plugins, Slack/Telegram control; increasingly pitched as an 'AI technical cofounder' with app deployment. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 37. Warp

Agentic terminal / ADE with credit-metered agents and cloud agent orchestration ("Warp Factories"). Secondary segment: cloud_agent. Client source available under AGPL-3.0. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 38. Zed

Fast OSS editor with agentic features; free with your own keys or external agents, Pro $10/mo adds $5 of hosted-model tokens at list +10%. Also oss_self_hosted-adjacent (GPL editor, local models). No won verdicts for this use case yet; it ranks on ties and near-misses.

Source: https://www.versusref.com/coding-agents/best/terminal/