# Best AI coding agents for Free Plans (2026)

> The best AI coding agents platforms for free plans: Amp leads, for developers who want real agent work without paying yet: what a free tier actually allows.

For free plans, **Amp** is our pick: What the free plan allows is the deciding factor, and here the two are far apart. Developers who want real agent work without paying yet: what a free tier actually allows (requests, models, a daily allowance, or nothing until you bring your own key) rather than whether a free badge exists. Below is the full ranking and the tradeoffs, or read [how we score](https://www.versusref.com/methodology/).

## What matters for free plans

Weight ×5 = decisive, ×1 = relevant.

| Fact | Weight | Amp | Command Code | Freebuff | Letta Code | Mistral Vibe |
| --- | --- | --- | --- | --- | --- | --- |
| What the free plan allows | ×5 | Hobby (Free): all product features (Oct 2) | n/a | 100 Freebucks every day (Oct 2) | $0: 'Limited agents' (3 stateful agents) (Oct 2) | Limited messages and web searches; $10/mo in API credits (Oct 2) |
| Bring your own API key | ×4 | true - bypasses plan limits (Oct 2) | Yes (Oct 2) | No (Oct 2) | Yes (Oct 2) | Yes (Oct 2) |
| Cheapest paid plan (monthly) | ×3 | $20 (Oct 2) | $1 (Oct 2) | $8 (Oct 2) | $20 (Oct 2) | $14.99 (Oct 2) |
| Runs local models | ×2 | n/a | ✓  Yes (Oct 2) | n/a | ✓  Yes (Oct 2) | ✓  Yes (Oct 2) |

- ×5 **What the free plan allows:** The question is never "is there a free plan" but what it allows: a resetting daily allowance on a strong model reads very differently from a handful of requests a month.
- ×4 **Bring your own API key:** A free tool that accepts your own API key turns "free" into "you pay the model provider directly at list price", often the cheapest honest route.
- ×3 **Cheapest paid plan (monthly):** Free tiers run out; the price of the next rung up is what a free-tier evaluation is really shopping for.
- ×2 **Runs local models:** Running a local model removes the usage meter entirely, at the cost of your own hardware.

## The ranking, tool by tool

| Rank | Tool | Verdict | Score | Price |
| --- | --- | --- | --- | --- |
| 1 | [Amp](https://www.versusref.com/coding-agents/tools/amp/) | What the free plan allows is the deciding factor, and here the two are far apart. | 2 of 2 points · 1 matchup | See pricing |
| 2 | [Command Code](https://www.versusref.com/coding-agents/tools/command-code/) | Neither has a confirmed free plan: Claude Code is not included on the Free plan, and Command Code does not publish one. | 2 of 2 points · 1 matchup | See pricing |
| 3 | [Freebuff](https://www.versusref.com/coding-agents/tools/freebuff/) (OSS) | What the free plan allows is the deciding factor. | 2 of 2 points · 1 matchup | See pricing |
| 4 | [Letta Code](https://www.versusref.com/coding-agents/tools/letta-code/) (OSS) | What the free plan allows decides this. | 2 of 2 points · 1 matchup | See pricing |
| 5 | [Mistral Vibe](https://www.versusref.com/coding-agents/tools/mistral-vibe/) (OSS) | What the free plan allows decides this, and the gap is wide. | 2 of 2 points · 1 matchup | See pricing |
| 6 | [OpenHands](https://www.versusref.com/coding-agents/tools/openhands/) (OSS) | What the free plan actually allows decides this. | 2 of 2 points · 1 matchup | See pricing |
| 7 | [Qwen Code](https://www.versusref.com/coding-agents/tools/qwen-code/) (OSS) | Neither tool has a free plan: Claude Code is not included on the Free plan, and Qwen Code's free tier was discontinued on 2026-04-15. | 2 of 2 points · 1 matchup | See pricing |
| 8 | [Zed](https://www.versusref.com/coding-agents/tools/zed/) (OSS) | What the free plan allows decides this. | 2 of 2 points · 1 matchup | See pricing |
| 9 | [Google Antigravity](https://www.versusref.com/coding-agents/tools/google-antigravity/) | What the free tier actually allows is the deciding factor here. | 5 of 6 points · 3 matchups | See pricing |
| 10 | [OpenCode](https://www.versusref.com/coding-agents/tools/opencode/) (OSS) | What the free plan allows is the deciding factor. | 5 of 6 points · 3 matchups | See pricing |
| 11 | [GitHub Copilot](https://www.versusref.com/coding-agents/tools/github-copilot/) | What the free plan actually allows decides this one. | 13 of 16 points · 8 matchups | See pricing |
| 12 | [OpenAI Codex](https://www.versusref.com/coding-agents/tools/openai-codex/) | What a free plan actually allows is the deciding factor here. | 5 of 8 points · 4 matchups | See pricing |
| 13 | [Aider](https://www.versusref.com/coding-agents/tools/aider/) (OSS) | What you get without paying decides this. | 3.5 of 6 points · 3 matchups | See pricing |
| 14 | [Cline](https://www.versusref.com/coding-agents/tools/cline/) (OSS) | What the free plan allows decides this. | 2 of 4 points · 2 matchups | See pricing |
| 15 | [DeepSeek Harness (dsh)](https://www.versusref.com/coding-agents/tools/deepseek-harness/) (OSS) | Neither tool publishes a free plan allowance, so this comes down to how you start without paying. | 1 of 2 points · 1 matchup | See pricing |
| 16 | [Goose](https://www.versusref.com/coding-agents/tools/goose/) (OSS) | Neither tool offers a free plan with agent access: Claude Code is not included on the Free plan, and Goose publishes no plan at all. | 1 of 2 points · 1 matchup | See pricing |
| 17 | [Grok Build](https://www.versusref.com/coding-agents/tools/grok-build/) (OSS) | Neither publishes a usable free plan: Claude Code is not included on the Free plan, and Grok Build does not publish a free tier. | 1 of 2 points · 1 matchup | See pricing |
| 18 | [Kimi Code](https://www.versusref.com/coding-agents/tools/kimi-code/) (OSS) | Neither tool offers real free agent work. | 1 of 2 points · 1 matchup | See pricing |
| 19 | [Pi](https://www.versusref.com/coding-agents/tools/pi/) (OSS) | Claude Code is not included on the Free plan, so real agent work starts at $20/mo or with your own API key. | 1 of 2 points · 1 matchup | See pricing |
| 20 | [Trae](https://www.versusref.com/coding-agents/tools/trae/) | Both free plans are loosely capped. | 1 of 2 points · 1 matchup | See pricing |
| 21 | [Verdent](https://www.versusref.com/coding-agents/tools/verdent/) | The free plans are similarly modest. | 1 of 2 points · 1 matchup | See pricing |
| 22 | [Warp](https://www.versusref.com/coding-agents/tools/warp/) | Neither tool gives real agent work on a free plan without extra setup. | 1 of 2 points · 1 matchup | See pricing |
| 23 | [Devin](https://www.versusref.com/coding-agents/tools/devin/) | What the free plan actually allows matters most here. | 3 of 8 points · 4 matchups | See pricing |
| 24 | [Cursor](https://www.versusref.com/coding-agents/tools/cursor/) | What the free plan actually allows decides this one. | 6 of 22 points · 11 matchups | See pricing |
| 25 | [Kilo Code](https://www.versusref.com/coding-agents/tools/kilo-code/) (OSS) | Neither tool publishes a request cap or daily allowance for its free plan. | 1 of 4 points · 2 matchups | See pricing |
| 26 | [Kiro](https://www.versusref.com/coding-agents/tools/kiro/) | What the free plan actually allows matters most. | 1 of 4 points · 2 matchups | See pricing |
| 27 | [gptme](https://www.versusref.com/coding-agents/tools/gptme/) (OSS) | MIT local-first terminal agent; also web UI, desktop app, REST server, MCP/ACP; persistent autonomous-agent template. | 0.5 of 2 points · 1 matchup | See pricing |
| 28 | [Augment Code](https://www.versusref.com/coding-agents/tools/augment-code/) | Context-engine coding platform for large codebases; now led by Cosmos cloud agents + Auggie CLI (also ide_extension: VS Code, JetBrains, Vim/Neovim chat). Brief seeded it as an IDE extension; the 2026 pricing page leads with "Try Cosmos". Flat team pricing (up to 50 seats, no per-seat charge) with a pooled $ usage balance. | 0 of 2 points · 1 matchup | See pricing |
| 29 | [Claude Code](https://www.versusref.com/coding-agents/tools/claude-code/) | Terminal-first coding agent included in Claude Pro/Max/Team/Enterprise plans or billed via API; also IDE extension, desktop app and cloud sessions (cloud_agent). | 0 of 38 points · 19 matchups | See pricing |
| 30 | [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 |
| 31 | [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 of 2 points · 1 matchup | See pricing |
| 32 | [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 |
| 33 | [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 of 2 points · 1 matchup | See pricing |
| 34 | [Gemini CLI](https://www.versusref.com/coding-agents/tools/gemini-cli/) (OSS) | Open-source terminal agent (also oss_self_hosted), enterprise/API-key only after consumer users moved to Antigravity CLI. | 0 of 2 points · 1 matchup | See pricing |
| 35 | [GitLab Duo Agent Platform](https://www.versusref.com/coding-agents/tools/gitlab-duo-agent-platform/) | DevSecOps-native agents and flows for GitLab Premium/Ultimate; also IDE extensions (VS Code, JetBrains) and a Duo CLI; self-managed and air-gapped self-hosted-model options. | 0 of 2 points · 1 matchup | See pricing |
| 36 | [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 |
| 37 | [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 |
| 38 | [Tabnine](https://www.versusref.com/coding-agents/tools/tabnine/) | Private, governed enterprise coding agent with self-hosted and air-gapped deployment. Now a Tricentis product (acquired 2026-07-30). Secondary segment: terminal_agent (Tabnine Plugin for OpenCode). | 0 of 2 points · 1 matchup | See pricing |

### 1. Amp

What the free plan allows is the deciding factor, and here the two are far apart. [Full Amp vs Claude Code verdict](https://www.versusref.com/coding-agents/amp-vs-claude-code/)

### 2. Command Code

Neither has a confirmed free plan: Claude Code is not included on the Free plan, and Command Code does not publish one. [Full Command Code vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-command-code/)

### 3. Freebuff

What the free plan allows is the deciding factor. [Full Freebuff vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-freebuff/)

### 4. Letta Code

What the free plan allows decides this. [Full Letta Code vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-letta-code/)

### 5. Mistral Vibe

What the free plan allows decides this, and the gap is wide. [Full Mistral Vibe vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-mistral-vibe/)

### 6. OpenHands

What the free plan actually allows decides this. [Full OpenHands vs Devin verdict](https://www.versusref.com/coding-agents/devin-vs-openhands/)

### 7. Qwen Code

Neither tool has a free plan: Claude Code is not included on the Free plan, and Qwen Code's free tier was discontinued on 2026-04-15. [Full Qwen Code vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-qwen-code/)

### 8. Zed

What the free plan allows decides this. [Full Zed vs Cursor verdict](https://www.versusref.com/coding-agents/cursor-vs-zed/)

### 9. Google Antigravity

What the free tier actually allows is the deciding factor here. [Full Google Antigravity vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-google-antigravity/)

What the free plan actually allows matters most here. [Full Google Antigravity vs Cursor verdict](https://www.versusref.com/coding-agents/cursor-vs-google-antigravity/)

This one is decided by what the free plan actually allows. [Full Google Antigravity vs Gemini CLI verdict](https://www.versusref.com/coding-agents/gemini-cli-vs-google-antigravity/)

### 10. OpenCode

What the free plan allows is the deciding factor. [Full OpenCode vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-opencode/)

Both are open to start without paying: Kilo Code is free and open source in VS Code, and OpenCode offers its agent at no charge. [Full OpenCode vs Kilo Code verdict](https://www.versusref.com/coding-agents/kilo-code-vs-opencode/)

What the free plan allows matters most: OpenCode's free plan includes the agent itself, while Crush does not publish a free plan for the agent. [Full OpenCode vs Crush verdict](https://www.versusref.com/coding-agents/crush-vs-opencode/)

### 11. GitHub Copilot

What the free plan actually allows decides this one. [Full GitHub Copilot vs Cursor verdict](https://www.versusref.com/coding-agents/cursor-vs-github-copilot/)

For free use, GitHub Copilot is the only real option. [Full GitHub Copilot vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-github-copilot/)

What the free tier actually allows decides this. [Full GitHub Copilot vs Devin Desktop (formerly Windsurf) verdict](https://www.versusref.com/coding-agents/devin-desktop-vs-github-copilot/)

What the free plan allows decides this, and GitHub Copilot's is far roomier at 2,000 code completions a month. [Full GitHub Copilot vs JetBrains Junie verdict](https://www.versusref.com/coding-agents/github-copilot-vs-junie/)

What a free plan actually allows decides this one. [Full GitHub Copilot vs Tabnine verdict](https://www.versusref.com/coding-agents/github-copilot-vs-tabnine/)

What the free plan allows decides this. [Full GitHub Copilot vs GitLab Duo Agent Platform verdict](https://www.versusref.com/coding-agents/github-copilot-vs-gitlab-duo-agent-platform/)

What a free plan actually allows is the deciding factor. [Full GitHub Copilot vs Tabby verdict](https://www.versusref.com/coding-agents/github-copilot-vs-tabby/)

### 12. OpenAI Codex

What a free plan actually allows is the deciding factor here. [Full OpenAI Codex vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-openai-codex/)

Both free plans allow real work: Cursor Hobby gives limited Agent requests and access to Composer, while OpenAI Codex Free at $0 offers GPT-6 Luna at Standard speed in the desktop app. [Full OpenAI Codex vs Cursor verdict](https://www.versusref.com/coding-agents/cursor-vs-openai-codex/)

For real agent work without paying, OpenAI Codex Free at $0 offers GPT-6 Luna at Standard speed in the desktop app, while GitHub Copilot Free is framed around 2,000 code completions a month. [Full OpenAI Codex vs GitHub Copilot verdict](https://www.versusref.com/coding-agents/github-copilot-vs-openai-codex/)

### 13. Aider

What you get without paying decides this. [Full Aider vs Claude Code verdict](https://www.versusref.com/coding-agents/aider-vs-claude-code/)

Aider's whole tool is free and open source, with no plan limits; you bring your own API key, which it requires. [Full Aider vs OpenAI Codex verdict](https://www.versusref.com/coding-agents/aider-vs-openai-codex/)

### 14. Cline

What the free plan allows decides this. [Full Cline vs Cursor verdict](https://www.versusref.com/coding-agents/cline-vs-cursor/)

### 15. DeepSeek Harness (dsh)

Neither tool publishes a free plan allowance, so this comes down to how you start without paying. [Full DeepSeek Harness (dsh) vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-deepseek-harness/)

### 16. Goose

Neither tool offers a free plan with agent access: Claude Code is not included on the Free plan, and Goose publishes no plan at all. [Full Goose vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-goose/)

### 17. Grok Build

Neither publishes a usable free plan: Claude Code is not included on the Free plan, and Grok Build does not publish a free tier. [Full Grok Build vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-grok-build/)

### 18. Kimi Code

Neither tool offers real free agent work. [Full Kimi Code vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-kimi-code/)

### 19. Pi

Claude Code is not included on the Free plan, so real agent work starts at $20/mo or with your own API key. [Full Pi vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-pi/)

### 20. Trae

Both free plans are loosely capped. [Full Trae vs Cursor verdict](https://www.versusref.com/coding-agents/cursor-vs-trae/)

### 21. Verdent

The free plans are similarly modest. [Full Verdent vs Cursor verdict](https://www.versusref.com/coding-agents/cursor-vs-verdent/)

### 22. Warp

Neither tool gives real agent work on a free plan without extra setup. [Full Warp vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-warp/)

### 23. Devin

What the free plan actually allows matters most here. [Full Devin vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-devin/)

What a free plan actually allows is the deciding factor, and only Devin publishes one: a free plan with limited Devin usage. [Full Devin vs Factory verdict](https://www.versusref.com/coding-agents/devin-vs-factory/)

What a free tier allows matters most here, and only Devin publishes one, though it promises just limited Devin usage. [Full Devin vs Cosine verdict](https://www.versusref.com/coding-agents/cosine-vs-devin/)

### 24. Cursor

What the free plan actually allows decides this one. [Full Cursor vs Claude Code verdict](https://www.versusref.com/coding-agents/claude-code-vs-cursor/)

Neither free plan is generous on paper. [Full Cursor vs Devin Desktop (formerly Windsurf) verdict](https://www.versusref.com/coding-agents/cursor-vs-devin-desktop/)

This one is close. [Full Cursor vs Kiro verdict](https://www.versusref.com/coding-agents/cursor-vs-kiro/)

What a free tier actually allows decides this, and only Cursor publishes one: its Hobby plan includes limited Agent requests and access to Composer. [Full Cursor vs Augment Code verdict](https://www.versusref.com/coding-agents/augment-code-vs-cursor/)

### 25. Kilo Code

Neither tool publishes a request cap or daily allowance for its free plan. [Full Kilo Code vs Cline verdict](https://www.versusref.com/coding-agents/cline-vs-kilo-code/)

### 26. Kiro

What the free plan actually allows matters most. [Full Kiro vs Devin Desktop (formerly Windsurf) verdict](https://www.versusref.com/coding-agents/devin-desktop-vs-kiro/)

### 27. gptme

MIT local-first terminal agent; also web UI, desktop app, REST server, MCP/ACP; persistent autonomous-agent template. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 28. Augment Code

Context-engine coding platform for large codebases; now led by Cosmos cloud agents + Auggie CLI (also ide_extension: VS Code, JetBrains, Vim/Neovim chat). Brief seeded it as an IDE extension; the 2026 pricing page leads with "Try Cosmos". Flat team pricing (up to 50 seats, no per-seat charge) with a pooled $ usage balance. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 29. Claude Code

Terminal-first coding agent included in Claude Pro/Max/Team/Enterprise plans or billed via API; also IDE extension, desktop app and cloud sessions (cloud_agent). No won verdicts for this use case yet; it ranks on ties and near-misses.

### 30. 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.

### 31. 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.

### 32. 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.

### 33. 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.

### 34. Gemini CLI

Open-source terminal agent (also oss_self_hosted), enterprise/API-key only after consumer users moved to Antigravity CLI. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 35. GitLab Duo Agent Platform

DevSecOps-native agents and flows for GitLab Premium/Ultimate; also IDE extensions (VS Code, JetBrains) and a Duo CLI; self-managed and air-gapped self-hosted-model options. No won verdicts for this use case yet; it ranks on ties and near-misses.

### 36. 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.

### 37. 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.

### 38. Tabnine

Private, governed enterprise coding agent with self-hosted and air-gapped deployment. Now a Tricentis product (acquired 2026-07-30). Secondary segment: terminal_agent (Tabnine Plugin for OpenCode). No won verdicts for this use case yet; it ranks on ties and near-misses.

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