# Best AI Coding Agents for vibe coders

> Compare tested terminal and cloud coding agents, with scores and test editions.

- HTML: https://vibetoolrank.com/best/ai-coding-agents/
- Best free: https://vibetoolrank.com/best-free/ai-coding-agents/
- Markdown: https://vibetoolrank.com/best/ai-coding-agents.md
- Tracked: 25 · Tested: 15 · Updated: 2026-11-11
- Scores are agent tests (outcome 40%, speed/cost/DX/reliability 15% each). Untested tools have no score.

## Ranked tools

1. [Aider](https://vibetoolrank.com/tools/aider/) — **9.3/10** (tested 2026-10-16, 3 runs, CLI, free model). Free: Yes: free tool, BYO API key or local models. Price: Free open source (Apache 2.0); pay your LLM provider.
   - 3/3 runs fixed our seeded cart bug (4/4 tests pass) in 9-13s with a free OpenRouter model, without touching the test file. Install needed uv because pip was blocked on the system Python.
2. [Claude Code](https://vibetoolrank.com/tools/claude-code/) — **9.3/10** (tested 2026-11-01, 3 runs, Anthropic Sonnet 5.5 API). Free: No (not included in Claude Free). Price: Included in Claude Pro $20/mo ($17/mo annual, $200 upfront); Max from $100/mo (5x or 20x); or API pay-as-you-go.
   - Anthropic Sonnet 5.5 edition (headline): Claude Code CLI fixed our seeded cart bug in 3 of 3 runs (5.7–7.1s, 5 turns each). Test file untouched. Real API spend ~$0.035 for smoke + 3 runs at Sonnet 5.5 list prices ($2/$10
3. [Cline](https://vibetoolrank.com/tools/cline/) — **9.2/10** (tested 2026-10-16, 3 runs, CLI, free model). Free: Yes: free for individuals, pay inference only. Price: Extension free; Teams $20/user/mo (first 10 seats free); Enterprise custom.
   - 3/3 headless CLI runs fixed our seeded cart bug (4/4 tests pass) in 24-35s with a free OpenRouter model, without editing the test file.
4. [GitHub Copilot CLI](https://vibetoolrank.com/tools/copilot-cli/) — **9.2/10** (tested 2026-10-17, 3 runs, Copilot Free CLI). Free: Yes: Copilot Free includes the CLI with a monthly AI Credits allowance, Auto model only. Price: Copilot Free $0 (monthly AI Credits allowance); Pro $10/mo (1,500 credits); Pro+ $39/mo; Max $100/mo.
   - 3/3 runs fixed our seeded cart bug (4/4 tests pass) in 22-26s on Copilot Free, using 0.16-0.27 AI Credits each. It used our existing gh login with no browser step and never touched the test file.
5. [OpenCode](https://vibetoolrank.com/tools/opencode/) — **9.2/10** (tested 2026-10-16, 3 runs, CLI, free model). Free: Yes: open-source agent free with own keys; some free Zen models. Price: Go $10/mo; Go Plus $40/mo; Zen pay-as-you-go ($20 prepaid).
   - 3/3 runs: fixed a seeded cart-discount bug (2 failing tests) in 18-22s with a free Zen model and no account or API key, without touching the tests. Only task T3 was run. In scripts, opencode run hangs silently if stdin i
6. [Memdoor](https://vibetoolrank.com/tools/memdoor/) — **9.1/10** (tested 2026-11-04, 3 runs, CLI, BYOK). Free: Yes: the CLI, decision model and workflows are free; bring your own model key (for example OpenRouter) or run a local model with memdoor connect local. No account needed. Price: Free and open source (Apache 2.0): the agent, the decision model and workflows. Pro is $10/month for phone remote control and workflow state kept on memdoor.ai. Every model call runs on your own key.
   - Memdoor fixed our seeded cart discount bug in 3 of 3 headless runs (35–47s each) with a free OpenRouter model, never touched the test file, and printed its own test receipt. Cost $0. Overall 9.1 (outcome 10, speed 8, cos
7. [OpenHands](https://vibetoolrank.com/tools/openhands/) — **9.1/10** (tested 2026-11-04, 3 runs, headless CLI, BYOK). Free: Yes: self-host Agent Canvas / CLI / SDK free with your own model key; Cloud free BYOK tier for individuals with usage limits. No card required for local BYOK. Price: Agent Canvas free to self-host (MIT, BYOK, single shared identity). Teams $500/mo up to 10 users (+$50/seat), self-hosted with RBAC. Enterprise custom. OpenHands Cloud: free BYOK tier with daily/parallel conversation limits; hosted models at provider cost with no markup.
   - OpenHands CLI headless fixed our seeded cart discount bug in 3 of 3 runs (42–51s each) with a free Gemini key, never touched the test file. Cost $0. Overall 9.1 (outcome 10, speed 8, cost 10, DX 6, reliability 10). DX lo
8. [Zerg Client](https://vibetoolrank.com/tools/zerg-client/) — **9.1/10** (tested 2026-11-11, 3 runs, Headless CLI, BYOK). Free: Yes: free evaluation of the CLI/desktop under the source-available license; bring your own model keys or use Zerg Router billing. Commercial use requires a license (official product page, verified 2026-11-06). Price: Free to evaluate under the Zerg Source Available License; commercial use needs a paid license. Model usage is billed separately (Zerg Router or your own provider keys). No Zerg account required if you use local API keys.
   - Zerg Client fixed our seeded cart discount bug in 3 of 3 headless runs (17–33s each) with a free OpenRouter model, ran the tests itself, and never touched the test file. Cost $0. Overall 9.1 (outcome 10, speed 9, cost 9,
9. [Amp](https://vibetoolrank.com/tools/amp/) — **9/10** (tested 2026-11-06, run count not recorded, cloud free plan). Free: Yes (Hobby): all features, local runners, BYOK; ad-supported Amp Free discontinued. Price: Individual $20/mo (45,000 orb minutes).
   - 2026-11-06 cross-check: Amp fixed our seeded cart discount bug in 3 of 3 headless Hobby Free runs (62–136s) with a free OpenRouter model and never touched the test file. Cost $0 on OpenRouter (49 free requests). Overall 
10. [Reason](https://vibetoolrank.com/tools/reason/) — **8.6/10** (tested 2026-10-18, 3 runs, cloud free plan). Free: Partly: the Free plan includes no agent runs (our API check showed the quota exhausted at zero usage); you can bring your own model API key. Reason Network is free.. Price: Free plan (no included agent quota; bring your own model key or buy credits); Pro $20/mo with a 7-day trial; Max $200/mo (seen in the app, 2026-10-17).
   - 3/3 runs fixed our seeded cart bug (4/4 tests pass) in 20-36s of agent time with a free OpenRouter model, $0. On the Free plan the agent's cloud computer doesn't start, so it can't run tests or edit a repo itself; it ret
11. [Alysis Code](https://vibetoolrank.com/tools/alysis-code/) — **8.4/10** (tested 2026-11-11, 3 runs, CLI, BYOK). Free: Yes: open-source CLI/engine free; 50 free Alysis credits/30 days with no card; BYOK and local models supported (official site, verified 2026-11-07). Price: Engine/CLI free under Apache-2.0. Model usage via (a) 50 free Alysis credits every 30 days with no card, (b) your own API key / AI subscription paid to the provider, or (c) local models (Ollama/LM Studio) with no Alysis credits. Paid Alysis plans add more credits..
   - Alysis Code made the correct fix to our seeded cart discount bug in 3 of 3 one-shot runs (21–78s) with a free Gemini key and never touched the test file, but every run exited with an error: in one-shot mode it refused to
12. [Harness (Autonomous)](https://vibetoolrank.com/tools/harness/) — **8.4/10** (tested 2026-10-17, 3 runs, CLI, free model). Free: Yes: the Harness app is a free download and open source (MIT). Price: App free (open source, MIT); optional Harness Device $149 and Harness Pro $299 desk hardware.
   - Harness started OpenCode 3 times on our seeded cart bug and each run fixed it (4/4 tests pass) in 19-38s, at $0 with a free model. Before that, the first attempt picked a paid Claude model because Harness passed our shel
13. [Jules](https://vibetoolrank.com/tools/jules/) — **8/10** (tested 2026-10-16, 1 (single run), cloud free tier). Free: Yes: 15 tasks/24h, 3 concurrent. Price: Jules in Pro via Google AI Pro (100 tasks/day); Jules in Ultra via Google AI Ultra (300/day). Google AI plan prices not on this page (search excerpt: $19.99 / $99.99).
   - Jules is an async coding agent: it delivered our T1 todo app as a GitHub pull request after about 14 minutes, about 5 of which it appeared stuck. It wrote and ran its own Playwright test. We cloned the PR, built it and v
14. [OpenAI Codex](https://vibetoolrank.com/tools/codex/) — **7.4/10** (tested 2026-10-16, 3 runs, CLI, free model). Free: Yes: Codex CLI, IDE extension and app on ChatGPT Free and Go with plan usage limits (no Codex Cloud). Price: Included in every ChatGPT plan (Free, Go, Plus, Pro, Business, Enterprise, Edu); usage limits vary by plan. Codex Cloud needs Plus, Pro, Business, Enterprise or Edu. Plus/Pro buyers can add credits. Plan prices on chatgpt.com/pricing.
   - Using a custom OpenRouter provider and a small free model, Codex CLI fixed our seeded cart bug in 2 of 3 runs (19-76s). In the failed run the model issued an apply_patch call that Codex rejected. Token use was high (33K-
15. [Gemini CLI](https://vibetoolrank.com/tools/gemini-cli/) — **6.1/10** (tested 2026-10-17, 3 runs, CLI, free API tier). Free: No longer via Google sign-in (consumer users moved to Antigravity CLI June 18, 2026); free API-key quota unclear. Price: Requires paid Gemini API key, Vertex AI, or Gemini Code Assist Standard/Enterprise.
   - Google-account login for individuals no longer works (the CLI says to migrate to Antigravity), so we used a free-tier API key. Run 1 (16 Oct 2026) wrote a complete todo app in about 5 minutes, then hit the free tier's 20
16. [Agent Manager](https://vibetoolrank.com/tools/agent-manager/) — not yet tested. Free: Yes: Apache-2.0 CLI/TUI free via Homebrew, binaries, or go install; no Agent Manager account or card (official site + GitHub, verified 2026-11-08). Price: Free and open source under Apache-2.0. Uses the coding-agent subscriptions and API keys you already have; Agent Manager itself has no paid plan..
17. [Conducted](https://vibetoolrank.com/tools/conducted/) — not yet tested. Free: Yes: MIT desktop app free to download; no Conducted account or card claimed (GitHub README + Releases, verified 2026-11-08). Price: Free and open source under MIT. macOS Apple silicon .dmg from GitHub Releases; uses the agent subscriptions/keys you already pay for. No Conducted cloud plan..
18. [Crewplane](https://vibetoolrank.com/tools/crewplane/) — not yet tested. Free: Yes: Apache-2.0 open source (GitHub API licence field, verified 2026-11-11). Price: Free and open source (Apache-2.0) per the GitHub repository; install with uv tool install crewplane. The README says the first run can be tried without API keys. Underlying agent CLIs have their own pricing..
19. [Devin](https://vibetoolrank.com/tools/devin/) — not yet tested. Free: Yes: light agent quota. Price: Pro $20/mo; Max $200/mo; Teams $80/mo + $40/seat; Enterprise custom.
20. [Mirror (Reflection)](https://vibetoolrank.com/tools/mirror/) — not yet tested. Free: Yes: the CLI is free and open source; Reflection's API has a free daily allowance during the Beta, but needs card verification before keys work. Price: Free and open source (Apache-2.0). Its default Beam model runs on Reflection's API, which is free during the public Beta with a daily token allowance (per-token prices not published); API keys require credit-card verification in Billing. Or bring your own OpenRouter, OpenAI or Anthropic key, a ChatGPT plan, or a local model.
21. [Parallax (Conifer)](https://vibetoolrank.com/tools/parallax/) — not yet tested. Free: Yes: $50 of Conifer credit and 5 free reviews when you sign up with GitHub. Price: Free to start; agents run on your own Claude/Codex subscriptions or on Conifer credit.
22. [psi](https://vibetoolrank.com/tools/psi/) — not yet tested. Free: Yes: MIT open-source binary, no psi account or card claimed (psicode.ai + GitHub, verified 2026-11-09). Price: Free and open source (MIT). Bring your own model provider key or a local Ollama model; no psi paid plan listed..
23. [Roomote (formerly Roo Code)](https://vibetoolrank.com/tools/roo-code/) — not yet tested. Free: Yes: self-hosted free up to 10 users; you pay infrastructure and model providers. No credit card for the Roomote license itself.. Price: Self-hosted: Free for up to 10 users (you pay host + inference). 11–50 users $249/mo; 51–100 $499/mo; 100+ talk to them. No per-seat charge on the free tier..
24. [Ski](https://vibetoolrank.com/tools/ski/) — not yet tested. Free: Yes: unlimited free text chats; free monthly voice credits on Free (no card claimed on the marketing site). Pro/Enterprise for higher concurrent voice (official site + Show HN, verified 2026-11-06). Price: Free forever for unlimited text chats with every agent (no subscription). Voice: free tier with monthly voice credits (Show HN: 300 credits/month); Pro unlocks more concurrent voice sessions; Enterprise for teams. macOS only today; Windows/Linux waitlist.
25. [Wonder](https://vibetoolrank.com/tools/wonder/) — not yet tested. Free: Yes: Free plan $0 for one editor, no card claimed for Free; uses your Claude Code/Codex subscriptions (official changelog + Product Hunt, verified 2026-11-07). Price: Free $0 for one editor: use your own agent subscriptions, multiple parallel agents, 3,000 AI-generated layers/week, live app on canvas, unlimited private files. Pro $20/editor/month ($16/mo yearly): unlimited layers, AI image/vector, publish Preview link, full team collab, priority support. Agent subscriptions billed separately..

## See also

- Methodology: https://vibetoolrank.com/methodology/
- All rankings: https://vibetoolrank.com/best/
- Releases: https://vibetoolrank.com/releases/