Best free AI Coding Agents for vibe coders
22 of 25 tracked tools in AI Coding Agents have a free plan; 0 have no monthly fee and charge per transaction. 12 free or no-monthly-fee tools have test scores.
This is the free-plan guide to AI coding agents, including bring-your-own-key CLIs and hosted free quotas we have on record. Tools are ordered by recorded overall score among those with a free plan or no monthly fee; untested free tools are listed without a score. Free does not mean unlimited — official limits are dated on each tool page. For the scored ranking of every agent we track, including paid-only tools, see Best AI Coding Agents.
“Free” does not mean unlimited. Limits and test editions are listed from tool records. Last updated: 2026-11-11 · Methodology
Free plans
| # | Tool | Free tier | Score |
|---|---|---|---|
| 1 | Aider | Yes: free tool, BYO API key or local models | 9.3 |
| 2 | Cline | Yes: free for individuals, pay inference only | 9.2 |
| 3 | GitHub Copilot CLI | Yes: Copilot Free includes the CLI with a monthly AI Credits allowance, Auto model only | 9.2 |
| 4 | OpenCode | Yes: open-source agent free with own keys; some free Zen models | 9.2 |
| 5 | Memdoor | 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 | 9.1 |
| 6 | OpenHands | 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 | 9.1 |
| 7 | Zerg Client | 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) | 9.1 |
| 8 | Amp | Yes (Hobby): all features, local runners, BYOK; ad-supported Amp Free discontinued | 9 |
| 9 | Alysis Code | 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) | 8.4 |
| 10 | Harness (Autonomous) | Yes: the Harness app is a free download and open source (MIT) | 8.4 |
| 11 | Jules | Yes: 15 tasks/24h, 3 concurrent | 8 |
| 12 | OpenAI Codex | Yes: Codex CLI, IDE extension and app on ChatGPT Free and Go with plan usage limits (no Codex Cloud) | 7.4 |
| 13 | Agent Manager | 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) | Not yet tested |
| 14 | Conducted | Yes: MIT desktop app free to download; no Conducted account or card claimed (GitHub README + Releases, verified 2026-11-08) | Not yet tested |
| 15 | Crewplane | Yes: Apache-2.0 open source (GitHub API licence field, verified 2026-11-11) | Not yet tested |
| 16 | Devin | Yes: light agent quota | Not yet tested |
| 17 | Mirror (Reflection) | 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 | Not yet tested |
| 18 | Parallax (Conifer) | Yes: $50 of Conifer credit and 5 free reviews when you sign up with GitHub | Not yet tested |
| 19 | psi | Yes: MIT open-source binary, no psi account or card claimed (psicode.ai + GitHub, verified 2026-11-09) | Not yet tested |
| 20 | Roomote (formerly Roo Code) | Yes: self-hosted free up to 10 users; you pay infrastructure and model providers. No credit card for the Roomote license itself. | Not yet tested |
| 21 | Ski | 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) | Not yet tested |
| 22 | Wonder | 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) | Not yet tested |
1. Aider — 9.3/10
Yes: free tool, BYO API key or local models
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.
- Fixed the seeded bug correctly in 3 of 3 runs, in 9-13 seconds
- Works with free OpenRouter models, so our test cost $0
- Built-in --auto-test loop runs your tests after each edit
- pip install was refused on Debian's system Python; we needed uv
- Unattended runs need several flags (--yes-always, --message, --test-cmd)
- Free model slugs change; one we tried returned 'unavailable for free'
2. Cline — 9.2/10
Yes: free for individuals, pay inference only
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.
- Headless CLI with a -y mode ran start to finish with no prompts
- Fixed the seeded bug in 3 of 3 runs and never touched the test file
- Works with free OpenRouter models, so our test cost $0
- Slower than Aider on the same model (24-35s vs 9-13s)
- Warns on Node versions below 22.15
- The -k flag saves your API key into the config directory
3. GitHub Copilot CLI — 9.2/10
Yes: Copilot Free includes the CLI with a monthly AI Credits allowance, Auto model only
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.
- Fixed the seeded bug correctly in 3 of 3 runs, in 22-26 seconds
- Runs headlessly with an existing GitHub CLI login (GH_TOKEN), no browser step
- Ran the test suite itself before finishing
- Copilot Free is limited to the Auto model
- The Free AI Credits allowance isn't stated in GitHub's docs, so heavy use is hard to plan
- Unattended runs need --allow-all-tools, which lets it run any command in the folder
4. OpenCode — 9.2/10
Yes: open-source agent free with own keys; some free Zen models
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 is left open.
- Solved our bug-fix task 3/3 in about 20s
- Free Zen models work with no account or API key
- Minimal, correct diffs that left the tests untouched
- opencode run hung silently in a script until stdin was redirected from /dev/null
- Free model names and availability change over time
- We only ran the bug-fix task (T3), not full app builds
5. Memdoor — 9.1/10
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
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, cost 10, DX 6, reliability 10). DX lost points because the default free-model auto-pick hit an OpenRouter 403 and pinning a model needed environment variables.
- Fixed the seeded bug in 3/3 runs with a free model
- Single binary, no account, clean --json output for scripts and CI
- Ends each run with a receipt showing the tests it ran before and after
- Did not modify the test file in any run
- Default free-model auto-pick failed with an OpenRouter 403 in our test
- Pinning a specific model needed AI_GATEWAY_* environment variables
- Slower than paid-model agents (35–47s per run on a free model)
6. OpenHands — 9.1/10
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
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 lost points because Gemini free context caching caused 429s until we seeded agent_settings and forced caching_prompt=False — there is no simple CLI/env switch.
- Fixed the seeded bug in 3/3 headless runs with a free model
- Did not modify the test file in any run
- Self-host / BYOK path works with no OpenHands Cloud account
- Large open-source project (~92.6k GitHub stars on 2026-11-04)
- Default Gemini path uses context caching that the free Gemini tier rejects (429); turning it off needed a settings seed + JSON patch
- CLI TUI is in maintenance mode; docs steer new local users to Agent Canvas
- We only scored the headless CLI edition, not Agent Canvas or Cloud
7. Zerg Client — 9.1/10
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)
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, DX 6, reliability 10). DX lost points because the Linux npm install needed --ignore-scripts, the built-in Gemini provider failed with a free key, and headless output is noisy. Cost is 9 because the licence is free for evaluation only; commercial use needs a paid licence. We tested the headless CLI only, not the macOS desktop app or Zerg Router models.
- Fixed the seeded bug in 3/3 headless runs with a free model
- Ran node --test itself and exited cleanly (exit 0) every run
- BYOK with no Zerg account: three environment variables and --auth-mode direct
- Did not modify the test file in any run
- Linux npm install failed until we used --ignore-scripts (node-pty build needs make)
- Native Gemini provider returned 400 schema errors with a free key in our test
- Headless output repeats long checkpoint blocks; interactive TUI and desktop app are Apple Silicon only
- Free for evaluation only; commercial use needs a signed licence
8. Amp — 9/10
Yes (Hobby): all features, local runners, BYOK; ad-supported Amp Free discontinued
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 9.0 (outcome 10, speed 8, cost 10, DX 5, reliability 10). Prior 2026-11-05 batch scored 7.4 (2/3). DX still loses points for device login, API token, full model-routing setup, and the need for a sandbox.
- Fixed the seeded bug in 3/3 cross-check runs with a free OpenRouter model
- Hobby Free + BYOK completed the task at $0 OpenRouter spend
- Did not modify the test file in any scored run
- Free path needs an Amp account, access token, and a full model-ID to :free mapping
- Without a sandbox the local executor can edit files outside the project
- Web and media tools bill Amp credits (small dip observed when the agent called read_web_page)
Other tracked tools
- Claude Code — No (not included in Claude Free)
- Gemini CLI — No longer via Google sign-in (consumer users moved to Antigravity CLI June 18, 2026); free API-key quota unclear
- Reason — 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.
FAQ
Is this the same as Best free Coding Agents?
It covers the same free-plan tools in that category, but this page is written for the “free AI coding agents” question, including bring-your-own-key options on record.
Which free AI Coding Agents tool scored highest?
Aider scored 9.3/10 overall.
Does free mean unlimited?
No. A free plan may have usage limits; check each tool’s published free-tier details.
Full AI Coding Agents ranking · All best-free guides · Free-tier measurements · All tools · Best free Vibe Coding Tools · Best free AI Coding Tools
Scores come from our own tests and are never for sale; sponsored placements are always labelled. Some links are affiliate links (currently Railway). Disclosure