Free Conducted alternatives

Conducted is in Coding Agents (CLI & Cloud). It is not yet tested. We list free or no-monthly-fee options first. Aider is the highest-scoring tested free or no-monthly-fee alternative at 9.3/10. OpenHands is recorded as requiring no card: 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

Our record describes Conducted as suited to: Mac Apple silicon developers who want a Conductor-style workspace to run several local coding agents with worktrees, review, and PRs after Conductor's Meta acquisition..

Free or no-monthly-fee alternatives

Listed first because most people comparing alternatives want a free or no-card starting point. Scores are recorded overall scores from our tests, not one shared benchmark. Official limits can change; re-check the tool page dates.

1. #1 Aider 9.3/10

   Tested: Aider 0.86.2 CLI with OpenRouter free model cohere/north-mini-code:free · 2026-10-16

   Free tier: 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.

   Pros

   • 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

   Cons

   • pip install was refused on Debian's system Python; we needed uv
   • Unattended runs need several flags (--yes-always, --message, --test-cmd)

   Best if: Terminal-first developers who want an open-source pair programmer that works with any model, including free ones.

2. #2 Cline 9.2/10

   Tested: Cline CLI 3.0.72 with OpenRouter free model cohere/north-mini-code:free · 2026-10-16

   Free tier: 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.

   Pros

   • 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

   Cons

   • Slower than Aider on the same model (24-35s vs 9-13s)
   • Warns on Node versions below 22.15

   Best if: Developers who like Cline in VS Code and want the same agent in a terminal or CI, with any model.

3. #3 GitHub Copilot CLI 9.2/10

   Tested: Copilot CLI 1.0.98, Copilot Free, Auto model, existing gh login · 2026-10-17

   Free tier: 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.

   Pros

   • 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

   Cons

   • 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

   Best if: Developers who already use GitHub and want a free terminal agent without setting up an API key.

4. #4 OpenCode 9.2/10

   Tested: OpenCode CLI 1.19.2, free Zen model opencode/big-pickle, no account · 2026-10-16

   Free tier: 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.

   Pros

   • 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

   Cons

   • opencode run hung silently in a script until stdin was redirected from /dev/null
   • Free model names and availability change over time

   Best if: Developers who want an open-source terminal coding agent they can try for free and later point at their own model keys.

5. #5 Memdoor 9.1/10

   Tested: Memdoor CLI v1.788.0 with OpenRouter free model cohere/north-mini-code:free (BYOK, $0) · 2026-11-04

   Free tier: 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.

   Pros

   • 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

   Cons

   • Default free-model auto-pick failed with an OpenRouter 403 in our test
   • Pinning a specific model needed AI_GATEWAY_* environment variables

   Best if: Developers who want a small BYOK terminal agent they can run headless in CI, cron or over SSH, and script into repeatable multi-step workflows.

6. #6 OpenHands 9.1/10

   Tested: OpenHands CLI 1.16.0 headless with Google AI Studio gemini-3.5-flash-lite and caching_prompt=False (BYOK, $0). Not Agent Canvas, not Cloud · 2026-11-04

   Free tier: 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.

   Pros

   • 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

   Cons

   • 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

   Best if: Teams that want an open-source coding agent they can self-host or run headless in CI with their own model keys, without locking into one cloud vendor.

7. #7 Zerg Client 9.1/10

   Tested: ZTC 0.18.0-beta.1 headless CLI with OpenRouter free model cohere/north-mini-code:free (BYOK via openai_compatible, no Zerg account, $0) · 2026-11-11

   Free tier: 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.

   Pros

   • 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

   Cons

   • 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

   Best if: Developers who want a terminal (and optional macOS desktop) coding agent with BYOK or Zerg Router billing, including headless runs on Linux/Windows.

8. #8 Amp 9/10

   Tested: Amp CLI 0.0.1793736138-gdba311 Hobby Free with OpenRouter free model cohere/north-mini-code:free (BYOK, $0) · 2026-11-06

   Free tier: 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.

   Pros

   • 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

   Cons

   • 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

   Best if: Developers who want Sourcegraph's Amp agent with their own keys or subscriptions, and can set up model routing for a free path.

9. #9 Alysis Code 8.4/10

   Tested: Alysis Code CLI 0.16.3 one-shot run with Google AI Studio free key, gemini-3.5-flash-lite, web tools off (BYOK, $0) · 2026-11-11

   Free tier: 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)

   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 run the tests without a person's approval, even in auto mode with --yes, and its completion check then failed with a Gemini 400.

   Pros

   • Made the same correct fix in 3/3 runs with a free Gemini key
   • Open source (Apache-2.0), no account needed for BYOK
   • Built-in provider presets (Gemini, OpenAI, Anthropic, OpenRouter and more) and its own bubblewrap command sandbox

   Cons

   • One-shot runs could not execute node --test: any non-read-only shell command needs a person's approval, even with --mode auto --yes
   • Every run exited 1 after a Gemini 400 in its completion check, so CI would see a failure

   Best if: Developers who want an open-source BYOK/local terminal+desktop coding agent with sandboxing, not locked to one model vendor.

10. #10 Harness (Autonomous) 8.4/10

    Tested: Harness CLI v0.4.17 (Linux) running OpenCode 1.19.3 with the free Big Pickle model · 2026-10-17

    Free tier: Yes: the Harness app is a free download and open source (MIT)

    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.

    Pros

    • Started, waited for, read and closed agents from the CLI: harness new, wait, show, close
    • With a free OpenCode model, 3 of 3 runs fixed the seeded bug in 19-38s
    • Free and open source (MIT); no card needed

    Cons

    • The person must sign in and turn on agents-start-agents before an agent can start harnesses
    • Agent panes inherit the daemon's environment, secrets included; our first run picked a paid Claude model via Cloudflare AI Gateway

    Best if: Developers juggling several coding agents (Claude Code, Codex and others) on more than one machine.

11. #11 Jules 8/10

    Tested: Jules free tier, Gemini 3.6 Flash, async PR on GitHub · 2026-10-16

    Free tier: Yes: 15 tasks/24h, 3 concurrent

    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.

    Pros

    • Every T1 check passed when we built and tested the PR ourselves, including on mobile
    • Wrote and ran its own Playwright test and did a code review step
    • Delivers a clean pull request you can review before merging

    Cons

    • Slow: about 14 minutes, about 5 of which it appeared stuck
    • No live preview; you must clone and run the PR yourself

    Best if: Developers with a GitHub repo who want to hand off well-defined tasks and review a pull request later.

12. #12 OpenAI Codex 7.4/10

    Tested: Codex CLI 0.163.0 with OpenRouter free model cohere/north-mini-code:free (no ChatGPT login; not OpenAI's models) · 2026-10-16

    Free tier: Yes: Codex CLI, IDE extension and app on ChatGPT Free and Go with plan usage limits (no Codex Cloud)

    Using a custom OpenRouter provider and a small free model, Codex CLI fixed our seeded cart bug in 2 of 3 runs (19-76s).

    Pros

    • Runs without a ChatGPT login through any Responses-compatible provider
    • Fixed the bug in 2 of 3 runs on a free model at $0
    • Sandboxed workspace-write mode for unattended runs

    Cons

    • With a free model, 1 of 3 runs failed on an unsupported apply_patch call
    • Used 33K-262K tokens per run, versus about 2K for Aider

    Best if: Developers in the OpenAI ecosystem who want a terminal agent; it works best with OpenAI models via a ChatGPT plan or API key.

13. Agent Manager Not yet tested

    Free tier: 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)

    Local terminal multiplexer (Go TUI on tmux) for AI coding agents.

    Best if: Developers who already run several coding-agent CLIs and want one keyboard-first tmux TUI to spawn, watch, and review them together.

14. Crewplane Not yet tested

    Free tier: Yes: Apache-2.0 open source (GitHub API licence field, verified 2026-11-11)

    Open-source workflow runner for coding-agent CLIs.

    Best if: Developers who want repeatable, reviewable multi-stage workflows across several coding-agent CLIs.

15. Devin Not yet tested

    Free tier: Yes: light agent quota

    Autonomous AI software engineer by Cognition.

16. Mirror (Reflection) Not yet tested

    Free tier: 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

    Reflection's open-source terminal coding agent, released with its open-weight Beam model; it can also run on OpenRouter, OpenAI, Anthropic or local models.

    Best if: Developers who want an open-source terminal coding agent tuned for an open-weight model they can also self-host.

17. Parallax (Conifer) Not yet tested

    Free tier: Yes: $50 of Conifer credit and 5 free reviews when you sign up with GitHub

    Mac app (with a Linux build) that runs Claude Code, Codex, Cursor and other coding agents side by side, with a Captain that keeps them on task and built-in code review.

    Best if: Mac users running several coding agents at once who want one place to manage them and have each agent session reviewed.

18. psi Not yet tested

    Free tier: Yes: MIT open-source binary, no psi account or card claimed (psicode.ai + GitHub, verified 2026-11-09)

    Portable terminal coding agent written in ANSI C and Lua, shipped as a ~6.4 MB binary that runs on Linux, macOS, Windows, FreeBSD/OpenBSD and Haiku.

    Best if: Developers who want a tiny, auditable, scriptable terminal coding agent that runs on unusual systems and any of several model providers.

19. Roomote (formerly Roo Code) Not yet tested

    Free tier: Yes: self-hosted free up to 10 users; you pay infrastructure and model providers. No credit card for the Roomote license itself.

    Source-available self-hosted cloud coding agent from the Roo Code team (Fair Core License).

    Best if: Teams that want a self-hosted cloud coding teammate with BYOK, sandboxes, and PR delivery — not a local IDE extension.

20. Ski Not yet tested

    Free tier: 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)

    Voice-first macOS coding harness that steers the agents you already pay for (Claude Code, Codex, Antigravity, OpenCode and others).

    Best if: Mac developers who already run Claude Code, Codex or similar agents and want a voice-first harness to steer several of them without watching the screen.

21. Wonder Not yet tested

    Free tier: 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)

    Desktop harness (Mac and Windows) to run Claude Code and Codex agents you already subscribe to, in parallel git worktrees, with live app preview and a design canvas.

    Best if: Developers who already pay for Claude Code and/or Codex and want a local Mac/Windows workspace to run them in parallel with live preview and design canvas.

Other tested alternatives

These have a recorded test score but are not listed as a free plan or no-monthly-fee option on our records.

13. #13 Claude Code 9.3/10

    Tested: Claude Code CLI 2.1.314 with Anthropic Claude Sonnet 5.5 (claude-sonnet-5-5) via API key; OpenRouter free edition also tested the same day (also 9.3 — see FAQ) · 2026-11-01

    Free tier: No (not included in Claude Free)

    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).

    Pros

    • Fixed the seeded bug in 3/3 runs with Anthropic Sonnet 5.5 in about 6 seconds
    • Real API cost about $0.01 per T3 run at Sonnet 5.5 list prices
    • Did not modify the test file in any run

    Cons

    • No Claude Free plan access — Anthropic models need Pro, Max, or API credits
    • Cost score 7 reflects pay-as-you-go API, not a free tier

    Best if: Developers who want Anthropic's terminal agent on Sonnet/Opus (Pro, Max, or API). Headline score is Anthropic Sonnet 5.5 via API. A separate OpenRouter free edition (also 9.3) tests the CLI with a small free model only.

14. #14 Reason 8.6/10

    Tested: Reason Agent 1.10 (cloud API), Free plan, scratch sessions with our OpenRouter key on the free model cohere/north-mini-code:free · 2026-10-18

    Free tier: 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.

    3/3 runs fixed our seeded cart bug (4/4 tests pass) in 20-36s of agent time with a free OpenRouter model, $0.

    Pros

    • Fixed the seeded bug correctly in 3 of 3 runs, in 20-36 seconds
    • Lets you bring your own model key and pin a free OpenRouter model, so our test cost $0
    • The API reports outcome, cost and token usage for every session

    Cons

    • On the Free plan the cloud computer won't start, so the agent can't run tests, edit a repo or open a PR
    • The agent kept retrying tools on the missing machine, using 84-126k input tokens for a 7-line fix

    Best if: Developers who want a cloud agent to work GitHub issues and coordinate with Claude Code, Codex and teammates' agents.

15. #15 Gemini CLI 6.1/10

    Tested: Gemini CLI 0.64.0, free-tier Gemini API key, default model gemini-3.8-flash · 2026-10-17

    Free tier: No longer via Google sign-in (consumer users moved to Antigravity CLI June 18, 2026); free API-key quota unclear

    Google-account login for individuals no longer works (the CLI says to migrate to Antigravity), so we used a free-tier API key.

    Pros

    • The one app it finished passed every check in our own headless browser test, including mobile
    • Single command, headless mode with JSON output
    • Free API key tier, no card

    Cons

    • Google-account login for individuals fails with 'client no longer supported ... migrate to Antigravity'
    • Free tier allowed only 20 requests per day on gemini-3.8-flash; one small app used them all

    Best if: Developers with a paid Gemini API key or Vertex AI who want an open-source terminal agent; casual free use is now very limited.

Back to Conducted · Best free Coding Agents (CLI & Cloud) · Best Coding Agents (CLI & Cloud)

FAQ

Scores come from our own tests and are never for sale; sponsored placements are always labelled. Some links are affiliate links (currently Railway). Disclosure