- Terminals launched through the shell tool now stop when fx exits instead of staying alive for the next resume.
- New libfx checkpoints cannot be restored by older versions. Existing checkpoints still load.
- Invalid Base64 image input now throws directly from prompt() instead of failing the turn later.
- Enable Ultrafast with /ultrafast on or --ultrafast on supported OpenAI models through AI Gateway. It uses a higher-priced inference tier.
- Subagents and ACP sessions support Ultrafast. libfx supports it through model.ultrafast.
- /mcp add slack now configures Slack, opens sign-in, and connects your account in one command.
FX by Vercel Labs
Unix like coding agent
Recently added on Oct 10, 2026. The description, category and pricing were filled in from public metadata and have not been checked by an editor yet.
What FX does
Key facts
| Maker | Vercel Labs |
|---|---|
| First released | August 2026 |
| License | Apache-2.0 |
| Main language | Zig |
| Open issues and PRs | 269 |
Pricing
Open source under the Apache-2.0 licence; check the website for any paid hosted plans.
, checked Oct 10, 2026. Prices change often; confirm before you buy.
Quick answers
- Free to start?Yes
- Open source?Yes (Apache-2.0)
- Closest alternativeOpenAI Codex · all alternatives
FX alternatives
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | VS Code installs | Stars | Latest release | Price | ||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 |
OpenAI CodexOpenAI |
84 | 21.2M | down 17.3% | up 25.8% | 15.3M | 128K+148/day | 0.162.02d ago | Free + $8/mo | ||
| 3 |
Claude CodeAnthropic |
80 | 11.7M | down 20.3% | down 29.7% | 27.3M | 150K+170/day | 2.1.2952d ago | $20/mo | ||
| 8 |
PiEarendil Inc. (created by Mario Zechner) |
75 | 4.4M | down 3.3% | up 64.7% | — | 114K+334/day | 1.1.03d ago | Free (OSS) | ||
| 9 |
OpenCodeAnomaly (SST team) |
74 | 3.1M | up 7.0% | up 17.7% | 1.2M | 212K+184/day | 1.18.354d ago | Free + $10/mo | ||
| 37 |
Gemini CLIGoogle |
57 | 378K | down 19.3% | up 13.2% | 1.1M | 107K+22/day | 0.63.04d ago | Varies | ||
| 41 |
Oh My PiStencil Labs (Can Bölük) |
56 | 203K | down 22.0% | up 65.4% | — | 34.7K+104/day | 18.8.62d ago | Free (OSS) | ||
| No agents match that filter. | |||||||||||
Ratings from people who use FX
No ratings yet. Used FX? Rate it and say what it is good and bad at.
FX news
-
74 agents added to AgentGid
Symphony, OpenShell, Codex Security, NemoClaw, Agent Browser, Opensre, Caveman, Brag, Open Code Review, Understand-Anything, Codegraph, BrowserSkill and 62 more
-
FX 0.0.13 released
Terminals launched through the shell tool now stop when fx exits instead of staying alive for the next resume.; New libfx checkpoints cannot be restored by older versions. Existing checkpoints still load.; Invalid Base64 image input now throws directly from…
-
FX 0.0.12 released
libfx now uses LIBFXMODELUNSUPPORTEDEFFORT and LIBFXMODELUNSUPPORTEDFAST for unsupported model settings. Callers checking the old error codes must update.; libfx accepts model: { id, effort, fast } and supports Blob or File images directly.; Detached…
What changed: recent FX releases
13 stable releases in the last 90 days · Full changelog
- libfx now uses LIBFXMODELUNSUPPORTEDEFFORT and LIBFXMODELUNSUPPORTEDFAST for unsupported model settings. Callers checking the old error codes must update.
- libfx accepts model: { id, effort, fast } and supports Blob or File images directly.
- Detached processes such as tmux, ssh-agent, and browser drivers now stay alive between shell calls.
- /mcp list now opens the interactive Servers menu.
- In a 14,600-session benchmark, fx sessions dropped from 95 seconds to 0.17 seconds and fx --resume last from 33 seconds to 0.5 seconds.
- /new, /clear, and /reset now preserve the previous conversation in terminal scrollback.
- Automatic recovery: /continue has been removed. fx now retries and continues on its own.
- Default model: fx now uses Grok 4.7 as its default model. Fast mode remains opt-in.
- Custom connections: fx now supports named OpenAI Chat Completions connections for local servers and other gateways. Configure them in ~/.fx/settings.json, then select one with fx provider <name>…
- Provider routing: Gateway users can set providerorder and providerstrict, or pass --provider-order and --provider-strict, to prefer or restrict which providers serve a model.
- Interactive flags: Interactive sessions accept --provider, --model, --effort, and --fast; fx ask accepts --model, --effort, and --fast for one run without changing saved preferences. Grok models…
- Slack bot: fx can now install and manage your Slack workspace bot from the CLI.
- Speed gains vary with session length and usage. Longer sessions improve the most.
- Shell failures now give the model clearer recovery guidance.
- /trace now provides better diagnostics for session-title issues.
- System notices have a cleaner visual treatment.
- Resume recovery now restores shell activity more reliably.
- Scrollback retention is more reliable when resuming long conversations.
- For simplicity, ! in the composer is just prompt text now. It no longer starts a terminal session. Commands go through the agent and the usual approval flow.
- Subagents can use their own model and reasoning effort. Use GPT-6, Astra, or Fable 5.1 to steer, then delegate implementation to Kimi K3.
- You can send feedback to a running named subagent without interrupting its current tool. The final result still comes back to the parent conversation.
- New conversations get a short title from the first prompt. Turn generated session titles off in /settings.
- Press ctrl+p while writing to open the model picker. Your draft and attached images stay where they are.
- ACP clients can set reasoning effort on supported models. They can also replay earlier tool calls as structured events.
- fx now uses a smaller shell tool with 75% fewer actions (3 vs 12), replacing the old terminal tool.
- Enter now steers active turns instead of queuing follow-ups, and ctrl+enter does the same.
- The subagent interface now has 67% fewer commands (2 vs 6), with direct delegation replacing the ctrl+x manager.
- The memory tool has been removed without deleting existing saved memories.
- createFxAgent() now exposes prompt, checkpoint, and close instead of the old session, model, and config APIs.
- createFxAgent() now takes apiKey and an optional model directly; Agent configuration through env is no longer accepted.
FX popularity and usage data
The GitHub repository has 3,350 stars, 519 of them added in the last 30 days. The latest stable release is 0.0.13, published Oct 4, 2026; there were 5 stable releases in the past 30 days. It was mentioned in 3 Hacker News posts and comments over the last 30 days.
Download the raw daily series: fx.csv
Gid Score breakdown
Each component is scored 0 to 100 from public signals; a dash means no data for it. Methodology.
FX FAQ
How much does FX cost?
Open source under the Apache-2.0 licence; check the website for any paid hosted plans.
Is FX open source?
Yes. FX is open source, released under the Apache-2.0 license.
How popular is FX?
The GitHub repository has 3,350 stars, 519 of them added in the last 30 days. The latest stable release is 0.0.13, published Oct 4, 2026; there were 5 stable releases in the past 30 days. It was mentioned in 3 Hacker News posts and comments over the last 30 days.
What is the latest version of FX?
The latest stable release we track is 0.0.13, published on Oct 4, 2026.
What are the alternatives to FX?
The closest alternatives in the same category by Gid Score are OpenAI Codex, Claude Code, Pi, OpenCode.
For the makers of FX badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/fx/)
[](https://agentgid.com/agents/fx/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
GitHub: vercel-labs/fx. Site rank: fx.sh on the Tranco list. See data sources for how each one is collected.
Product facts and pricing were checked against: fx.sh, github.com.
