Boost is a CLI wrapper that makes every command your coding agents run faster, quieter, and cheaper in tokens. You prefix any command with `boost` (for example, `boost docker build`) and Boost runs the real tool transparently while replacing its noisy output with a compact, agent-friendly summary.

Which coding agents does Boost support?

Cursor, Claude Code, Codex CLI, and Gemini CLI — Boost works behind the scenes with the agents you already use.

How does Boost make commands faster and quieter?

Boost runs the underlying command (docker, npm, go, gh, git, vite, bun, and 100+ more) and applies a per-command filter that strips progress bars, repeated chatter, and ANSI noise. For supported tools it also adds intelligent caching. Typical token reductions are 60–90%.

Yes. The token-saving features in the Boost CLI are free, and the core will stay free forever — no signup, no credit card, no trial timer. Later on, some advanced, enterprise-grade capabilities (think team-scale governance and managed acceleration) may be paid, but the CLI that makes your agent runs leaner and cheaper stays free. We will always be upfront about what is free and what is not.

We built Boost to fix our own bloated, expensive agent runs — and it turned out to help everyone. Keeping the token-saving CLI free is how JFrog gives something genuinely useful back to the developer community: if it saves you tokens and money, that is the whole point. Any future paid enterprise features are there to fund the free tier for large teams, not to gate the basics.

Who should use Boost?

Boost is built for everyone from startups to enterprises: solo developers using coding agents, teams trying to keep agent context under control, and organizations that want leaner, cheaper agent runs without changing the tools they already use.

How does Boost handle my data and privacy?

Your code, logs, and terminal output stay on your machine — all filtering and compaction happens locally and is never uploaded. The only thing Boost sends is lightweight, anonymous telemetry about how many tokens it saved. Our philosophy is simple: we learn from how Boost performs in the real world so we can keep making it faster and smarter for the people who use it, without ever touching what is private to you.

Boost CLI — Save Tokens. Maximize Context. By JFrog

The token bill
just went up

Token traffic is rising, and developer AI bills are following.

boost monitor — token-cost-trend

trend sources: a16z · OpenRouter · Claude Code

boost-monitor 1.0trend ▲ 2025 → now

┤ token volume ├

annual traffic

~10T/year -> >100T/year by mid-2025

ref: a16z State of AI

┤ coding share ├

202511%

now50%+

0%->0%+

token share

Programming became a much larger share of all tokens

ref: programming token share

┤ AI cost ├

[░░░░░░░░░░░░░░░░░░░░░░]

$0│$150$250

$0-$0

per developer

Enterprise coding-agent bills now land per developer

ref: Claude Code cost averages

■unoptimizedq quit · b run boost

The anatomy of a bloated context window

Repetitive terminal noise balloons the loop. Here is how Boost trims it.

terminal

○ → acme-app git:(main) claude

 ▐▛███▜▌
▝▜█████▛▘
  ▘▘ ▝▝

Claude Code v2.1.195

Opus 4.8 (1M context) · Claude Enterprise

~/projects/acme-app

› Fix the failing build

⎿ ⊞ Read src/api.ts, tsconfig.json

● I'll run the build and read the errors.

⎿ Bash(npm run build)

✓ build ran — noise stripped, 1 error kept

ERROR ./src/api.ts:42:18 — TS2345

Argument of type 'string' is not assignable to 'number'.

→ exact stack trace preserved · boilerplate dropped

● Found it — patching src/api.ts on the first pass.

⎿ Update(src/api.ts) +1 -1

Brewed for 6s

✓ Boost saved 409,100 tokens in this session

? for shortcuts · ← for agents● high · /effort

context window742,900 tok · 62%

This is your session with Boost on — toggle it to see the raw, context-flooding output it just hid.

Get started with agents

Learn aboutBoost in three minutes

A quick tour of how Boost compacts noisy command output and shows you the tokens you saved.

boost.dev/learnHD · MP4

overviewready · click to play

Know exactly how boostsaved you tokens

Switch a metric and watch the savings add up — per day, per command, per dollar.

localhost:4317/observabilitylive

Tokens saved · last 7 days

2,501,300

input tokens never sent to the model

-89.6%

Jun 15Jun 21

Saved commands

+2-312

-ok boost/internal/app (cached)

-ok boost/internal/cli (cached)

-… 308 passing/cached lines

--- FAIL: TestRetrieve (0.03s)

+1 failing test surfaced

+184.2k tokens savedboost retrieve a3f9c1

Tokens savedlast 7 days · live

Built for the Agentic SDLC

Three capabilities, one wrapper. Select a pane on the left — boost runs it live on the right.

boost — agentic-sdlc — tmux

0 ❯ capabilities3 panes

1 ❯ compaction@boostrunning

$ (go build ./...) | boost

input tokens 1,184,300[ -89.6% ]

boost0:agentic-sdlc*0 compaction2,195,820 tokens savedOTel ●

Enterprise backed. Platform ready.

Backed by JFrog

Built by the team behind the platform thousands of teams trust to secure and ship software.

why-boost — workspace

Explorer

why-boost

enterprise-security.md×

# Enterprise security

DevSecOps DNA from the platform trusted

to secure software supply chains.

- Secure by default

- Backed by JFrog's security platform

Every saved token is energy you didn't burn

Fewer tokens means less compute, which means fewer emissions.

boost — emissions

$ boost report

            v             ~v~
     ~v~                              v
        /\            /\              /\
       /  \          /  \            /  \
      /    \        /    \          /    \
     /  /\  \      /  /\  \        /  /\  \
    /__/  \__\    /__/  \__\      /__/  \__\
        ||            ||              ||
       _||_          _||_            _||_

● Saved 1.7M tokens of terminal noise.

● You avoided 359 g CO2e. ≈ 0.21 kg CO2e / 1M saved tokens.

Less noise → less compute → less AI exhaust in the atmosphere.

A directional sustainability signal, not audited carbon accounting. See the emission savings docs.

From zero tofewer tokens

Copy one line from the site, paste it, run boost init, work in your favourite agent, then watch the savings — the whole loop, start to finish.

boost.jfrog.com

$free--forever·# no signup required

Save Tokens. Maximize Context.

Run one line in your terminal — that's it.

install.sh

$curl -fsSL https://raw.githubusercontent.com/jfrog/boost/main/install.sh | bash

Copy

Works with every coding agent

Claude CodeCursorGitHub CopilotCodex

Read the quickstart guideView on GitHub

Auto-playing demo · token, cost & CO2e figures are illustrative.

Questions about Boost

Everything you might want to know before you install.

# select a question

boost — faq

$ boost

Take control of your token spend.

Install Boost in one line. Free, no signup, no workflow changes.

install.sh

$curl -fsSL https://raw.githubusercontent.com/jfrog/boost/main/install.sh | bash

Download Boost (Free)View DocsCtrl /

New version of Boost released— New filters and website polish

Save Tokens. Maximize Context.

The token billjust went up

The anatomy of a bloated context window

Learn aboutBoost in three minutes

Know exactly how boostsaved you tokens

Built for the Agentic SDLC

Enterprise backed. Platform ready.

Backed by JFrog

Every saved token is energy you didn't burn

From zero tofewer tokens

Save Tokens. Maximize Context.

Questions about Boost

Take control of your token spend.

Help us improve Boost

The token bill
just went up