Spend by repository
- northwind/api$6,240.0033.0%
- northwind/web$4,810.0025.4%
- northwind/mobile$3,120.0016.5%
- northwind/infra$2,090.0011.0%
- Other (5)$2,672.0014.1%
Spend by developer
- alice@northwind.dev$4,210.00 / $3,800.00
- ben@northwind.dev$3,560.00 / $3,800.00
- chloe@northwind.dev$2,980.00 / $3,800.00
- diego@northwind.dev$2,540.00 / $2,800.00
- erin@northwind.dev$1,870.00 / $3,000.00
Spend over time
Actual spend and what Lineman saved, per hour across a day
Month-end forecast
Projected from current run-rate vs budget
At this run-rate you will exceed the monthly budget in ~4 days.
Cost efficiency
Unit economics and Lineman savings
Free plan, no credit card. 30-second install.
Ask Claude about your Lineman spend.
Connect the Reporting connector once, then anyone who watches the numbers (finance, managers, developers) can ask Claude about your usage, savings, and budgets in plain English. Straight from Claude Desktop or Claude Code, with no dashboard to learn.
- “How much did Lineman save us last month?”
- “Which repos used the most tokens this week?”
- “Set our monthly budget to $2,000 and alert me at 80%.”
Same context to the model. Fewer tokens on the bill.
Lineman sits between your tools and Claude. It shrinks the heavy stuff and labels the spend, without changing a line of how your team works.
Intercept
Hooks catch every Read, Bash, Grep and build output before it ever reaches Claude.
Compress
A secondary LLM rewrites the noisy bulk into a tight summary: the same signal, a fraction of the tokens.
Attribute
Every call is tagged from your git context: developer, repo, branch, ticket and model. No manual work.
Claude reads the same files and the same build results. You are simply billed for fewer tokens.
Catch the spend that should not be happening.
Lineman watches every 15-minute bucket and flags the spend that matters: an unauthorised repository, work outside hours, a budget breach, or a sudden spike, each with the developer, repo and model that caused it already attached.
- Unauthorised-repo detection, so secrets and side-projects don't burn budget unseen
- Per-team and per-member budgets, daily, weekly and monthly
- Out-of-hours flags tuned to each developer's timezone
- Root-cause on every spike: who, where, which model
From a session to a line of spend, instantly.
A developer just works. Lineman watches the calls, reads the git context, and resolves the whole session to one attributed figure. Zero manual tagging.
- developer
- alice@northwind.dev
- repo
- northwind/api
- branch
- feat/billing
- ticket
- NW-412
- model
- claude-opus-4
Bring Lineman to any MCP editor.
Shipping in Claude Code today. Cursor, Cline, Continue and Windsurf all speak the same open protocol, so Lineman travels with you.
- Claude Code
- CursorComing soon
- ClineComing soon
- ContinueComing soon
- WindsurfComing soon
- GitHub CopilotComing soon
No proprietary lock-in. Your editor, your workflow, your keys.
One line to install. Instant savings.
Drop Lineman into Claude Code and start cutting your token bill on the very next command. No prompts to rewrite, no workflow change.
- Installs the plugin + CLI in one command
- One-time browser sign-in, then nothing to manage
- Compresses every large Read, Bash and Grep result
Four jobs, one plugin.
Lineman compresses your spend, explains it, governs it, and keeps your sessions going. Pick a job to see how.
Compress the noise, keep the signal
Lineman trims large prompts, file reads and build output before they reach Claude, with no loss of meaning. You send fewer tokens and pay less.
- Prompt compression
- Smart file reading
- Build and test triage
Compress the noise, keep the signal
Lineman trims large prompts, file reads and build output before they reach Claude, with no loss of meaning. You send fewer tokens and pay less.
- Prompt compression
- Smart file reading
- Build and test triage
See every Claude dollar, attributed
Every Claude Code call is tracked and attributed to a developer, repo and ticket in real time, with no manual tagging.
- Per-repo and per-dev spend
- Live activity feed
- Month-end forecast
Catch the spend that should not happen
Lineman flags unauthorised repos, out-of-hours work and budget breaches, each with the developer, repo and model that caused it already attached.
- Unauthorised-repo alerts
- Per-team budgets
- Root-cause on every spike
Keep context past the compaction wall
Lineman summarises your session before Claude's native compaction, so long sessions hold on to far more of what matters.
- Smart compaction
- Longer working sessions
- Fewer lost threads
Enterprise-grade by default.
You are handing Lineman the most sensitive thing you own: your source. So the safe choice is the default. Compression happens in memory, your code never trains a model, and every dollar of Claude Code spend is logged and attributable.
ISO 27001 + ISO 27701 accreditation in progress (SOC 2 to follow). Goo Holdings Ltd (England and Wales), trading as Lineman.
- Memory-only compressionSource never persisted to disk
- Never trains on your codeYour code is never sent to model training
- EU data regionProcessing and storage stay in the EU
- Encrypted in transitTLS on every call, end to end
- Least-privilege accessScoped, fully attributed reads
- Full spend audit trailExportable, per-developer and per-repo
Everything you'd ask before you install.
The questions engineering leaders and developers raise most, answered up front.
Is there a free plan?
Yes. The Free plan needs no credit card and gives you the cost and spend reporting dashboard, tracking up to $1,500 per month of AI agent spend across your repos, tickets, and models. Paid plans add Lineman's token-saving tool (40%+ fewer tokens), team seats, and uncapped reporting. You can start a 14-day trial of a paid plan at any time.
Doesn't summarisation lose information the model needs?
Lineman never summarises blindly, every compression is task-aware: the secondary model sees what your model is working on and only drops content demonstrably unrelated to it. And it stays risk-free, because Claude keeps control. Whenever it judges a summary too thin for the task, it falls straight through to the full, verbatim output, so you never lose anything you actually needed. The false-drop rate sits at 0.4% across our benchmark suite.
What about privacy? Where does my code go?
Tool output is processed in memory only and discarded as soon as the response is returned. Nothing is logged, trained on, or persisted unless you opt in to telemetry.
Which clients does Lineman work with?
Today, Lineman works with Claude Code. Cursor, Cline, Continue and Windsurf are coming soon. Because they all speak the open MCP standard, support is mostly a matter of testing, and we only ship a client once we test it daily, which right now means Claude Code.
How do you count compressed tokens against my plan?
Only the input tokens that pass through Lineman count toward your monthly limit, Basic 100M / month, Pro 440M / month. We never count tokens we drop, and we never count the primary model's response tokens. You can watch the meter live in your dashboard.
What happens if I exceed my plan limit?
Compression keeps working, we never block your dev loop, but additional tokens are billed at a small per-million rate. If you're consistently over, switching plans saves money; the dashboard tells you when.
Drop it in. Watch your Claude bill drop by half.
One config line, works with Claude Code today. Most users see their first compressed call within 30 seconds.