Skip to main content

Built by makers, shipped in public

Sign in
Caveman Middleware logo

AI Coding Assistants

Caveman Middleware

Keep your framework, models, and tools while reducing token usage through per-format compression

Community votes
0
DR by Ahrefs
31 no change since last check

Ahrefs Domain Rating benchmarked 18 Nov 2026, rebuilt 18 Nov 2026.

Open-source middleware that compresses tool results in AI agent frameworks, reducing token consumption by up to 97% while keeping original data recoverable.

What it is

Screenshot of the Caveman Middleware homepage
caveman.so, as visitors see it

Caveman Middleware is an open-source compression solution for AI agents that reduces token usage by compressing tool results while preserving access to original data. It works as a lightweight wrapper around existing model calls in frameworks like Vercel AI SDK, OpenAI, Anthropic, and LangChain, supporting both TypeScript and Python. The middleware runs locally without requiring a Caveman account, maintaining your control over models, frameworks, and infrastructure. Results vary by content type: JSON sees 93.5% token reduction, YAML 96%, and XML 97.4%, while some formats like HTML may increase tokens slightly. Compressed data includes recovery handles so agents can retrieve full originals when needed, with recovery scope managed by application session and cache epoch.

What it is built with

  • Original data recovery via caveman_retrieve handles
  • Local runtime with no Caveman account required
  • 21 adapters across TypeScript and Python frameworks
  • Session-scoped recovery with cache epoch control

Pricing

Pricing model: Open source

Free and open source (Apache-2.0)

Follow the workshop. Log in to follow Caveman Middleware's workshop

Following Caveman Middleware means an email when they reach a milestone, post an update or launch a new product.

Caveman Middleware metrics

Benchmarks for caveman.so: Ahrefs Domain Rating and Majestic link data, with the change since the last build.
MetricValue
Domain Rating31 no change since last check
Trust Flow9 no change since last check
Citation Flow38 no change since last check
Referring domains443 no change since last check
External backlinks19,353 no change since last check

Ahrefs Domain Rating benchmarked 18 Nov 2026, rebuilt 18 Nov 2026. Main build topic: Computers/Open Source (8). Majestic benchmarked 17 Nov 2026, rebuilt 17 Nov 2026. Link data built by Majestic. Trust Flow, Citation Flow and Topical Trust Flow are trademarks of Majestic-12 Ltd.

Caveman Middleware domain build sheet

Open the build sheet
Public RDAP record, last read 17 Nov 2026, 23:50 UTC.
Domain age5 months
Registered
Expires
RegistrarKey-Systems
DNSSECNot signed

Inspect caveman.so's registration

Caveman Middleware after-launch build log

Since Caveman Middleware launched on Maker Launches on 17 November 2026, these are the figures we have tracked.

Domain Rating (Ahrefs)
31
First measured 18 Nov 2026
Trust Flow (Majestic)
9
First measured 17 Nov 2026
Referring domains (Majestic)
443
First measured 17 Nov 2026

Day 0 since launch. Next receipt: day 30, 17 Dec 2026. We show what changed, not what caused it: many things affect these numbers. Nothing here is estimated.

Biggest gains on Maker Launches

Planning a launch?

Plan your launch with our free playbook, from preparing your listing to choosing more launch directories.

  • The week before
  • Launch day
  • Launch week
  • Afterwards

Get the launch playbook

Questions from the bench

How do Caveman Code plans work?
A plan is a monthly amount of credits. Credits are dollars, spent at each model's list price: Pro is $20 a month with $20 of credits, Pro $60 is $60 a month with $60 of credits, Max $100 is $100 a month with $105 of credits and Max $200 is $200 a month with $220 of credits. Paying yearly costs 20% less for the same credits every month. Caveman Code is also free on your own keys and logins.
Which models make my credits go further?
On GLM-5.3 a credit goes three times as far, and twice as far on DeepSeek Flash and GLM-5.3 Flash. Every other model counts at list price. So Pro's $20 of credits buys up to $60 of GLM-5.3 in a month.
Is there a weekly limit on a Caveman Code plan?
One week, or any 5 hours, can spend at most 35% of a month's credits, so one long day can't use the month up. Past a limit, top-up credits pay if you have any, until the plan resets.
What is a top-up?
Extra credits you buy when you need them, on any plan or on Free. Top-ups are $5 to $500 at a time, are spent at list price on every model, and last 365 days. They have no weekly limit. Only the credits that come with a plan go further on some models.
How are Cloud computers charged?
A Cloud computer draws on the same credits while it is awake: $0.12 an hour for 2 CPU / 8 GB, $0.20 an hour for 4 CPU / 16 GB, $0.60 an hour for 8 CPU / 32 GB and $1.20 an hour for 16 CPU / 64 GB. Asleep is free. Each plan sets how many computers it keeps, how much memory can be awake at once and the largest machine.

Leave a review for Caveman Middleware

Nobody has put Caveman Middleware on the bench yet. Leave the first review.

Your rating

Reviewing is free, and nobody can pay for a review. Read the bench notes

Maker reviews · Workshop notes · Show it off · Did you make this? Claim it · Report this build

More on this profile

Caveman Middleware has a free listing. The owner can unlock the full profile with a paid launch for $5:

  • Founder story (locked)
  • Milestones (locked)
  • Demo video (locked)
  • Dofollow website link: not on this free listing (its website link is nofollow)

More builds like this

Ask us