Your AI. Freshly squeezed.

More juice.
Every turn.

Spend less, give your AI better context. Prefex squeezes more work from the AI budget you already pay for. ReadyBase adds the vitamin C, and the C is context.

Mac and Windows app · Claude Code and Codex · your models, your keys

01 / PrefexLess waste, more good stuff.Get 16 tools in one local binary, combining 450k+ GitHub stars

What's under the hood?For anyone tired of yet another AI-generated site: the measurements, the features we switched off, and the bugs that taught us.

Pay nothing until Prefex saves you $500. No trial clock, card or account.

$0 to $400Savings add up while you work.$400A heads-up at 80%.$50015 more days to add a licence key.

Only savings beyond your provider's own prompt caching count. After that, Prefex hands Claude Code and Codex back to their direct connection, so your agents keep working.

Meet your daily essentials

Squeeze the lemon. Take your vitamin C.

PREFEX · 01 / 05

0:00 / 0:20

01 · The budget squeezenow shipping

Prefex

Same lemon, a much better squeeze.

You're paying for powerful AI. Prefex gets more useful work out of it by trimming repeat work, making better use of prompt caching and matching the job to the model.

You shouldn't need one tool for routing, another for compression, a third for small fast models and a fourth for local LLMs. Prefex brings them all into your Claude Code or Codex terminal, and you keep working the way you do.

Stretch Claude and Codex plan limits
Cut waste on your API bills
Mix providers, with local models in the loop

Distils 16 proven projects with 447,644 GitHub stars between them, re-authored as a single Go binary with sidecars.

Explore Prefex

What's inside the squeeze?

Cache assist and routing do most of the saving, with compaction and session memory beside them. Savings are measured per request from provider billing fields, beyond the native caching baseline.

READYBASE · 01 / 05

0:00 / 0:20

02 · The context vitaminearly preview

ReadyBase

Meaningfully viable context, every turn.

An expensive model shouldn't have to rediscover your project every turn. ReadyBase hands it the smallest brief that still gets the turn right: the files, dependents and constraints this change touches.

A large graph database, or stuffing the whole repo into context, would work too. Most turns seldom need either, and you pay for both on every one. Start with the small dose, and reach for the heavy tools only when a turn calls for them.

Right-sized context, prepared per turn
Know what a change could affect before editing
Less searching, less repeating your brief

Distils 8 proven projects with 155,166 GitHub stars between them, re-authored as a single Go binary with sidecars.

Explore ReadyBase

How is the context prepared?

ReadyBase combines deterministic checks, repeatable rules about your project, with fast small models that pick the viable slice of context before a frontier model starts. Nothing to index into a graph store, nothing to stuff.

GitHub stars belong to the source projects; they are not PromptForce users or endorsements. Each product page carries the full attribution.

Your AI shouldn't come with a leash

One app. Your models, mixed your way.

Keep Claude and OpenAI in the picture, add other providers, and let local models take suitable work. You choose how the pieces fit.

AnthropicOpenAIGeminiVertex AIAmazon BedrockOpenRouterVercel AI GatewayTypeSafe JevLocal models+ more coming soon

01 / DOWNLOAD

Open PromptForce.

The app brings Prefex and ReadyBase together, so there's no pile of tools to assemble.

02 / CONNECT

Pick your apps and projects.

Connect Claude Code, Codex or both. Add the providers you use and the projects your agents should know.

03 / WORK

Keep working your way.

Savings and plan limits sit in the menu bar, and context briefings are ready before your agents start.

A few good questions

Before you take a sip.

Is the $500 a credit or a guaranteed saving?

Neither. It is the savings threshold for Prefex's free use, not a cash credit and not a promise of how much you'll save. Savings depend on your workload. Prefex counts only what it adds beyond your provider's own prompt caching, from the provider's billing fields.

Will my AI subscription actually last longer?

Prefex cuts avoidable token use and can route suitable turns to other models. How far your plan stretches depends on your workload, provider limits and settings. The app shows plan usage and warnings so you can decide what to do next.

Do I have to switch AI providers?

No. Start with Claude Code or Codex and the provider you already use, and add other providers or local models when you want to. You bring your own subscriptions and API keys.

What does "vitamin C" mean here?

The C stands for context. ReadyBase prepares the meaningfully viable context for each turn, using repeatable checks and fast small models, before the expensive model gets to work. Graph databases and context stuffing are the heavy dose; most turns do fine without them.

What leaves my Mac?

Prefex and ReadyBase run locally. Your prompts and keys go only to the providers you configure. Once a day the licence check sends a salted machine hash and the savings meter reading, so a reinstall can't reset the offer; it never sends prompts, keys or your email. An anonymous daily usage summary (counts only) is on by default; turn it off in Settings. Details: Prefex privacy and ReadyBase privacy.

What if I'm on Linux?

The app ships for macOS and Windows. On Linux, this installs Prefex, then ReadyBase:

curl -fsSL https://promptforce.ai/install.sh | bash &&
curl -fsSL https://promptforce.ai/rb-install.sh | bash

Each script is readable before you run it: install.sh and rb-install.sh.

Make every token worth the squeeze.

Less waste with Prefex, better context with ReadyBase.

Talk to us about your team