First 100 customers: $29 for a full yearfree 14-day trial
OAICA is a terminal AI CLI that points Claude Code, opencode and codex at a local Ollama or llama.cpp server, any OpenAI-compatible endpoint, or a machine you control. It hosts no models, needs no account, and never sees your code.
curl -fsSL https://oaica.com/install.sh | bash
Windows: irm https://oaica.com/install.ps1 | iex
14 days of the full paid set, no card. The free tier — local models, your own endpoints, the subagent tier — never expires.
The part nobody prices in
Wiring one model into a terminal agent is a weekend. Wiring a fleet — tiers, context limits, failover, adapters — is the project. Here is the work OAICA already did, with a conservative estimate of what doing it yourself takes.
| You would otherwise build | Typical effort |
|---|---|
| Endpoint config for every backend, with the same flags and env names across all of them | 4 h |
| Context-window probing and per-model token budgets, so long sessions stop truncating silently | 6 h |
| A health circuit breaker that moves a live stream to the other leg without dropping it | 10 h |
| Tier routing — one model to plan, another to execute — with the tool-call shapes normalised | 8 h |
| Per-request LoRA: loading, stacking, scaling, and keeping adapters isolated between callers | 12 h |
| Wrapping it all for Claude Code, opencode and codex, each with different expectations | 7 h |
| An installer for three operating systems that verifies its own download | 5 h |
| Then keep it working as the models keep changing | ongoing |
Estimates for a competent engineer starting from nothing, at 2026 model APIs. Not a quote for your time — a list of what is already done.
Pick your operating system. Each archive holds the oaica binary — unzip it, put it on your PATH, run it.
oaica-windows-amd64.zip
oaica-darwin-arm64.zip
oaica-darwin-amd64.zip
oaica-linux-amd64.tgz
oaica-linux-arm64.tgz
The script detects your platform and verifies the archive for you. Also available as .tar.zst, with SHA256SUMS and VERSION.txt.
Start with the machine under your desk. Move to a box on the network when you outgrow it. Nothing else changes.
Point it at a local Ollama or llama.cpp server on 127.0.0.1:11434. The common case needs no configuration at all.
oaica run llama3.2Set OAICA_HOST to any OpenAI-compatible base URL — a box on your network, a tunnel, or a hosted provider you already pay for.
export OAICA_HOST=https://<endpoint>Run Claude Code, opencode and codex on your own model, with the context window and tiers configured automatically.
oaica launch claude --model <model>Mix and match
Most launchers choose a vendor for you and stop there. OAICA runs a single session across every backend you have — a cloud model to plan, a local one to execute, a small one for the busywork, a long-context one for the moment the window fills — and names the leg that served each reply.
$ oaica launch claude \
--model <cloud-model> # the vendor you already pay
--sonnet-model <local-model> # the box under your desk
--haiku-model <small-local> # titles, topic detection, busywork
--oversize <long-context> # takes over when the window fills
--route-policy weighted \
--shard <local-model>:3 --shard <cloud-model>:1The model names are yours — OAICA ships no fixed list and probes whatever your endpoint actually serves. Walk it once with the wizard, save it as a named plan, and every later launch is one word:
$ oaica launch claude --plan workA primary, an execution tier, a background tier and an oversize/compaction tier. Nothing forces them onto the same provider — or onto the same machine. Each tier resolves from a flag, a saved plan, or a standing config, in that order.
local-first (the default), local-only, remote-first, remote-only, auto and weighted. weighted splits healthy traffic by weight on a session-sticky hash, so a conversation keeps its prefix cache instead of bouncing between legs.
The turn that digests a tool's output is the expensive one. oaica config set tool-model-default secondary moves every tool-heavy turn to another leg; oaica config set tool-model Bash tertiary does it for a single tool.
Built for real sessions
Not a chat box. The things that go wrong on day three, handled.
X-Oaica-Route names which one served each reply.oaica site new plans, writes, sanitizes and assembles a static page you can host anywhere.oaica doctor probes every configured leg and exits non-zero on any failure — safe to run anywhere.Check for yourself
Every claim below is a command you can run on the free tier. No asterisk, no "coming soon".
--model, --sonnet-model, --haiku-model, --oversize — four providers if you have four, and the wizard saves the whole arrangement as a named plan.--route-policy local-first|remote-first|auto|local-only|remote-only|weighted.--shard <model>:3 --shard <model>:1 — a consistent hash keeps one conversation on one leg, so its prefix cache stays warm.oaica config set tool-model Bash secondary sends the turn that digests a huge tool output to the cheap leg, and leaves the rest alone.127.0.0.1 address, so your provider key never leaves the machine and the tool never sees the raw stream.oaica remote add mine --base-url … --api-key-env … adds yours, and there is no release to wait for.claude, codex, cline, copilot, opencode, qwen, droid, pi and the rest of them, all pointed at the model you chose.oaica doctor probes every configured leg and exits non-zero on failure; --report writes the same thing with credentials stripped.Both are legitimate. One of them is a weekend; the other is every weekend.
Pricing
One licence, three devices, and no metering of what you run through it. Your inference bill — if you have one at all — goes to whoever serves the model, not to us.
$0
Never expires. No card, no account.
oaica doctor and the installer$29$39 / first year
Renews at $39 a year. Cancel any time.
$7 / month
Cancel any time.
Every fresh install runs the full paid set free for 14 days, no payment details. Full pricing and what is in each tier →
If you write about running models on your own hardware, you are the audience. Join from your dashboard, get a link, and keep 30% of each subscription payment it brings in — recurring, not a one-off bounty.
No. OAICA hosts no models and has no inference servers. It is a client that talks to the endpoints you configure — usually 127.0.0.1. There is nothing in the paid tier that sends your code anywhere else.
The paid tiers add what a single local model cannot do on its own: routing one tier of work to one model and another tier to a second, per-request LoRA adapters, failover that survives a dropped stream, the Claude Code / opencode / codex launchers, and the site builder. The free tier keeps local models, your own endpoints and the subagent tier, for ever.
Nothing breaks. The paid features stop responding and the free tier carries on working, unchanged and unlimited in time. You can buy a licence at any point afterwards and the paid features come back on the same install.
It is the first year of a yearly subscription. The launch price covers the first year only; from the second year it renews at $39 unless you cancel. Code Monthly is $7 a month if you would rather not commit to a year.
Three devices per licence. Deactivate one from your dashboard to move it to another — there is no waiting period.
Anything that speaks the OpenAI API: Ollama, llama.cpp, vLLM and most hosted providers. The launchers are tested against the models people actually run locally, and oaica doctor tells you what a given endpoint supports before you start a session on it.
Ask within 30 days and you get it, no interrogation. Email [email protected], or use the support button — the refund path is the same one a human reads.
The docs cover install, configuration and every command. There is a support chat on the site and at [email protected] — both reach the same inbox.
A tool you do not need is a subscription you have to remember to cancel. Here is the shortest version of who should close this tab.
What you are actually buying
Not a lighter tier — the whole product, on three devices, with nothing metered.
The risk is not yours. Run the entire paid set free for 14 days first, with no card. If it turns out not to be for you, ask within 30 days and you get your money back.
The price does move. The first 100 customers keep a full year at $29; after that it renews at $39. $7 a month if you would rather not commit to the year.
Still not sure? Compare the editions line by line, or run oaica doctor after install and let it tell you what your setup can do.