wednesday
beta · Apache 2.0

Small open models,
staffed as a team.

Install Wednesday. Bring the models you already have. Get a pipeline that plans, builds, runs real tests, and repairs until they pass — with your approval every time.

Verification, not vibes Your models, your GPUs No token meter
Wednesday terminal home
THE PROBLEM
wednesday

Cheap models exist.
Checked code does not.

Frontier seats are metered. Small open models are free to run but produce unchecked output. The gap between “it generated something” and “it ships” is still filled by humans.

Token meters kill seats

A full day on a frontier coding agent burns through daily caps before the feature is done.

One model alone guesses

No planner, no real test gate, no repair loop. Output looks plausible and fails in CI.

Code leaves the building

Regulated buyers cannot send source to frontier labs. Local models need structure to be useful.

THE SOLUTION
wednesday

Same models. Different structure.

Wednesday is the factory around the model: named roles, explicit approval, real verification, and repair until green. The tests decide — not the model’s opinion.

ONE MODEL ALONE

Small model → unchecked output

No plan gate. No real tests. No receipt. You still do the verification.

guess → hope
WEDNESDAY CREW

Planner → Coder → Tests ⇄ Repair

You approve the plan. Verification runs real commands. Failures loop until green. Receipt stays on your machine.

plan → build → verify ⇄ repair
HOW IT WORKS
wednesday

Type a request. Approve the plan.
Tests gate the result.

Keys stay on your machine. Every task requires explicit approval before any file is touched.

1
Request
→
2
Plan + Approve
→
3
Build
→
4
Verify ⇄ Repair
→
5
Ship + Receipt
Wednesday approval gate
You stay in control

Nothing runs until you type y. Piped input never auto-approves.

Real verification

Commands run against real files. The model’s opinion does not count.

Full receipt

Every run is persisted with evidence: tasks, events, result.

PRODUCT
wednesday

One install. Two buyers.
Full control.

Terminal harness today. Desktop surface next. Works with any OpenAI-compatible model — local or hosted.

Wednesday TUI home

Fullscreen TUI

Command palette, pager, per-seat model picks, 21+ slash commands.

Named teams & roles

Planner, coder, vision, workers — each with its own model and repair budget.

Local-first data

Credentials, tasks, and event logs live in ~/.wednesday. Never leave the machine.

Ollama · LM Studio · vLLM OpenRouter · NVIDIA NIM Any OpenAI-compatible
MARKET
wednesday

Where the demand is real.

Three clear buyer segments that already feel the pain of metered seats and data-leaving-the-building.

1

GPU-rich teams

Agencies and product teams already running local models who need structure so output is reliable enough to ship.

Need

Verification loop + roles

2

Regulated buyers

Banks, health, defense — source cannot leave the building. Local models only work with a proper factory around them.

Need

Air-gapped, auditable runs

3

Cost-sensitive seats

Teams that hit frontier daily caps and want unlimited coding seats without another metered subscription.

Need

Owned capacity, not tokens

Relative pull (illustrative)
Regulated
high
GPU teams
high
Cost seats
med
Why now

Small open models crossed the usefulness threshold. The missing piece is the factory that makes them trustworthy.

BUSINESS MODEL
wednesday

Never sell tokens.
Sell the factory.

The open core stays free. Revenue comes from the surfaces and services that enterprises and agencies actually need.

OPEN CORE

Free forever

Terminal harness, verification loop, team roles, full source under Apache 2.0. No feature gates.

HOSTED SEATS

Agency & team seats

Managed runs, shared crews, usage dashboards, priority support. Billed per seat, not per token.

ENTERPRISE

Air-gapped & pilots

On-prem packaging, SSO, audit exports, dedicated support for regulated deployments.

Unit of value

A reliable coding seat, not a token counter

Alignment

We win when customers ship more, not when they burn more tokens

WHY NOW
wednesday

Small models got good enough.
The missing piece is structure.

Three shifts landed at the same time. Wednesday sits at their intersection.

Models crossed the line

Open 7–32B coding models now produce usable diffs. They still need a process that refuses to ship unchecked work.

Local inference is easy

Ollama, LM Studio, vLLM, and tunnels made “bring your own model” the default path for many developers.

Data residency pressure

Enterprises and regulated teams cannot keep sending source to frontier labs. They need owned pipelines.

◎
The window

Whoever owns the verification-first harness for open models becomes the default seat for teams that refuse another token meter.

TEAM & TRACTION
wednesday

Founder-led,
shipping in the open.

Founder
Vaibhav Hajare
Founder · Builder

Shipping the terminal, the verification loop, and the open-source core in public. Focused on making small models ownable and trustworthy for real teams.

Where we are
PRODUCT
Terminal beta live · Apache 2.0 · npm @lab1207/wednesday
OPEN SOURCE
Full source on GitHub · no paid feature gates
NEXT
Desktop IDE · hosted seats · regulated deployments
THE ASK
wednesday

Turn open models into
owned coding teams.

We are building the structure that makes small models reliable enough to sell as seats — without token meters and without shipping source to frontier labs.

USE OF FUNDS

Core engineering, verification reliability, desktop surface, and first regulated pilots.

TRACTION PATH

Open-source adoption → agency & GPU-host seats → enterprise air-gapped deployments.

WHY US

Shipping the full open core now. No vaporware. The factory is already runnable.

wednesdaylabs.pages.dev github.com/lab1207/Wednesday npm i -g @lab1207/wednesday@beta