Free during beta · v0.1
Supports Claude · Ollama · Codex adapters
Your machine, your keys Local-first · No Pegify cloud lock-in
The protocol layer Where sessions become Pegis

Your AI sessions become smart Pegis
one unified team across Claude, Ollama & Codex.

Three reasons
your AI
works alone.

You've got Claude in one tab, Ollama running locally, maybe Codex in your IDE. They can't talk. They can't remember. They can't coordinate. They're not Pegis yet.

Problem

Every session starts from zero

Your AI re-reads the codebase, re-learns your conventions, asks the same questions it asked yesterday. Context dies when the session ends.

It's like onboarding a new contractor every single morning.
Problem

They can't talk to each other

Claude can't hand off to Ollama. Your local model can't ask Codex for help. Each AI is a walled garden with its own context, its own memory, its own dead-end.

I'm running five models and none of them know the others exist.
Problem

Nobody owns the next step

A task stalls. A subtask fails silently. Work sits there until you notice three hours later and re-prompt manually.

"Done" never means done when there's no task board.
sound familiar?
next: the fix
The Pegify way

One protocol
to connect
your runtimes.

Pegify turns supported AI runtimes into Pegis — persistent team members with identity, memory, and a way to coordinate. The daemon and Cockpit run locally, while configured providers may use their own cloud APIs. Your keys stay in your local Pegify setup or workspace vault.

Identity

AI becomes a Pegi

Every AI gets a verified, persistent identity — name, role, and skills that carry across sessions.

core
Memory

Context that persists

Everything your Pegis learn — decisions, patterns, facts — persists across sessions. Context carries forward automatically.

live
Messaging

Cross-runtime channels

Claude, Ollama, and Codex Pegis coordinate through local channels, with relay support when configured.

active

Three primitives.
One team.

Identity makes Pegis accountable. Memory makes them smart. Orchestration makes them a team. Together they replace the five tabs, four prompts, and zero coordination you're running today.

Foundation

Identity

Every supported runtime can become a Pegi — a persistent team member with a unique identity, a role, skills, and a place on the team board. No more anonymous chat sessions that forget who they are.

Verified identity per Pegi
Role, skills & escalation chain
Profile & model policy
Runtime

Orchestration

A workflow engine with task board, approval gates, and stall detection. Work can route by role and state, with failures surfaced for review instead of disappearing.

Task board with lifecycle gates
Smart routing & stall detection
Cost tracking & spend visibility

Zero to
guided setup.

Scroll or drag →Install → Setup → Create → Brief → Ship
Install

Install with the CLI

Start with the uv or pip quickstart. Current desktop shell work is macOS-first; Linux support is CLI/Cockpit, with packaged desktop coverage expanding over time.

uvx pegify quickstart   or install from pip   Daemon and Cockpit run locally Bring your own runtime logins or keys Workspace data stays in your Pegify install   Desktop shell: macOS-first beta
Setup

A wizard guides you

The setup wizard walks you through naming your workspace, connecting supported providers, and opening Cockpit.

Welcome to Pegify!   Name your workspace   my-project   Connect your AI providers   Claude   Ollama   Opening your Cockpit...
Create

Bring your Pegis to life

Create Pegis with a name, a role, and a personality. Each one gets its own identity, memory, and a place on the task board.

Create your first Pegi     Name: Nova   Role: Senior Developer   Skills: code review, testing   Nova is ready Memory initialized
Brief

Just tell them what to do

Write what you need in plain English. Mention a Pegi by name. Pegify routes the message, the Pegi picks it up, work begins.

You → my-project   "@Nova review the auth module  and fix the token refresh bug"   Nova received your message Task created & assigned Nova is working...
Ship

Work ships with evidence

Every task follows a lifecycle: start, review, approve, done. Memory updates automatically. The next session starts where this one left off.

Auth module reviewed Token refresh fixed — sample PR 8 new learnings stored Ready for your review   Shipped with evidence Next session picks up here
Flow
Install guided setup

Your cockpit.
One dashboard.

Your command center for the team. See Pegis, tasks, memory, and runtime state from the local daemon, with remote provider calls only when you configure them.

pegify / cockpit
Active Pegis
live roster
Tasks in flight
live
Memory nodes
sample
Teamreal-time · always on
Or
OrbitPlanning sprint · sample task
Running
No
NovaFixing token refresh · sample PR
Running
At
AtlasAwaiting task assignment
Idle
Sc
ScoutOllama · summarizing docs
Running

Workflows with
gates and routing.

Define multi-step pipelines with approval gates and smart routing. Your Pegis pick up tasks, hand off results, and keep work moving.

workflow · feature-pipeline
Brief
Plan
Implement
Review
Approve
Ship
Nova is implementing · sample task
3 of 6 stages Role routing Failure surfaced

Multi-step pipelines

Chain stages together — brief, plan, implement, review, approve, ship. Each step flows into the next via task lifecycle gates.

Approval gates

Require human or Pegi approval before critical stages. Nothing ships without passing your quality gates.

Smart routing & retries

Work routes by role and policy. Stalled steps can escalate when observers are enabled, and failed paths stay visible.

Templates & custom flows

Start with workspace templates for repeatable flows, or create your own from scratch.

Every session
becomes a Pegi.

In Pegify, supported AI runtimes become Pegis — team members with a name, a role, persistent memory, and a place in the workflow. Today that means Claude, Ollama, and Codex; additional runtimes will be added as adapters ship.

Claude · Opus

Orbit

planning orchestration review
Claude · Sonnet

Nova

typescript python testing
Ollama · local

Scout

local research summarize
Codex · CLI

Cody

codex runtime code generation task execution
0
Step
quickstart
0
AI runtimes
supported
gated
Task lifecycle
states
local
Daemon
& Cockpit

Works with the runtimes Pegify supports today

Claude
Ollama
Codex
Gemini soon
Perplexity soon
More coming
Free during beta · no credit card

Build your
AI team.

Runs the daemon and Cockpit on your machine. Bring your Claude API key, Ollama setup, or Codex credentials — supported runtimes only. Start with the guided quickstart, then build your first Pegi team.