One editor · every model
Claude 3.7 Sonnet Claude 3.5 Haiku GPT-4o o3-mini Gemini 1.5 Pro Llama 3.1 Mistral Large DeepSeek-V3 Qwen 2.5 Ollama · local
v1.0 macOS now — Linux & Windows next →

Conversation in.
Shipped code out.

codefyio is the AI-native code editor where chat becomes code, code becomes files, and your workspace context never resets — across every model you choose.

  • Reasoning visible
  • Artifacts first-class
  • Context persistent
  • Unlimited local AI
codefyio — workspace
  
$ codefyio analyze auth.ts
✓ 0 bugs · 2 refactors suggested · tests generated
›
you

refactor auth to use JWT refresh tokens

Claude

Rewriting auth.ts with rotation. Surfacing as an artifact:

📄 src/middleware/auth.ts
+47 -12

> jwt.verify() throws on expiry — wrap try/catch

> refresh token → httpOnly cookie, not body

> rotation: 15m access · 7d refresh

> keep export shape, change internals only

[reasoning complete — 3.2s]

editor.tsx4,812
auth.tsmodified
terminal.log1,400
git diff840
18,240 / 200,000 tokens

9% · grounded in your workspace

// what's special

Everything Cursor does. The things it can't.

codefyio runs local AI with no caps, talks to your team inside the editor, and ships deep code intelligence — at 40% below Cursor Pro.

∞

Unlimited local AI

Run Ollama with zero completion caps — even on Free. Cursor limits you to 2,000/month.

⌬

Graphify

A live knowledge graph of your codebase — architecture, dependencies and blast-radius before you change a line.

⊘

Code Analyzer

Bug detection, refactors, documentation and test generation — wired into the editor, not a bolt-on.

◎

Talk where you build

WhatsApp, Zoom and Google Meet live inside the IDE. Review, pair and ship without context-switching.

⧉

Desktop app

A full Electron desktop IDE for macOS, Windows and Linux. Web Coder, the browser IDE, is Not released.

⛨

Compliance-grade

MCP v2 approval gate, audit logs and a runtime compliance guard. Enterprise controls from day one.

// integrations

Plugs into how your team already works.

Talk, ship and run models without leaving the editor — communication, providers and infrastructure wired into codefyio's native surfaces.

Communication

Pro+
WaWhatsApp
WhatsApp
In-IDE chat & review
ZmZoom
Zoom
Calls inside the editor
GMGoogle Meet
Google Meet
Pair without switching
MTMicrosoft Teams
Microsoft Teams
Chat & huddles

Models & Local AI

Free+
ClClaude
Claude
Recommended · BYO key
AIOpenAI
OpenAI
GPT-4o · BYO key
OlOllama
Ollama (local)
Unlimited completion
TsTailscale
Remote Ollama
over LAN & Tailscale
Pro+

Dev & Infrastructure

Pro · Business
GHGitHub
GitHub
PR review · clone · OAuth
Pro+
MCP
MCP v2
Approval gate · audit log
Pro+
GX
Shared GPU cluster
GX10 · split across team
Business
// the workflow

Describe it. Codefyio writes, reasons, remembers.

01 / chat → code → file

Conversation becomes a commit

Claude writes code fenced with a file path. codefyio surfaces it as a one-click artifact — diff preview, apply, undo. Natural language to committed file in a single turn.

02 / reasoning visible

See the work, not just the answer

Extended thinking isn't hidden. The Thinking panel streams the chain of thought in real time, so you can trust the change before you apply it.

03 / context persistent

Grounded in your workspace

The model knows your open files, recent terminal output and last commit. The conversation is grounded in the workspace — not a blank chat window.

// every model

Bring any model. codefyio routes the work.

Cloud or local, frontier or fast — codefyio orchestrates them all. Use your own API keys, run Ollama on your LAN, or share a GPU cluster across the team. Claude is the recommended default because it fits the way the editor thinks about code.

  • → Bring-your-own-key for Claude & OpenAI
  • → Remote Ollama over LAN & Tailscale
  • → Shared Ollama GPU cluster for teams
model · providercodefyio
  • Claude 3.7 Sonnet Recommended ✓
  • Claude 3.5 Haiku Fast
  • GPT-4o
  • o3-mini
  • Ollama (local) ollama.lan
  • Remote Ollama tailscale
context engine · workspace
▾ workspace/
▾ src/
editor.tsx indexed
auth.ts modified
chat.tsx indexed
▾ .git/
COMMIT_EDITMSG in context
// context engine

It knows the workspace. Not guessing.

codefyio continuously indexes your open files, terminal output and git history, then grounds every answer in that context. Graphify maps the dependencies so the model understands impact — before it writes a line.

200K
token window
50+
languages
∞
workspaces (Pro)
// pricing

Start free forever. Local AI included.

Upgrade when you ship daily. Annual billing brings the price down.

Founding Customer Offer

Save 50% with annual billing for a limited time. Your discounted renewal price is locked in for as long as your subscription stays active.

Monthly Annual · save 50%
Free
$0 /mo

Local-first AI coding. Yours forever.

Download Codefyio
  • ✓ Local Ollama
  • ✓ Gemini Code Assist (Google sign-in, where eligible and supported by Google)
  • ✓ BYO API keys (OpenAI, Anthropic, DeepSeek, Google)
Most popular
Pro
$20 /mo
or $120/year (save 50%)

The full AI IDE for individual developers.

Upgrade to Pro
  • ✓ Everything in Free, plus
  • ✓ OpenAI Codex (official sign-in where supported)
  • ✓ Claude Code (official sign-in where supported)
  • ✓ AI orchestration
  • ✓ Multi-agent workflows
  • ✓ Smart routing
  • ✓ Shared prompts & templates
  • ✓ Advanced context management
Business
$39 /user/mo
or $234/year (save 50%)

Team-wide AI with organization controls.

Upgrade to Business
  • ✓ Everything in Pro, plus
  • ✓ Organization-managed AI providers
  • ✓ Team policies
  • ✓ Usage analytics
  • ✓ Cost controls
  • ✓ Audit logs
  • ✓ SSO
Enterprise
Custom

Private gateway, compliance, and dedicated support.

Contact sales
  • ✓ Everything in Business, plus
  • ✓ Private AI Gateway
  • ✓ Self-hosted models
  • ✓ Custom provider integrations
  • ✓ Compliance controls
  • ✓ Dedicated support
+$8/mo
Extra cloud AI pack

500 additional premium requests

+$10/user/mo
Compliance pack

SOC 2 report · GDPR DPA · audit export

+$15/user/mo
Priority SLA

4-hour response guarantee

// the comparison

Compared to every other AI editor.

Unlimited local AI on every plan, in-IDE comms, and a codebase knowledge graph.

∞
local AI — even on Free
4
plans — Free, Pro, Business, Enterprise
0
code stored on our servers — Business+
codefyio
recommended
Cursor
Pro
Windsurf
Pro
Copilot
Pro
Replit
Core
Zed
Pro
Paid entry plan / month $20 $20$15$10$20$10
Unlimited local AI (Ollama) Yes Free ?????
BYO API keys Yes Free ????Yes
Cloud AI included Yes Pro YesUsage-basedUsage-basedYesUsage-based
MCP support Yes Pro Yes????
Codebase knowledge graph Yes Pro ?????
Code Analyzer (bug · test · docs) Yes Pro ?????
MCP approval gate + audit log Yes Pro ?????
In-IDE comms (WhatsApp · Zoom · Meet · Microsoft Teams) Yes Pro ?????
Org-managed providers · SSO · audit logs Yes Business ?????
Private / self-hosted gateway Yes Enterprise ?????

Vendor list pricing as of August 2026; plans differ in scope, so the quoted plan is named per column. GitHub Copilot is a VS Code extension, not a standalone IDE. Yes included · Partial / Add-on / Usage-based / Enterprise available with limits · — not offered · ? not verified by us (43 cells).

// roadmap

Shipping in the open.

Where codefyio is today, and what lands next.

Product

  1. Free v1.0 + Pro v1.1 Live
    Jun 15, 2026 · v1.0.0
  2. Business Upcoming
    Org-managed providers · SSO · audit logs · cost controls
  3. Enterprise On request
    On-premise · SOC 2 · private hosting

Platforms

  1. macOS Signing pending
    Electron desktop app
  2. Linux Build only
    Electron desktop app
  3. Windows In submission
    Electron desktop app
  4. Web Coder Not released
    Full browser IDE
$ codefyio .
◉ Claude 3.7 Sonnet — ready
›

Open the editor.
The rest writes itself.