The agentic IDE
you can actually own.
Code with Capuchin — our own fast-and-reasoning model — or with Claude, Gemini, or ChatGPT. Or point it at your own model, local or on your own server.
Free to start. Open core. Any model — even yours.
Every model — including Capuchin, and yours.
Capuchin (ours), Claude, Gemini, ChatGPT — or your own model, local or remote. Switch per task; never locked to one vendor.
Never phones home.
On-device indexing and local models. Fully air-gapped when you need it. Your code never leaves unless you say so.
Agents that prove their work.
Signed, replayable runs. Test-gated edits. Automation an auditor will sign off on.
Your code. Your models.
No single company should control how you build software. MonkeysCode runs locally and connects to any API you choose.
Capuchin
A fast-and-reasoning coding model. Capuchin Flash for instant edits, Capuchin Reason for planning and agents. Included usage, no per-token surprise.
ours
Claude · Gemini · ChatGPT
Bring your own key (BYOK) or use managed access. Frontier power when you want it, billed transparently.
frontier
Your own — local
Run Ollama, llama.cpp, or vLLM on your hardware. Zero data leaves the machine.
on-device
Your own — remote
Point MonkeysCode at your own server or any OpenAI-compatible endpoint. Your infrastructure, your rules.
your infra
100 % Local. No telemetry.
We don't collect your code, your prompts, or your metrics. Point MonkeysCode at a local Ollama instance and it runs entirely off-grid.
Capuchin, the big three, or your own.
- 1Capuchin — our model — Fast-and-reasoning, two tiers (Flash + Reason), tuned for coding and included in your plan.
- 2Claude · Gemini · ChatGPT — First-class via BYOK or managed; swap with a setting, not a reinstall.
- 3Your own, local or remote — Ollama/llama.cpp/vLLM on your machine, or your own server / OpenAI-compatible endpoint. Same agent features either way.
- 4No degraded fallback — Local and self-hosted are full tiers, not a lesser mode.
1import { Router } from 'express'
2
3const router = Router()
4
5router.get('/api/users', async (req, res) => {
6 const users = await db.query('SELECT…')
7 res.json(users)
8})
Add pagination to the users endpoint
Capuchin
I'll add limit/offset params and update the query…
Your codebase never has to leave your machine.
- 1On-device index — Merkle-tracked, tree-sitter-chunked, embedded and searched locally.
- 2Air-gapped mode — Local index + local models + internal registry. Zero outbound calls.
- 3Optional team sync — Share an encrypted index when you want; turn it off and you're fully local.
- 4Monorepo-aware — A symbol/dependency graph so agents reason across services, not just nearby files.
Every agent run, signed and replayable.
- 1Signed event logs — A tamper-evident, replayable trail of plan, tools, and diffs.
- 2Test-gated apply — Agents can't commit code that fails your tests.
- 3Content-signed diffs — Verify exactly what changed and reproduce it byte for byte.
- 4Audit-ready — Hand a run to a reviewer or compliance officer to check themselves.
Diff Preview
- $except = [];
+ $except = [
+ '/api/webhook',
+ '/api/stripe',
+ ];
// shouldSkip()
+ if ($this→inEx…
SIGNATURE
sha256:e4a9f2c7…d31b
Stop guessing your AI bill.
- 1Included Capuchin usage — Generous use of our model with no per-token surprise.
- 2BYOK frontier — Use Claude/Gemini/ChatGPT on your own key; we don't mark up your tokens.
- 3Per-task budgets + hard cap — Agents stop instead of surprising you.
- 4Local-first routing — Keep routine work near-zero cost.
TODAY
$0.42
THIS WEEK
$2.87
BUDGET LEFT
$47.13
Per-Model Usage
Agent stops when budget is reached — no surprise bills
Plan. Edit across files. Verify. In parallel.
- 1Plan or Fast — Approve a plan for big changes, or fire instant edits for small ones.
- 2Parallel agents — Split work across files and services, then merge cleanly.
- 3Real tools, gated — Terminal, git, test runner, browser, MCP — each behind permissions.
- 4Browser verification — Agents prove a web change works with real navigation and screenshots.
Planning…
Planning…
Planning…
From IDE to full-stack platform.
MonkeysCode is just the first brick — we're building the tools developers need to go from keystroke to production.
MonkeysCode IDE
Win · macOS · Linux
The full agentic editor. Goes head-to-head with Cursor and Antigravity.
MonkeysCode Terminal (CLI)
All platforms
Agentic coding from the command line and CI — the same engine, headless. Runs Capuchin, Claude, Gemini, ChatGPT, or your own model.
Desktop Agent App
Win · macOS · Linux
A focused window to launch, watch, and orchestrate parallel agents — without the full editor.
How MonkeysCode stacks up.
Feature-by-feature comparison with the tools developers use today.
From keystroke to production.
MonkeysCode is the IDE arm of MonkeysCloud — an ecosystem that handles Git, tasks, hosting, databases, and monitoring.
MonkeysCode
write
MonkeysLegion
build
MonkeysCMS
model
MonkeysMail
send
MonkeysCloud
deploy
First-class for MonkeysLegion
Capuchin understands PHP 8.4 and the 28-package framework, not just JavaScript.
Powered by Apex
The same orchestration engine in the framework drives the IDE's agents.
Deploys to MonkeysCloud
From a verified diff to a live deploy without leaving the flow.
Free to start
Like every MonkeysCloud product.
Built for teams that can't compromise.
Whether you're in a regulated enterprise or a fast-moving startup, MonkeysCode adapts to your environment.
Regulated & sovereignty-bound
Air-gapped, your own/local models, every action signed.
Cost-conscious teams
Included Capuchin usage, BYOK frontier, hard spend cap.
Polyglot & back-end shops
First-class PHP, Python, Go, Rust.
Open-source-minded developers
Open core, Open VSX, no lock-in.
MonkeysCloud teams
One ecosystem from first keystroke to production.
We lead with how it works, not with hype.
MIT
Core license
Open where it counts
Open core, Open VSX registry, self-hostable end to end.
100%
Auditable runs
Verifiable
Signed, replayable runs you can audit yourself.
Zero
Vendor lock-in
No lock-in
Your models, your keys, your data, your machine.
Own your tools. Run any model.
Prove every change.
MonkeysCode — code with Capuchin, Claude, Gemini, ChatGPT, or your own model. The newest product in the MonkeysCloud ecosystem.