Claude Code
Through the Claude Agent SDK, with an API key or your Claude subscription. Stops to ask when it needs a decision, and reports its own cost (API-equivalent on a subscription).
Agent orchestrator · Nº 01
Run Claude Code, Codex and Cursor side by side — queued, sandboxed and on a budget — on your server or your own machines. Watch every agent work, answer its questions, and ship the result as a branch or a pull request.
Claude Code · Codex · Cursor · parallel runs · sealed containers · self-hosted · MIT
QUEUED
waiting for a slot
QUEUED
waiting for a slot
QUEUED
waiting for a slot
§ 01 · Providers
Three coding agents, one workflow. Each runs through its own SDK in the same sealed container, reports into the same timeline, gets the same skills and MCP tools, and delivers the same way.
Through the Claude Agent SDK, with an API key or your Claude subscription. Stops to ask when it needs a decision, and reports its own cost (API-equivalent on a subscription).
Through the OpenAI Codex SDK. Makes its own choices and lists open questions in the summary; its cost is estimated from the price table you can edit.
Through the Cursor SDK. Like Codex, it decides on its own and lists open questions at the end, with an estimated cost.
.env, the OS keychain for npx jungle-monkey, the macOS Keychain on a computer you add. A run gets only its own agent's key.§ 02 · Orchestration
A queue in front of every agent, limits on what runs at once and what it may spend, and loops that bring a task home.
Tasks queue and start when their host has a free slot: the server runs up to MAX_CONCURRENT_TASKS at once (default 2), each computer you add has its own limit (1–32). A schedule skips or queues a firing while its last task still runs.
Add a Mac in Settings → Computers (it runs fleetpocket-node with its own Docker and agent keys, and only connects out), then choose per project or per task where a task runs.
Every run's tokens and cost: reported by Claude, estimated for Codex and Cursor (≈$0.84). Totals by project, agent and day with a CSV export. Monthly caps per project, schedule or overall hold new runs at 100%, with a notice at 80% and a one-tap "Start anyway".
Off until you turn it on, globally or per project. Then a failing check on a Jungle Monkey PR starts a minimal fix from the trimmed CI logs, up to a few attempts and within a budget. A fix that touches CI config or tests waits for your OK.
MCP servers (Linear, Sentry, a database, any npm/pip package or image) per project or globally. The agent reaches them through a gateway that holds the credentials, enforces tool lists and call limits, and logs every call.
Start a task on a timetable with its own budget, or let a task loop until your check (npm test, go test ./...) passes; the PR or local branch arrives once, at the end.
Claude hands exploring and test runs to subagents on a cheap model, and a reviewer checks the diff. Their steps show as "via explorer", their cost counts toward the run, and the same sandbox policy applies. Claude only.
§ 03 · Observation
The canvas puts every running task on one board as a live node, whichever agent runs it: what it is doing now, its activity lanes, the files it read (R) and wrote (W), its steps, cost and time. Flip a node to a plain terminal for the same run as log lines. Answer a question, send a follow-up, or restore a checkpoint and let the agent continue from there.
QUEUED
waiting for a slot
Touched
§ 04 · Security
Whichever agent runs, it gets a folder, a prompt and its own provider key. No GitHub token, no Docker access, no host network. The GitHub and MCP credentials live outside its box. Tap a hop.
§ 05 · Deployment
Three ways in. Start on your laptop in a minute; move to a server when you want it running while you sleep.
npx jungle-monkeycurl -fsSL https://raw.githubusercontent.com/AndrewSl105/jungle_monkey/main/deploy/install.sh | sh.env.docker compose -f docker-compose.deploy.yml up -ddocker-compose.deploy.yml: Caddy, the web app, the server, Postgres and a Docker socket proxy.deploy/cloud-init.yaml for Hetzner or DigitalOcean.| Question | On your computer | On a server | Self-hosted |
|---|---|---|---|
| Where it runs | your laptop or desktop, in your Docker | a small Linux VPS | wherever you put it |
| GitHub needed? | no: local repos get a branch back; connect GitHub for PRs | yes (your own GitHub App) | yes (your own GitHub App) |
| Phone access | not yet: use a server install | yes: PWA and Telegram | yes: PWA and Telegram |
| Runs 24/7 | no, stops when the computer sleeps | yes | yes |
| Setup time | about a minute | about 10 minutes | as long as you like |
§ 06 · Field access
One app on every screen. Phone and Telegram need a server install.
The task list and the open task side by side: start, answer, follow up, merge.
Every running task as a live node on one board, grouped by the machine it runs on.
Laid out for one hand. With the Ideas board turned on, drop in ideas (voice notes with a speech-to-text provider) and turn a card into a task.
An optional bot and Mini App that ping you when an agent asks something.