ProAgentStore

ProAgentStore Platform

Marketplace for server-powered AI agents. Creators build agent templates, clients subscribe and run them on their own data.

Store: https://proagentstore.online API: https://api.proagentstore.online MCP: https://mcp.proagentstore.online/mcp Console: https://proagentstore.online/console/ GitHub: https://github.com/ProAgentStore Free pair: https://freeagentstore.online

What's in here

platform/

├── packages/sdk/ Internal TypeScript SDK for agents ├── packages/cli/ @proagentstore/cli — init, check, publish, MCP proxy, local runtime ├── packages/browser-runner/ ProAgentStore Playwright + terminal/coding runtime bundled into the CLI ├── workers/api/ Hono API worker (auth, agents, instances, coding, apply, keys, analytics) ├── workers/host/ Marketing site + console + widget ├── workers/mcp/ MCP server for Codex, Claude Code, Cursor, and VS Code ├── store/ Source HTML for all pages ├── skills/ Open Agent Skills source files ├── plugins/ Codex and Claude plugin wrappers ├── agents/ Tier-0 first-party agent sources kept in this repo └── templates/ Agent scaffolding (worker, cron, api)

Agent types

Quick start

Use an agent

# Try any published agent — no sign-up needed

curl -X POST https://api.proagentstore.online/v1/public/agents/chatbot/try \ -H "Content-Type: application/json" \ -d '{"message":"Hello!"}'

Build an agent

npx @proagentstore/cli init my-agent --template worker

cd my-agent pnpm install && pnpm dev npx @proagentstore/cli publish

SDK

import { initPro } from '@proagentstore/sdk'

const agent = initPro({ agentId: 'your-id', token: 'your-token' }) const { response } = await agent.chat('Hello!')

Embed widget

<script src="https://proagentstore.online/widget.js"

data-agent="chatbot" data-theme="dark">

MCP

codex mcp add proagentstore --url https://mcp.proagentstore.online/mcp

codex mcp list

If the server shows "Not logged in":

codex mcp login proagentstore

claude mcp add --transport http proagentstore https://mcp.proagentstore.online/mcp claude mcp list

npx mcp-remote https://mcp.proagentstore.online/mcp npx @proagentstore/cli mcp

MCP has two runtime modes:

• chat_with_agent calls the public trial endpoint. Use it for discovery and smoke tests.
• subscribe_agent creates your private instance, then chat_with_instance runs that instance with your own state, knowledge, and caller-provided AI credentials.

Typical user run:

list_agents -> subscribe_agent -> my_instances -> add_instance_knowledge -> chat_with_instance

The expected response when user-owned AI credentials are missing is:

Add your Cloudflare Workers AI account ID and API token before running this agent.

That means the instance runtime path is working and correctly refusing to bill the platform AI account. See MCP Instance Runtime for the full tool map, live test record, and OAuth troubleshooting.

The full MCP-first developer surface is documented at:

• https://proagentstore.online/docs/mcp/
• MCP
• server.json
• .mcp.json
• AGENTS.md

MCP safety is enforced server-side. OAuth supports read, write, runtime, and destructive scopes; MCP_READ_ONLY=1 forces read-only mode; mutating tools support dry_run where useful; overwrite/destructive tools require exact confirm values; and mcp_audit_log exposes recent MCP write, runtime, dry-run, denied, and destructive events.

Architecture

The current system map, runtime boundaries, data ownership rules, risk assessment, and refactor roadmap live in Architecture.

Browser runtime (pags up)

Browser- and coding-capable agents use PAGS as the control-plane brain and a local ProAgentStore browser runtime (runtimePlane: "pags", Playwright + terminal/coding capabilities, bundled into the CLI) as the hands. One public package, one command — no monorepo and no tunnel binary.

PAGS control plane / MCP / Workflows

-> task, auth, approval, audit, the LLM brain ProAgentStore browser runtime (pags up) -> Playwright, local files, real browser profile, terminal/coding engines Real browser / real repo -> job boards, uploads, receipts, coding sessions

npm i -g @proagentstore/cli

pags login pags up # one runner for every active runtime-capable instance

Signing in over SSH or on a headless machine (#1157). pags login --device shows a link and a short code (BCDF-GHJK); open the link on your phone or any device where you are signed in to ProAgentStore, check that the page names this machine, and approve — the machine signs in within seconds. It is chosen by itself in an SSH session (any OS) and on Linux with no display; pags login --browser forces the browser. A running pags up keeps its own sign-in alive: in a session's last 7 days it refreshes it, and if it cannot it says so in the pags up window and list_runner_nodes warns about the machine — while there is still time to run pags login --device over SSH.

Install once per machine, ever. Since CLI 0.4.63 the pags that npm installs is a small bootstrap stub (#862): every pags up asks npm for the latest @proagentstore/cli, fetches a newer release into ~/.config/proagentstore/cli/ / and runs it — so a machine never needs npm i -g again, however far behind it falls or whether it has ever heard of runner_update. runner_update (#859) updates the same cache remotely while pags up keeps running. A machine on 0.4.62 or older gets the stub from one last npm i -g @proagentstore/cli (or, on 0.4.62, from runner_update). PAGS_NO_SELF_UPDATE=1 turns the check off; a source checkout is never self-updated.

Remote updates restart everything, not just the runner (#860). After runner_update installs a release, pags up restarts itself — supervisor included — with the same flags, and every agent re-attaches (an older pags up restarts only the runner, and runner_update's answer says so in supervisor). A runner started without pags up can be updated remotely too, once something will start it again:

• launchd / systemd — run pags runner connect --watch-instances with PAGS_SERVICE=1 and restart-on-failure (launchd KeepAlive → SuccessfulExit: false; systemd Restart=on-failure). The runner exits with code 75 after an update, and the service manager starts it on the new release. It signs in with the saved pags login session.
• anything else (a tmux script, nohup) — set PAGS_RESTART_COMMAND to the shell command that starts it; the runner runs it, detached, as it exits.

With neither, runner_update refuses rather than stop a runner nothing would bring back. Either way a coding engine mid-turn is waited for first.

pags up is the canonical runner: one process serves every active instance whose `capabilities.runtime` is non-null. Cloud-only chat/RAG/connector agents (runtime: null) are skipped — they never need a local runner.

Membership is live, not a startup snapshot. pags up passes --watch-instances (CLI ≥ 0.4.30), so the runner re-reads /v1/instances/my/instances every 20s and attaches newly eligible agents — and detaches ones that stopped being eligible — without a restart. Subscribing to a coding agent while the runner is up just works. (Polling, not push: a brand-new instance has no socket to push over; #83 tracks the push path.) A scoped pags up --instance deliberately does *not* watch — it means that one agent and nothing else.

Transport is a WebSocket relay: the runner connects outbound to a per-(instance, node) RelayDO — no cloudflared, no public server, no inbound port. Cloud -> callRunner() -> RelayDO -> WebSocket -> runner. There is no --tunnel flag or tunnel fallback in the current CLI. The runner mints a short-lived, instance-scoped relay token for the handshake; the 30-day account JWT is never put in the WebSocket URL.

• Coder can run multiple machines against the same instance at once. Each coding session is pinned to the runner node that owns it; different repos can run on different machines concurrently.
• pags up --force — replace the current relay socket when debugging stale local connections
• pags up --instance — pin to one agent (debug)
• pags up --headless — headless mode

Job applications have two supported browser paths: the JOB_APPLY workflow (below) and the Scout → Tailor → Runner pipeline. The Coder agent runs its chosen engine (Claude Code, Codex, Gemini CLI, Grok, or a local command) on the session's assigned runner node; Claude uses a persistent structured session, while other engines run one-shot turns.

Legacy job application agent (JOB_APPLY, supported)

"Legacy" names its age, not its status: the Cloudflare JobApplyWorkflow brain driving the pags up browser is a supported way to run browser-based job applications, alongside the Scout → Tailor → Runner pipeline (#1062). Start one with POST /v1/instances/{id}/apply, the chat submit_job_application tool, or MCP apply_to_job. Every start needs a Job Application Assistant instance, a live runner and a résumé on file; one application runs per instance at a time, candidate values come only from your Profile, and each run opens a spend pool and a run row you can stop. The pipeline is the other path: triage a lead, tailor materials, then ask for review or let the Application Runner fill under its configured submission policy.

For the pipeline, upload source files directly in Application Tailor’s uploaded sources card (multiple files are supported), select the exact résumé and profile, and check readiness. With CLI 0.4.205+, newly generated résumés, cover letters and their profile/answers snapshots are stored in the Tailor’s private PAGS Files before materials become ready. Applications show Stored in PAGS with authenticated preview/download. A different runner machine fetches and verifies those exact versions and hashes, stages them privately for the browser, and removes the staged copies when the run ends. Existing Tailor workspace outputs follow their configured retention; they are no longer the only copy. Older applications remain explicitly local until regenerated. A material failure before the engine starts can offer Retry tailoring; an uncertain submission cannot use that recovery. Uploading or regenerating documents does not grant submission approval.

Skills and plugins

ProAgentStore publishes skills through platform-specific plugin marketplaces so users can find them from both Codex and Claude Code.

Codex:

codex plugin marketplace add ProAgentStore/platform

Claude Code:

/plugin marketplace add ProAgentStore/platform

/plugin install proagentstore@proagentstore /reload-plugins

See Skill Publishing for the publishing layout, marketplace files, and dual Codex/Claude release checklist.

Public discovery pages:

• https://proagentstore.online/skills/
• https://proagentstore.online/skills/proagentstore-mcp-operator/
• https://proagentstore.online/llms.txt
• https://proagentstore.online/llms-full.txt
• https://proagentstore.online/skills.json

Catalog agents

Where the catalog actually lives

The authoritative catalog is the `agents` table in D1, read through GET /v1/agents. Nothing in this repo is a mirror of it. A file in this repo is either a *sou