The problem
AI tools can generate more social content than a person can safely publish. Closed schedulers are browser-only, so agents cannot queue posts, and teams still copy-paste between ChatGPT and Buffer-style dashboards. That creates volume without control: wrong captions, wrong accounts, and posts that go live without review.
Solutions
We are building Social Scheduler. Its features are:
- Connect social channels (OAuth) and group them by brand or client.
- Draft, schedule, and cross-post from a web composer with calendar and kanban review.
- Let agents schedule via @openquok/auto-cli, MCP tools, or the public API (@openquok/node-sdk).
- Media library, photo editor, analytics, recurring posts, templates, and workspace isolation (channels, tokens, and MCP endpoints per workspace).
- Self-host with Docker Compose as an alternative to closed SaaS scheduler
Why this approach works
Most teams still treat scheduling as a human-only dashboard: agents draft in chat, someone copy-pastes into Buffer-style tools, and volume grows faster than review can keep up. OpenQuok treats scheduling as infrastructure agents can call—CLI, MCP, and a documented public API—while every draft, whether from a person or an agent, lands in the same calendar and kanban queue with approvals and preview links before anything publishes. That is the gap closed schedulers leave open: you keep OAuth-connected channels, per-platform captions and media, channel groups for clients, plugs and recurring workflows, and workspace-isolated tokens—not a second silo for “AI posts.” You can run it on OpenQuok Cloud or self-host with Docker when you want control over data and integrations instead of betting on a black-box SaaS.
Where it stands now
The product is live and usable end to end: major networks (Facebook, Threads, Instagram, LinkedIn, X, YouTube, TikTok, Dev.to), web composer with global vs per-channel modes, media library and photo editor, analytics where providers allow, templates, team workspaces, and first-party agent paths (@openquok/auto-cli, hosted MCP, @openquok/node-sdk). The Building Blocks and Playbooks catalog plus setup docs are aimed at shipping repeatable agent workflows, not one-off scripts. Active work follows the public roadmap—deeper parity across networks (formats, analytics, provider edge cases), polish on self-host and enterprise-style deployments, and growing the creator catalog. We are looking for early teams and agencies stress-testing agent + human review at real volume, self-hosters reporting integration pain, and contributors who care about open scheduling (new providers, docs, playbooks); Discord and roadmap proposals are the fastest ways to steer what ships next.
ทีมงาน
เจ้าของโปรเจกต์