agentleFS
aryaminusaryaminus/socials-assistant/llms.txt

socials-assistant

llms.txt0 starsChanged 3 months agoMITView on GitHub

Open-source creator analytics vault + MCP server + agent skills. Official APIs only, permanent local history, draft-first outreach. Pulls a creator's OWN TikTok, Instagram, Facebook, and YouTube analytics into a local SQLite vault the platforms can't expire, then reads it: weekly digests, top-content analysis, audience demographics, media kits, and brand-pitch drafts backed by verified numbers. No scraping, no ToS risk — official APIs plus TikTok Studio CSV imports for Studio-only data (retention, traffic sources). Then add the MCP server to…

  • Installs packages

The file

Files
llms.txt
# Socials Assistant

> Open-source creator analytics vault + MCP server + agent skills. Official APIs only, permanent local history, draft-first outreach.

## What it does

Pulls a creator's OWN TikTok, Instagram, Facebook, and YouTube analytics into a
local SQLite vault the platforms can't expire, then reads it: weekly digests,
top-content analysis, audience demographics, media kits, and brand-pitch drafts
backed by verified numbers. No scraping, no ToS risk — official APIs plus
TikTok Studio CSV imports for Studio-only data (retention, traffic sources).

## Quick start

```bash
git clone https://github.com/aryaminus/socials-assistant && cd socials-assistant
pnpm install && pnpm build          # or: ./setup.sh
node apps/mcp/bin/socials-mcp.js onboard
```

Then add the MCP server to any agent (config snippets in `agents/README.md`):
Claude Code, Claude Desktop, Codex, Gemini CLI, opencode, Cursor — locally via
stdio/HTTP, or deploy `infra/worker` to Cloudflare for a single remote URL.

## Key files

- `apps/mcp/` — socials-mcp server (20 tools, stdio + streamable HTTP) + CLI
- `packages/vault/` — SQLite vault, TikTok Studio CSV importer, analytics queries
- `packages/connectors/` — YouTube / Meta / TikTok official-API connectors
- `skills/` — socials-connect, weekly-digest, brand-outreach, media-kit, script-review, publish-package
- `infra/worker/` — Cloudflare Workers remote MCP (OAuth 2.1, multi-tenant)
- `docs/` — per-platform onboarding, hosting, automation, deliverability

## Full docs

See `AGENTS.md` for all install methods, env vars, and operations.
See `README.md` for the project overview and capability map.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.