FreelanceOS

Created By
Sohlin22 months ago
AI-powered freelance business manager for Claude Code. Proposals, invoices, time tracking, scope management, and follow-ups - 37 tools, 5 coaching skills.
Overview

FreelanceOS

Manage your entire freelance business from Claude Code. Proposals, invoices, time tracking, scope management, and follow-ups — all conversational.

npm version smithery badge freelance-os MCP server freelance-os MCP server

Install

claude plugin install freelance-os

When prompted, paste your API key. That's it — start managing your freelance business conversationally.

Get Your API Key

PlanPriceLink
Monthly$19/month (7-day free trial)Start Free Trial
Lifetime$40 one-timeBuy Once

Monthly plans include a 7-day free trial — no charge until day 8. Your API key is delivered instantly. Stored in your system keychain — never in plaintext.

What You Get

37 MCP Tools

Full CRUD across your entire freelance lifecycle:

EntityToolsWhat You Can Do
Clientscreate, list, getFull CRM — contacts, billing rates, notes
Projectscreate, list, get, updateTrack work per client with budgets and timelines
Proposalscreate, list, get, updateDraft, price, send — auto-seeds scope on accept
Invoicescreate, list, get, updateJSONB line items, tax, status tracking (draft/sent/paid/overdue)
Timecreate, list, aggregateLog hours, aggregate per project for invoicing
Scopecreate_definition, list_changes, log_changeDefine boundaries, detect scope creep
Follow-upscreate, list, get, mark_sentContext-aware reminders and check-ins

5 Coaching Skills

Claude learns freelance best practices — not just data entry:

SkillWhat It Does
ProposalsPricing strategy, scope clarity, revision limits, payment terms
InvoicesLine item structure, payment terms, overdue management
Follow-upsTiming, tone, and content for every follow-up scenario
ScopeScope definition, change requests, creep detection
TimeLogging practices, hour aggregation, time-to-invoice workflow

How It Works

You (Claude Code) → "Draft a proposal for Acme Corp's website redesign at $150/hr"
Claude (with FreelanceOS skills) → Expert proposal with pricing, terms, scope
MCP Server → Saves to your secure, isolated database
  • 5 skill files teach Claude freelance domain expertise
  • Hosted MCP server persists all data with per-user isolation
  • API key auth — your data is yours, protected by row-level security
  • Works offline — coaching skills work without a key (data persistence requires one)

Example Workflows

New client onboarding:

"I have a new client, Acme Corp. Contact is Jane at jane@acme.com. They need a website redesign, budget around $5k."

End-of-week invoicing:

"Show me all uninvoiced time for the Acme project this week and generate an invoice."

Scope creep detection:

"Jane asked for a blog section — is that in scope for the Acme redesign?"

Follow-up on overdue invoice:

"Invoice #INV-042 is 2 weeks overdue. Draft a polite but firm follow-up to Jane."

Requirements

License

MIT — skills are free, MCP server requires an API key.

Server Config

{
  "mcpServers": {
    "freelance-os": {
      "url": "https://freelance-os-production.up.railway.app/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
Sohlin2
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Mnemom

14 hours ago
//beforeyouship — LLM Cost Modeling From Your Editor
@Indiegoing

Query realistic LLM cost models without leaving your editor. beforeyouship models the **true monthly cost** of an LLM app architecture — retries, prompt caching, batch discounts, infra overhead, and 3×/10× growth — across GPT-5.x, Claude, Gemini, DeepSeek, and more. Not a token calculator: a planning tool for the design phase, before you commit to a stack. **No API key needed to try it** — demo mode covers the six free-tier models. A Pro key from [beforeyouship.dev](https://beforeyouship.dev) unlocks the full 18-model catalog. ## What you can ask - "How much will a RAG chatbot cost at 10,000 requests/day?" - "Compare Claude Haiku vs Gemini Flash pricing for my workload" - "What's the cheapest model for a multi-step agent at scale?" - "Show me current per-token prices for Anthropic models" ## Tools ### `estimate_cost` Full cost model for an architecture at a given usage level. Returns Naive / Realistic / Worst Case monthly cost per model, 3×/10× growth scenarios, and an opinionated recommendation with reasoning. ### `get_model_prices` Current per-1M-token pricing — input, output, cached input, batch — with context windows and staleness metadata. ### `list_archetypes` Seven preset architecture patterns (simple chatbot, chatbot with history, RAG pipeline, multi-model router, coding assistant, document processor, multi-step agent) used as starting points for estimates. ## Setup **Claude Code:** ​```bash claude mcp add --transport http beforeyouship https://beforeyouship.dev/api/mcp ​``` **Cursor / other clients** — add a remote server: ​```json { "mcpServers": { "beforeyouship": { "type": "streamable-http", "url": "https://beforeyouship.dev/api/mcp" } } } ​``` Add an `Authorization: Bearer bys_...` header with a Pro key for the full catalog. ## Try it > Estimate the monthly cost of a RAG pipeline at 10,000 requests/day

13 hours ago
Docwand

13 hours ago