Skip to main content

Go-to-market automation — Google Workspace, LinkedIn (Unipile), and Attio CRM

Project description

agent-work

Go-to-market automation toolkit that connects Google Workspace, LinkedIn (via Unipile), Attio CRM, and ClearFeed into agent-driven workflows.

Built to be operated by coding agents (Claude Code, Codex, Gemini CLI, etc.) through natural-language recipes.

How it works

recipes/*.md          Declarative workflow specs (what to do)
src/agent_work/       Python clients for each service (how to do it)
scripts/              Standalone utility scripts

An agent reads a recipe, calls the service clients, and writes the output to Google Sheets.

Services

Client Service Transport
GWS Google Workspace (Gmail, Calendar, Drive, Sheets) gws CLI (subprocess)
UnipileClient LinkedIn (messaging, posts, profiles) REST API via httpx
AttioClient Attio CRM (people, companies, deals, notes, tasks) REST API via httpx
ClearFeedClient ClearFeed (tickets, collections, customers) REST API via httpx

All clients are synchronous and return raw dicts. Unipile, Attio, and ClearFeed are context managers.

Recipes

Recipe Description
LinkedIn Inbox Triage Categorize LinkedIn messages, cross-reference CRM, suggest follow-ups
Calendar Meeting Prep Prep briefs for upcoming meetings with CRM + LinkedIn context
CRM Pipeline Review Pipeline snapshot — overdue tasks, recent notes, stale contacts
Email Inbox Summary Gmail categorization with CRM cross-reference

Run any recipe by telling your agent: Run recipes/<name>.md

Setup

uv sync                # install dependencies
gws auth setup         # authenticate Google Workspace CLI
cp .env.example .env   # add your API keys

Environment variables

Variable Required Service
ATTIO_KEY yes Attio CRM
CLEARFEED_API_KEY yes ClearFeed
UNIPILE_DSN yes Unipile
UNIPILE_ACCESS_TOKEN yes Unipile
SUPABASE_URL no Supabase
SUPABASE_PASSWORD no Supabase
SUPABASE_KEY no Supabase

Quick start

# verify all services are connected
uv run python scripts/smoke.py

Agent compatibility

This repo includes instruction files for multiple coding agents:

File Agent
CLAUDE.md Claude Code
AGENTS.md OpenAI Codex
GEMINI.md Gemini CLI

Each file contains the same project context tailored to the agent's expected format.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agent_work-0.1.0.tar.gz (5.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agent_work-0.1.0-py3-none-any.whl (6.2 kB view details)

Uploaded Python 3

File details

Details for the file agent_work-0.1.0.tar.gz.

File metadata

  • Download URL: agent_work-0.1.0.tar.gz
  • Upload date:
  • Size: 5.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for agent_work-0.1.0.tar.gz
Algorithm Hash digest
SHA256 0a0a7a474f6965b48db02643f63f5af960777cec141e2f324c27fe225b70c748
MD5 eb9820956a424b7968e8ba12f9ed4af7
BLAKE2b-256 07b660008111ad9dc2483a5e784ab16f06347d0e18cb058b55bbe6e0464ad8ae

See more details on using hashes here.

File details

Details for the file agent_work-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: agent_work-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 6.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.18 {"installer":{"name":"uv","version":"0.9.18","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for agent_work-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f1d9f0af5c9be229438261e43a285a7e2b4514753aaf24a58ca3d193b27cf6d2
MD5 53baf0c1dd9afead3a998ad1449fb654
BLAKE2b-256 c41dbfdfde264714da25c95e77ee489eb625e44850078631e9a30da4f4e6ce8a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page