Best Open-Source GTM Skills, Plugins & AI Agents (Updated Weekly)
Last updated: September 11, 2026. Reviewed weekly. If you're picking three open-source GTM tools today: OpenSEO for content and search (a genuinely MIT self-hostable replacement for Semrush), GTM Skills by Prospeda for outbound (the only "GTM agents" repo we found that contains a working MCP server rather than instructions), and Crawl4AI for research (Apache-2.0, runs on your machine, no vendor key).
Content
7 listedPostiz
35,709★ · AGPL-3.0A full Next.js/NestJS app with workers; schedules and publishes across 20+ channels. The most mature product here, but AGPL makes embedding it in a closed product legally awkward.
Open on GitHub →OpenSEO
18,360★ · MITThe only tool here that replaces an expensive incumbent — Semrush, Ahrefs — with a genuinely MIT-licensed application you can host yourself, and it ships an MCP server so an agent can call it as well as a human. The honest limitation: the app is free, the data isn't. You bring a paid DataForSEO key, so "free" ends at the API boundary.
Open on GitHub →Mixpost Lite
3,686★ · MITSelf-hosted social scheduling, full Laravel app. Not pushed to since March 16 — five months and twenty-six days, four days inside our removal window.
Open on GitHub →AI Marketing Skills
3,518★ · MITCommunity marketing skill pack for AI agents — prompts and playbooks more than a full product.
Open on GitHub →SerpBear
2,073★ · MITSelf-hosted rank tracker (MIT). Useful SEO monitoring; check last-push date before you depend on it.
Open on GitHub →Outbound
10 listedTwenty
56,594★ · unresolved (AGPL-3.0 plus enterprise files is the claim)Most actively developed open CRM here; model an event as a custom object. Still a sales CRM underneath.
Open on GitHub →Listmonk
23,370★ · AGPL-3.0A compiled Go binary that will push hundreds of thousands of emails.
Open on GitHub →Mautic
10,489★ · no assertion (GPL-3.0 claimed)Mature PHP marketing automation platform for email and campaigns when you outgrow a plain newsletter tool.
Open on GitHub →Cold Outbound Skills
701★ · MITlast pushed August 18. Genuinely executes: 59 TypeScript scripts. Also ships a bundled "12M US businesses" Google Maps scrape — a provenance and compliance question you inherit on install.
Open on GitHub →gtm-agents
399★ · Apache-2.0Large markdown GTM library with little executable code — treat as playbooks, not automation.
Open on GitHub →Research and enrichment
9 listedThat's the pattern across this whole bucket: the open-source client is real, the data behind it is paid. Exa's MCP server is MIT and returns nothing without a key. Firecrawl's MCP server defaults to the paid cloud. Aero's skills route every enrichment through the proprietary Deepline CLI. None of that is dishonest — but if you're budgeting a GTM stack, the licence column is not the cost column.
Firecrawl
179,063★ · AGPL-3.0Firecrawl is more polished, but its self-hosted path is deliberately second-class to its paid cloud. Honest limitation on Crawl4AI: it gives you extraction, not identity resolution. It will not turn a domain into a verified contact, and nothing free will.
Open on GitHub →browser-use
114,194★ · MITBrowser automation framework agents use to research pages like a human operator.
Open on GitHub →Crawl4AI
82,160★ · Apache-2.0Apache-2.0, and it runs entirely on your machine with no vendor key and no hosted dependency — the only entry in this group with zero commercial chokepoint. Firecrawl is more polished, but its self-hosted path is deliberately second-class to its paid cloud. Honest limitation on Crawl4AI: it gives you extraction, not identity resolution. It will not turn a domain into a verified contact, and nothing free will.
Open on GitHub →GPT Researcher
29,413★ · Apache-2.0Autonomous research agent that produces sourced reports from the open web.
Open on GitHub →Firecrawl MCP Server
7,435★ · MITMCP wrapper around Firecrawl so agents can fetch clean page content — often defaults to the paid cloud path.
Open on GitHub →Analytics
4 listedWatch the licence details here. Metabase's repository is mixed. Matomo's core is GPL but many of the attribution and funnel features people actually want are paid premium plugins, so the free build is thinner than it looks.
Metabase
49,199★Open BI/analytics for founder dashboards — AGPL with separate commercial licensing on some parts.
Open on GitHub →PostHog
39,744★The only entry that answers the whole GTM measurement question — funnels, conversion, retention, session replay — in one MIT-licensed system you can run yourself. Honest limitation: self-hosting at real volume means operating ClickHouse and Kafka. That's an engineering commitment, not a docker-compose afternoon, and PostHog itself steers most users to their cloud for exactly that reason.
Open on GitHub →Dub
24,723★ · AGPL-3.0Open-source link shortener with analytics — useful when you want owned attribution instead of bit.ly.
Open on GitHub →Matomo
21,855★ · GPL-3.0Self-hosted web analytics (GPL) — privacy-friendly alternative to Google Analytics for founder sites.
Open on GitHub →What didn't make the list
n8n — the most-used automation tool in GTM full stop, and it fails on licence, not quality. The Sustainable Use Licence is fair-code and restricts commercial use. It isn't open source, and calling it that has become routine. RudderStack — relicensed to Elastic License 2.0, not OSI-approved. SalesGPT — MIT, real runtime, last pushed September 2024. PostHog MCP — official and useful, last pushed January 2026, misses the six-month bar by two months. hansdekker.ai skills — real and free, but no repository, no licence and no source to inspect; free to use is not the same as open source. HubSpot and Apollo MCP servers — neither has verifiable open source. theHarvester — no LICENSE file, and OSINT email harvesting carries terms-of-service exposure we won't point founders at.
How the star counts work, and why they were stale for two weeks
They come from GitHub, exact and never rounded — rendered page labels return materially stale numbers, one repo showed 266 against 392. The staleness had a specific cause: GitHub's unauthenticated REST API allows 60 requests an hour, and this page sits fourth in a four-page audit, so the quota was gone before its turn twice running. The fix, found this week: every repository page embeds its own exact figure in the HTML as `"stargazerCount":