Persistent memory
Shotgun maintains founder profile, venture state, decision history, open loops, and session notes in files so the cofounder can build context over time instead of treating each session as a reset.
Shotgun
Shotgun is an open-source AI cofounder for solo founders that keeps persistent project memory, helps execute technical work, and drafts writing in the founder’s voice. It runs inside supported AI agents and stores state in files so the same workflow can continue across sessions.
Overview
Shotgun is an open-source project that describes itself as an AI cofounder for solo founders. Its core idea is to turn an AI agent into a persistent operating system that stays with a venture, remembers its history, and helps run product, research, writing, planning, and shipping work across sessions.
The repository frames Shotgun as more than a chatbot or a narrow coding assistant. It uses a file-based memory and workflow system built around SHOTGUN.md, .shotgun skills, a memory vault, and workspace state so the same process can run across supported agents and models.
Core capabilities
Technical execution
The README says it can plan, code, test, ship, and verify work before handing it over, while also logging shortcuts honestly.
Voice-matched writing
It learns from samples of the founder’s writing and drafts launch posts, emails, landing copy, and investor updates in that voice.
Research and market scouting
It can research market questions, competitor pricing, and existing alternatives, then store sourced findings with dates and notes rather than guessing.
Operating rhythm
The system includes daily standups, weekly reviews, one-thing-per-day planning, and loop detection to keep work moving in a structured rhythm.
Reusable workflows and review
Shotgun ships with 24 production-grade engineering skills, specialist personas, autonomous loops, and a virtual panel for review before shipping.
Common use cases
Running a founder memory system
Use Shotgun to keep a running memory of your company, decisions, unresolved tasks, and operating notes so work can resume without rebuilding context each time.
Executing technical work
Use it when you want an AI agent to carry a product from plan to code to tests to a verifiable handoff, with shortcuts and blockers recorded along the way.
Writing in a founder’s voice
Use it to draft launch posts, emails, landing copy, or investor updates that reflect your own writing samples instead of a generic AI tone.
Managing an operating cadence
Use it for recurring planning and review habits such as daily standups, weekly reviews, open-loop cleanup, and one-thing-per-day focus.
Scouting the market
Use it to research competitors, map what already exists, or organize external findings into a dated, sourced file that stays useful later.
Pros and Cons
Pros
- Designed for persistent context across sessions through markdown files and git-backed state.
- Works with a wide set of agents, including AGENTS.md-compatible tools and native wiring for Claude Code, Cursor, Gemini CLI, and GitHub Copilot.
- Covers a broad founder workflow: building, writing, organizing data, researching, distribution, daily planning, and review.
- Includes explicit checklists, self-verification steps, and loop contracts to make the workflow more repeatable.
- Can be injected into an existing codebase without cloning a separate repository, according to the quickstart.
Cons
- Setup is described as a local, file-based workflow, so it is not a simple web app you can start using without installing it into a project folder.
- Some capabilities, such as compliance guidance, market research, and shipping decisions, depend on the quality of the connected agent and the underlying project context.
FAQ
How do you set up Shotgun?
Shotgun is designed to inject its operating system into an existing project folder with a global installer, then run through an agent that supports the AGENTS.md standard or one of the listed native integrations. The repository states that it works with 28+ tools, including Claude Code, Cursor, Antigravity, Gemini CLI, and GitHub Copilot.
What is Shotgun for?
The source describes Shotgun as a persistent, personalized cofounder for solo founders that can build product work, write in the founder’s voice, organize data, research the market, run distribution, and manage a daily operating rhythm. It is meant for a company-of-one workflow rather than a generic chat experience.
Does Shotgun depend on one specific model?
The repository says Shotgun keeps memory, vault, workspace, and learned skills in files, so a new supported model can read the same state and continue. Its operating loop is written as explicit checklists so the behavior is intended to be model-portable.
How does Shotgun handle existing files and updates?
The quickstart notes that the installer does not overwrite existing files and that an upgrade command can update the framework while leaving memory, vault, workspace, and learned skills untouched. The architecture docs also describe state as plain markdown plus git.
What does Shotgun cost?
The repository does not present a traditional hosted SaaS plan for Shotgun itself. The only pricing evidence in the collected sources is GitHub’s platform pricing page, which shows free, team, and enterprise plans for GitHub.
Quick Facts
- Category
- AI cofounder / developer tool
- Product type
- Open-source repository
- Primary users
- Solo founders and company-of-one builders
- Platform
- Local project folders with supported AI agents
- Source domain
- github.com
- Pricing signal
- GitHub offers free, Team, and Enterprise plans; the repository itself does not show a standalone product price
Shotgun Alternativen
SonOf
SonOf connects to your repo and PM tool, audits the codebase and surrounding product context, and turns approved work into shipped tickets with senior engineering review. It is aimed at founders and engineering leaders who need backlog help without hiring a full team immediately.
runevr
runevr is a connected workspace for creative teams that combines boards, media review, chat, recordings, drive, calls, and AI agents in one room-based environment. It is designed to reduce tool switching and keep project context together.
ByteAsk
ByteAsk is a terminal-first AI coding agent for C and C++ that edits repositories and verifies changes with the real compiler, debugger, sanitizers, and tests before showing a diff. It offers a free tier plus paid plans, with editor connectors and zero-retention handling described in the source.
Goldfish
Goldfish is an AI memory app for macOS that helps you reply, write, summarize, and continue using the context already on your Mac. It stores memory locally and writes in your tone.
Lasso
Lasso is an ecommerce product data platform for enriching catalog records, processing supplier files, generating product content, and monitoring competitors. It combines a web app with a REST API, SDK, and MCP server for teams and developers.
CreateOS Sandbox
CreateOS Sandbox is an isolated compute environment for running code and agent workloads inside Firecracker micro-VMs. It is designed for workflows that need machine-level isolation, private networking between sandboxes, and programmatic control through SDK, CLI, or MCP.