AI agents that
live on your machine.
Pumkin is a local-first agent IDE for developers. Build, run, and audit AI agents using your own Ollama models and your own MCP tools. No cloud. No API keys. No recurring fees.
Real output. Local Ollama. llama3.2:3b. Built-in get_time tool. 1.5s.
What's in the box.
Everything below is built, tested, and shipping in v0.0.1. No roadmap items in this list — what you pay for is what you get.
Native desktop app
Tauri-based installer for Windows (macOS and Linux next). Bundled Node.js — no system dependencies beyond Ollama itself.
Local models via Ollama
Talks to your existing Ollama install. Picks up your installed models automatically. Run llama3.2:3b on 8GB of RAM or qwen3:14b if your machine can handle it.
MCP tools, allowlisted per agent
Connect any stdio or Streamable HTTP MCP server. Pumkin runs each tool through a JSON schema check and per-tool timeout. Tools are namespaced so the model can't accidentally call something it shouldn't.
Per-call approval gate
Mark any tool as 'requires approval' and Pumkin pauses the run, shows you the exact call and args, waits for your green light. Approve once. Deny once. No global trust.
Run history with full event replay
Every run persisted to SQLite. Inspect the model response, the tool calls, the tool results, the timings. Replay anything. Debug what the model actually saw, not what you thought it saw.
Multi-turn conversations
Persistent threads with full context. Ask a follow-up; Pumkin remembers turn one. Same agent, multiple conversations, all logged.
Pumkin is for you if…
- You already run Ollama and you've been wiring agents together by hand
- You don't want your prompts, tool calls, or conversation history leaving your machine
- You're tired of paying $20/mo to five different AI products to do what one local model could handle
- You want to inspect every tool call your agent makes before it runs
- You've used Open Interpreter, AnythingLLM, or LM Studio and wanted them to do more, not less
- You believe a tool you own outright beats a subscription you rent forever
Pumkin is not for you if…
- You don't have Ollama installed and don't want to install it
- You want to chat with one model — Pumkin is for agents that do things
- You need the absolute best model quality — local models can't match GPT-5 on hard reasoning
- You're looking for a no-code product. Pumkin is built for people comfortable in a terminal.
- You expect Mac/Linux support today. Windows first; the rest is on the roadmap.
Honest answers.
Why pay for this when LM Studio and AnythingLLM are free?
Different problem. LM Studio is a model runner — it lets you chat with a local model. AnythingLLM is a RAG product — it lets you ask questions over your documents. Pumkin is an agent IDE — it lets you build named agents with specific tools and audit every call they make. If you've tried wiring agents together by hand using the Ollama API + MCP servers, you know how much glue this saves. The $99 is for the saved weekend of building it yourself.
What do I need installed on my machine?
Just Ollama (free, from ollama.com). Pumkin's installer bundles Node.js and everything else. No Rust, no Visual Studio, no Python. Run the .exe, you're done.
Is the source code open?
Source-available to license holders, but not open-source under a permissive license. That's an intentional choice — Pumkin is a paid product, not a free one. License holders get the full source, can modify it for their own use, can audit every line. They just can't redistribute it.
Mac and Linux support?
Windows installer ships today. Mac and Linux are next — the Tauri shell is cross-platform; the bottleneck is getting the bundled-Node + code-signing story working on each platform. Founding license holders get all platforms when they ship, no upcharge.
What if it doesn't work for me?
30-day refund, no questions, no forms. Email and you get your money back. If you're past 30 days and a major version update breaks your workflow, email anyway — I'm one person and I'll work it out with you.
What about updates?
Lifetime updates for all v0.x releases. v1.0 (when it ships) will likely be a paid upgrade for new buyers, but founding license holders get it free.
Why $99? Why a founding license cap?
Because I want to ship something real and not a Series-A pitch deck. 50 founding licenses at $99 funds the code-signing certs, the macOS/Linux build work, and a year of development. After 50, price goes up — probably to $149 or $199 — and I get to keep building based on actual user feedback rather than guessing.
Who built this?
An indie founder shipping out of Vigo, Spain. Software For Humans. Track record of building, shipping, and supporting small tools. Not a venture-backed startup. Not a side project of a bigger company. Just one person who wanted this thing to exist.
Get Pumkin.
- Windows installer today, macOS & Linux next, all included
- Lifetime updates for v0.x; free upgrade to v1.0
- Full source code for personal use and audit
- Direct email line to me — one founder, real support
- 30-day refund, no questions asked