Can we address the elephant in the room?
Face it, working with coding agents is not ALL fun.
One step back for every two forward is not a productivity boost.
It's a hassle.
Context engineering alleviates the pain, but has you focused on the wrong things.
How does Jumbo help?
Jumbo is a CLI tool that gives your coding agent memory like an... well, 🐘.
It keeps your agent on track, and you focused on what you want to build.
Tracks project details
Important aspects of you project are stored, retrievable, and mutable.
(see below)
Delivers optimized context
Agents receive the context they need to work aligned with YOUR criteria.
Portable
Switch models, or move from CLI to IDE, without interruption. Jumbo stays with you project and knows exactly where you left off.
Easy to use
Two commands and your agent is collaborating with Jumbo.
Extends context windows
Optimal context delivery lets agents work longer.
Automatic
Hooks into your agent session and orchestrates the flow. It just works.
Full control
Jumbo's memories are yours. Stay in control and manage your data directly from the terminal.
Private
All data stays local. Nothing leaves your machine.
Fast
No network calls. No lag. Works instantaneously.
Compatible with all frontier harnesses and models.
What's in the trunk?
Jumbo captures important details about your project as they arise in agent interactions, and serves them back curated when needed.
"Since using Jumbo, I'm only focused on my goals. I define what to build, the agent builds it to my satisfaction, and I move on."
FAQs
What is Jumbo?
Jumbo is an open source command-line tool that helps you manage your coding agents context, so you can focus on what you want to build.
Is Jumbo for context engineering?
Exactly! Jumbo is essentially context engineering with a fraction of the effort required to maintain markdown files and with better results. It works by collecting insights about your project as they arise in your agent workflow and serving context automatically to your coding agent.
Can I control what data Jumbo captures?
Absolutely. You control how you want your agent to interact with Jumbo. Stay in-the-loop by approving each command, or run with pre-approved Jumbo commands for an automated experience.
Is Jumbo going to hijack my agent?
Not at all. Jumbo prescribes an opinionated workflow that you can always bypass. It works alongside your agent to enhance its capabilities.
How does Jumbo ensure privacy?
Jumbo is designed with privacy-first. All data is stored locally on your machine. No data is transmitted externally unless you explicitly configure it to do so.
Which harnesses, agents and models is Jumbo compatible with?
Jumbo is harness, agent and model agnostic. Use any of them, switch between them, and switch back again. Jumbo maintains your project context seamlessly. It's been battle tested with Claude Code CLI, Copilot CLI/VS-CODE-AGENT, Gemini CLI, OpenAI models, Anthropic models, Google models and more. The list will grow as the project matures. [Stay tuned]
Why not just use markdown files?
Jumbo goes beyond static markdown files. It's an immutable event stream—capturing your entire project history, always current and auditable. You stay in your flow, never repeat yourself—only add new information when you need to. Markdown is a snapshot in time, Jumbo is your project's living memory.
How do I install Jumbo?
Installation is simple with npm, just run: npm i -g jumbo-cli.
Is there documentation?
The CLI will guide you in getting started.
In addition, the help command jumbo --help provides a comprehensive overview of all available commands and options.
For a deep dive, see the documentation on GitHub.
Does Jumbo work for teams?
You can try, but will likely encounter conflicts. Jumbo is currently optimized for single developer use. A subscription-based version for teams is under developement[Stay tuned].
Cross my heart and hope to die (a.k.a. Promises)
Jumbo is free and open source for single developer use. Forever.