Hamster for Gemini CLI

The context layer for Gemini CLI.

Hamster syncs briefs, plans, and team decisions into your repo. Gemini CLI reads them directly — full context on every prompt.

The problem

Gemini is fast. But speed without context is waste.

Every prompt starts from scratch

Gemini CLI has no memory of what your team decided yesterday. You re-explain requirements, constraints, and context every session.

Product context lives outside the terminal

Requirements are in docs, tickets, and Slack threads. By the time you type a Gemini prompt, critical context has been lost or simplified.

No traceability from decision to code

Gemini generates code, but there is no link between what was built and the product decision that prompted it. PRs appear without traceable requirements.

Hamster gives Gemini CLI the full picture.

Write a brief in Hamster, and AI expands it into a full spec. Generate a plan with scoped tasks. The Hamster CLI syncs everything into your repo — Gemini reads the brief, the reasoning, and every team decision from .hamster/ files.

Structured briefs for speed

Gemini CLI excels at fast generation. Hamster briefs give it the structured input to channel that speed into the right output — requirements, constraints, and acceptance criteria included.

Scoped tasks for focused sessions

Hamster decomposes features into well-bounded tasks. Each Gemini session works on a single scoped unit with clear outcomes, reducing hallucinated scope.

Always-on context via the CLI

The Hamster CLI syncs briefs, tasks, and plans into .hamster/ as markdown files in real time. Gemini reads them on every action — no copy-paste, no stale specs.

How teams use Hamster with Gemini CLI

Feature implementation

Before

Write a long prompt explaining the feature. Hope Gemini infers the right scope. Re-prompt when it misses constraints.

After

The Hamster CLI syncs the full brief into your repo. Gemini reads .hamster/ files and builds against the spec your team aligned on.

Multi-model workflows

Before

Use Gemini for speed on some tasks, Claude for reasoning on others. Each tool starts cold with no shared context.

After

Both agents read the same .hamster/ files. Switch models per task without re-explaining context. The brief travels with the repo.

Parallel team execution

Before

Two developers using Gemini on the same feature produce overlapping changes with no coordination.

After

Hamster breaks features into non-overlapping tasks. Each developer picks a scoped task. Gemini sessions run in parallel without conflict.

Give Gemini the context it needs.

Structured briefs and scoped tasks for focused AI-assisted development.

Start building with Hamster