whereismyai
zerostack
zerostack is a Rust-based coding agent that executes tasks through a terminal UI with low memory consumption and multi-model support.
Zerostack is a coding agent written in Rust designed for minimal memory usage and high performance. It operates via a terminal interface, offering features like session management, automated prompt chaining, and a customizable permission system. Users interact with the agent through various system prompts such as code, plan, debug, and review, which tailor agent behavior to specific development tasks. The platform supports integration with multiple LLM providers, including OpenAI, Anthropic, and local models via Ollama. It offers extended capabilities through MCP servers and allows connection to editors via the Agent Communication Protocol. For security, it provides optional sandboxing for bash commands using bubblewrap or zerobox.
zerostack at a glance
- Best for: Software engineer
- Runs on: CLI, Linux, macOS, Windows, open source
- Pricing: Free and open source; donations and corporate sponsorships accepted.
- Released: May 2026
- Category: AI coding tool
- Website: github.com/gi-dellav/zerostack
Key features
- Low RAM footprint (~16MB average)
- Multi-provider support including OpenAI, Anthropic, and local Ollama
- Terminal UI with markdown rendering and reasoning visibility
- Configurable permission system with five security modes
- Integrated sandboxing via bubblewrap or zerobox backends
- Persistent memory with daily logs and scratchpad
- Prompt chaining for automated development workflows
- Agent Communication Protocol support for editor connectivity
Use it for
- Automating code planning, writing, and debugging workflows
- Conducting security reviews of codebases
- Navigating documentation through an interactive configuration agent
- Performing codebase exploration using subagents
Companions
Tools that articles about zerostack recommend using with it, each with its job.
- Context7 — Provides up-to-date documentation for AI agents and code editors.
- Ollama — Run local models at zero marginal cost, with code kept on your machine.
- OpenRouter — Access over 500 models and 80 providers through one unified API.
- Daytona — Runs sessions in isolated sandboxes synced to git branches.
- Composio — Equips AI agents with tools, managed user auth, and sandboxes across 1,500+ apps
- Oh My OpenCode Slim — Lightweight multi-agent orchestration and background tasks.
Alternatives to zerostack
- ZeroClaw — Own your AI infrastructure with no subscriptions or cloud dependencies.
- jevgrep — Reduces coding agent costs by providing targeted, relevant repository context.
- Zeron — Manage and control coding agent sessions across multiple devices from one window.
- pstack — Improves AI coding agent outcomes with rigorous workflows.
- OpenCode — Works with 75+ model providers, local models, and existing subscriptions
- BeautifulRust — It improves agent output using guidelines from five major Rust sources.
- Stagewise — Maintain full sovereignty over AI models while running agents in parallel.
- Freebuff — Access multiple coding AI models for free without subscriptions.
- APIStack — Connect AI agents to over 100 tools using one API key or a single MCP endpoint.
- Neptune — It combines a fast native terminal engine with built-in management for AI coding agents.
- Tunr — Deploys agent-built software and shares local dev servers instantly via a single command.
- TanStack AI — Typed options and adapters for every model.
All zerostack alternatives