mercury-agent vs openinterpreter
AI agents for persistent assistance and terminal coding compared
mercury-agent is a self-hosted assistant for CLI, Telegram, and web use, with memory, scheduling, and approval controls. openinterpreter is a Rust-based terminal coding agent focused on coding workflows, low-cost models, and integrations with editors and agent protocols.

mercury-agent: Run a Permission-Aware AI Agent Across Channels
Mercury is a self-hosted AI agent for CLI, Telegram, and web use, with permission prompts, persistent memory, token budgets, and scheduled tasks. It suits people who want an always-on assistant they can configure and operate locally.

openinterpreter: Run Coding Agents in Your Terminal
Open Interpreter is a Rust-based terminal coding agent designed to get useful results from low-cost language models. It supports multiple agent harnesses and connects to ACP-compatible editors and Codex SDK clients.
| mercury-agent | openinterpreter | |
|---|---|---|
| Language | TypeScript | Rust |
| License | MIT | Apache-2.0 |
| Stars | 3.2k | 68.5k |
| Forks | 341 | 5.9k |
| Last analyzed | Oct 3, 2026 | Oct 3, 2026 |
Key differences
- mercury-agent offers multiple interfaces and persistent assistant features, while openinterpreter focuses on coding sessions in a terminal and compatible editors.
- mercury-agent includes memory, token budgets, scheduling, and Kanban task boards; openinterpreter supports multiple coding-agent harnesses and shared AGENTS.md and skills conventions.
- mercury-agent is written in TypeScript and licensed under MIT; openinterpreter is written in Rust and licensed under Apache-2.0.
- mercury-agent can run as a background daemon with platform service integration; openinterpreter provides native command sandboxing on macOS, Linux, and Windows.
- mercury-agent is aimed at individuals who want a configurable assistant across channels; openinterpreter targets developers integrating coding agents into terminal or editor workflows.
Choose mercury-agent if you…
- need an assistant across CLI, Telegram, and a local web dashboard.
- want persistent memory, scheduled tasks, or Kanban-based task execution.
- need approval controls and folder-level access scoping for agent tools.
Choose openinterpreter if you…
- want a Rust-based terminal agent for coding workflows with low-cost models.
- need to connect an agent to ACP-compatible editors or Codex SDK clients.
- want to switch among supported coding-agent harnesses or use native command sandboxing.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.