inertia-ai: a desktop workspace for AI agents. Chat, built-in tools, MCP and OpenAPI integrations, Docker/Daytona sandboxes with a live desktop, routines and memory. Bring your own model and keys.
A desktop workspace for AI agents: chat, tools, sandboxes, routines and memory.
Website and case study · Download · Documentation
inertia-ai (the app itself is called Inertia) is a desktop app for working with AI agents on your own machine. You chat with agents that can read and edit your files, run commands, drive a browser, delegate to sub-agents, use tools from MCP servers and APIs, and work on sandboxed computers with a desktop you can watch. Everything it knows (conversations, agents, routines, memories, settings) is plain files in a folder you choose. You bring your own model provider and API keys; there is no Inertia account or server.
inertia-ai is not related to Inertia.js.
- Chat with agents in four modes: Chat (no changes), Plan (ends with a plan you approve), Autonomous (full tools), and Agent Group (several agents in one conversation). - Any model provider: Anthropic natively, and anything that speaks the OpenAI chat-completions API (OpenAI, OpenRouter, Groq, Together, DeepSeek, xAI, Ollama, local servers, gateways). - Built-in tools: read, write, edit and patch files; search; a shell with background processes; git worktrees; a task list; language-server queries; per-turn snapshots with diff and undo. See docs/tools.md. - Permissions you control: allow/ask/deny rules per tool and per command or path, workspace-wide or per agent, and an approval card showing the exact command or path for everything else. - Agents and sub-agents: agents with their own instructions, model, working folder and permissions; blocking task delegation and a background crew that work
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/nettanvirdev--inertia.html)
Connect AI models to your own computer and MCP tools — with device-side control.
systempromptio/systemprompt-demoAI Governance Infrastructure — open gateway demo. Self-hosted systemprompt.io gateway in a single Rust binary: policy, audit trails, and cost attribution on every AI request, with the Systemprompt Bri
magna-nz/tallybookPrices your Claude Code and Codex sessions from the transcripts on disk, shows what each agent cost over any period, and tells you in plain English what would have been cheaper. CLI, Browser UI and MC
BANG404/openagentA modern, multi-agent desktop AI client built with Tauri, SvelteKit, and Rust.
azimov777/casefileThe task tracker your AI agents keep for each other: every task carries a case file, so the next agent picks up where the last one stopped. MCP server + live board. Self-hosted, one-line install.
Araz0-0dev/am-codeAM Code — agentic coding assistant (VS Code + Windows/Linux/macOS desktop) with your own models, MCP support and a token saver that compresses every request. | دستیار کدنویسی ایجنت با مدلهای خودت
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.