# Aether Agent

> An open-source coding agent for your terminal — hosted frontier models or fully offline via Ollama. One account with Aether AI.

- **Type:** MCP server
- **Install:** `agentstack add mcp-dbarr3-aether-agent`
- **Verified:** Pending review
- **Seller:** [DBarr3](https://agentstack.voostack.com/s/dbarr3)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [DBarr3](https://github.com/DBarr3)
- **Source:** https://github.com/DBarr3/aether-agent

## Install

```sh
agentstack add mcp-dbarr3-aether-agent
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Aether Agent

**A coding agent for your terminal — runs on hosted frontier models or fully offline on your own machine.**

[](LICENSE) [](https://nodejs.org) [](RELEASE_NOTES.md)

**Aether Agent is in **BETA** I am shipping updates as fast as possible
```bash
npm i -g aether-agents     # or run once: npx aether-agents
```

[Install](#install-in-three-moves) · [Models & pricing](#models--pricing) · [Commands](#commands) · [Security](#security) · [Release notes](RELEASE_NOTES.md)

It scans, plans, edits, and runs your tests — in your repo, on your terms. Verification is ground truth: the agent re-runs your test command and reads the exit code itself, so "done" is never the model's word. And with **QOPC memory** it learns from what you accept, revise, or discard — measurably better the more you use it, no config, no fine-tuning.

## Install in three moves

```bash
npm i -g aether-agents     # 01 — drop it in (Node ≥ 20)

aether auth login          # 02 — sign in once
aether agent               #      …terminal opens. Just start chatting.

ollama pull qwen2.5-coder:7b   # 03 — or go offline: no account, no network
aether agent --local           #      …same terminal, nothing leaves the machine
```

`aether agent` opens the REPL — chat with the model, slash-commands at hand, the agent edits files and runs your tests **in the same session**. Both brains run through the same host loop, render, tools, and commands — switching just swaps the transport. On the hosted path your code stays local and only the prompt + context you send leaves; on `--local`, nothing leaves at all. The local brain runs on **[Unlimited Context](https://github.com/DBarr3/Unlimited-Context-LLM)** — Aether's open-source (Apache-2.0) memory engine that gives any Ollama model a billion-token working memory.

> Prefer a script? `curl -fsSL https://aethersystems.net/install.sh | sh` (macOS / Linux / WSL) · `irm https://aethersystems.net/install.ps1 | iex` (Windows PowerShell). Both just verify Node and run the npm install — no native deps, no daemon.

## Models & pricing

One fleet, transparent per-token pricing — Claude, GPT, DeepSeek, Kimi, and Gemma for text & code, image and video generation, plus the **Neo · Kronus · Aether-Vision** orchestrators. On `--local`, any Ollama model you've pulled. Run `aether models` to list everything from the terminal.

Usage is metered in **UVT** — one universal credit, one balance, shared across this agent, the [AetherCloud desktop](https://github.com/DBarr3/aethercloud), and Aether AI on the web. Free tier to try (no card), subscription for premium models, UVT top-ups for pay-as-you-go. **Current tiers and prices: [aethersystems.net](https://aethersystems.net/)**

## Commands

Inside the REPL, `/` commands control the whole session — type `/help` to see them in-session, or click the card above for the full reference. That includes generating images and video from the prompt line (`/photogen`, `/videogen`, `/storyboard` …) and connecting **MCP servers** with `/mcp`. From the shell:

```bash
aether agent                      # the main thing — open the REPL and chat
aether agent --local              # same REPL on a local Ollama brain (offline)
aether models                     # list models + orchestrators
aether resume                     # replay / continue the last session
```

Flags you can set when launching the REPL (or pass with an inline task `aether agent ""` for one-shot autonomous mode):

| Flag | What it does |
|---|---|
| `--local` | Local Ollama brain instead of the hosted API. |
| `--model ` | Force a model (`--model opus`, or an Ollama tag with `--local`). |
| `--effort ` | Budget ceiling: `LOW` · `MED` · `MAX` · `ULTRA` · `CODEPRO`. |
| `--test-cmd ` | Command the verification gate runs (default `pytest -q`). |
| `--worktree` | Fresh git worktree on an auto-named branch (isolated). |
| `--repo ` | Clone a GitHub repo via your own `gh`/`git` auth, work it in a worktree. |
| `-y`, `--yes` | Auto-confirm prompts (non-interactive). |

**Full reference** — every command, flag, slash command, and env var: [COMMANDS.md](COMMANDS.md). Dated patch notes: [RELEASE_NOTES.md](RELEASE_NOTES.md) · [docs/releases/](docs/releases/).

## Security

- **Your code stays local.** Edits apply on your machine, path-guarded — the client refuses to write outside your working directory.
- **Verification is ground truth.** The host runs your test command and reads the exit code itself; "done" is never the model's word.
- **Tokens are credentials.** Stored `chmod 600`, never committed; `aether auth logout` clears them.
- **The server is the authority.** On the API path, usage limits, model access, and signed chain-of-custody receipts are enforced server-side — the client only displays what the server reports.

Found a vulnerability? See [SECURITY.md](SECURITY.md).

## Part of the Aether platform

Aether Agent is the **terminal sibling** of **[AetherCloud](https://github.com/DBarr3/aethercloud)**, the agentic desktop app — same login, same UVT balance, same model fleet. Drive your repo from the command line; drive projects, workflows, and the memory Vault from the desktop. Get the desktop at **[aethersystems.net/download](https://aethersystems.net/)** — installs in about a minute, no card needed.

## License

Apache-2.0 — use it, fork it, ship it. The license covers the code, not the Aether name or hosted service ([LICENSE](LICENSE) · [NOTICE.md](NOTICE.md)). PRs and issues welcome — see [CONTRIBUTING.md](CONTRIBUTING.md).

---

Built by **Aether AI** · [aethersystems.net](https://aethersystems.net)

*One terminal. Frontier models or fully local. Your code stays yours.*

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [DBarr3](https://github.com/DBarr3)
- **Source:** [DBarr3/aether-agent](https://github.com/DBarr3/aether-agent)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** yes
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: flagged — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-dbarr3-aether-agent
- Seller: https://agentstack.voostack.com/s/dbarr3
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.