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
npm i -g aether-agents
aether auth login
aether agent
ollama pull qwen2.5-coder:7b
aether agent --local
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 — 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, 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
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:
aether agent
aether agent --local
aether models
aether resume
Flags you can set when launching the REPL (or pass with an inline task aether agent "<task>" for one-shot autonomous mode):
--local | Local Ollama brain instead of the hosted API. |
--model <id> | Force a model (--model opus, or an Ollama tag with --local). |
--effort <tier> | Budget ceiling: LOW · MED · MAX · ULTRA · CODEPRO. |
--test-cmd <cmd> | Command the verification gate runs (default pytest -q). |
--worktree | Fresh git worktree on an auto-named branch (isolated). |
--repo <owner/name> | 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. Dated patch notes: RELEASE_NOTES.md · 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.
Part of the Aether platform
Aether Agent is the terminal sibling of 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 — 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 · NOTICE.md). PRs and issues welcome — see CONTRIBUTING.md.
Built by Aether AI · aethersystems.net
One terminal. Frontier models or fully local. Your code stays yours.