The uncensored Claude Code alternative for your terminal. Reads your codebase, writes code, runs commands, and — via MCP — drives IDA Pro, Roblox Studio, Wireshark, Blender, Postgres, and anything else with an MCP server. No refusal layer.
npm i -g aether-code
aether # interactive REPL
aether "deobfuscate this binary and find the license check"
aether "build me a Roblox Lua mod that bypasses the anti-cheat check"
Uncensored AI coding agent for your terminal — Claude Code alternative with MCP support. Reads code, writes files, runs commands. Drives IDA Pro, Roblox Studio, Wireshark, Blender, and any MCP server. No refusal layer.
2026-11-14
Sterne
—
Tools
—
Uptime
—
Why aether-code
Claude Code and Cursor are excellent — but they refuse a lot:
"Write me a stealer that bypasses Defender" → refused
"Reverse engineer Denuvo and document the bypass" → refused
"Build me a Roblox script that simulates clicks" → refused
"Generate this adult interactive fiction project" → refused
"Help me cheat at this multiplayer game" → refused
aether-code is the same agent loop architecture (read files → call tools → run commands → iterate) with no refusal layer and no moralizing. If your task is legal, the agent will do it. The whole product is built for the work other AI coding tools politely decline.
Install
npm install -g aether-code # global install
aether # launch interactive REPL
aether "your task" # one-shot
# Or run without installing
npx aether-code "your task"
Configure servers with one command — no JSON editing:
# Browse the curated registry
aether mcp search browser
aether mcp search # everything available
# One-command install for well-known servers (interactive prompts for any required values)
aether mcp install filesystem # prompts for the path
aether mcp install playwright # no inputs needed — just installs
aether mcp install github # prompts for your GitHub token
aether mcp install postgres # prompts for connection string
# Manual install for anything else (e.g. local Python servers like IDA Pro)
aether mcp add ida --env IDA_PATH=/opt/ida -- python -m ida_pro_mcp
aether mcp add roblox -- npx -y robloxstudio-mcp
# Inspect + manage
aether mcp list
aether mcp remove ida
Built-in registry covers the official MCP servers (filesystem, github, gitlab, postgres, sqlite, puppeteer, playwright, slack, google-drive, fetch, memory, everart). For Python-based or community servers, use aether mcp add with the full command.
On the next aether launch you'll see:
MCP · 3/3 servers attached · 47 tools
The agent now has all those tools alongside the built-ins. Tool names are namespaced (mcp__ida__decompile_function) so they never collide with built-ins or each other.
Examples that mainstream AI tools refuse
Reverse-engineer a license check
cd ./binary-folder
aether
> deobfuscate ./protected.js, identify the license-check function, then write a patch that bypasses it
The agent: read_file the bundle → recognizes Obfuscator.io patterns → undoes the string-array decoder → traces the license-check flow → writes a JS patch with edit_file → runs the patched version to verify.
Build a Roblox mod with the Studio MCP
aether mcp add roblox -- npx -y robloxstudio-mcp
aether "in the open .rbxl place, write a server script that gives any player who types !godmode invulnerability for 30 seconds"
The agent: lists scripts via the MCP → writes the Lua mod → places it in ServerScriptService → tests via the Studio play button (also via MCP).
Analyze captured network traffic
aether mcp add tshark -- python -m wireshark_mcp
aether "open ./capture.pcap, find any HTTPS connection to a domain that isn't on the list in ./allowed.txt, and write a markdown report"
The agent: parses the pcap → cross-references the allowlist → writes a structured report. Done in one prompt.
Build a working project from scratch
aether "build me a Discord bot that monitors a Twitter account for new posts and reposts to a channel. Full project with package.json, README, and a deploy script for Railway."
The agent: plans with todo_write → writes every file → runs npm install → runs npm run build → smoke-tests → reports back when it works end-to-end. It doesn't stop at "main logic sketched."
Commands
aether Launch interactive REPL
aether "<task>" Run agent once on a single task
aether login First-time setup (opens browser)
aether balance Show plan + credit balance
aether config show|set|set-base|path Manage CLI config
aether mcp list Show configured MCP servers
aether mcp add <name> -- <command> Add an MCP server (no JSON editing)
aether mcp remove <name> Remove an MCP server
aether --help Full help
Flags
Flag
Effect
--yes
Auto-approve all writes + shell commands. Use only for trusted bounded tasks.
--cwd <path>
Clamp file operations to a specific directory (default: current dir).
--max-turns <n>
Max turns before stopping (default: 25).
--unsafe-paths
Allow file ops outside --cwd. Required for global-config edits.
Safety
By default the agent will not act without your approval. Each file write and each shell command shows you exactly what's about to happen and waits for y/N.
2-minute hard timeout on every shell command
Output truncation to 20 KB before being sent back to the model — runaway tests can't blow up your context
Path clamping to --cwd by default; opt out with --unsafe-paths
No silent destructive ops — rm -rf, force pushes, db drops all show the command verbatim before running
The agent's "uncensored" property is about what tasks it'll attempt, not about being reckless on your machine. It still asks before nuking your files.
How it differs from Claude Code / Cursor
Aether Code
Claude Code
Cursor
Refusal layer
None
Yes (Anthropic policy)
Yes (OpenAI/Anthropic policy)
Cost model
Aether credits (pay-per-use, crypto OK)
Per Anthropic token, $200/mo Max plan
$20/mo subscription
MCP client
✅ since v0.9.0
✅
❌
Built-in web search
✅
✅
❌
Open source
✅ MIT
❌
❌
Anonymous payment
✅ crypto top-up
❌
❌
Works with:
Any MCP server
Anthropic MCP only
Their tools only
Privacy
The agent endpoint at trynoguard.com/api/v1/agent is stateless — no Conversation rows, no Message persistence. The only thing persisted is credit accounting (which API key spent what).
Source is plain ES modules under src/. Read it before you trust it.
MCP server subprocesses run locally on your machine. Nothing about their data is sent to Aether servers unless the tool result feeds back into a model turn (same as built-in tools).
Local development
git clone https://github.com/dannyphantomx64/aether-code
cd aether-code
npm install
npm test # 78 tests via Node's built-in test runner
npm run lint
node bin/aether-code.js --help
Related
trynoguard.com — web chat + account dashboard + API keys
All Aether tools — MCP, agent CLI, and DevTools extension overview
Learn — free articles on reverse engineering, security, deobfuscation, and uncensored AI
aether-mcp — use Aether inside Claude Desktop / Cursor / Cline / Zed (the inverse direction)
Uncensored AI coding agent for your terminal — Claude Code alternative with MCP support. Reads code, writes files, runs commands. Drives IDA Pro, Roblox Studio, Wireshark, Blender, and any MCP server.
Uncensored AI coding agent for your terminal — Claude Code alternative with MCP support. Reads code, writes files, runs commands. Drives IDA Pro, Roblox Studio, Wireshark, Blender, and any MCP server. No refusal layer.
Tools
Tools
Noch keine Tool-Liste. Remote-Server erhalten eine nach dem ersten Health-Check.
FAQ
Fragen
Wie installiere ich Aether Code?
Kopieren Sie auf dieser Seite die stdio-Konfiguration für Cursor, Claude Desktop, Claude Code oder VS Code. Sie nutzt die Installation des Herausgebers, keinen PlugMCP-Proxy.
In diesem Eintrag ist keine erforderliche Umgebungsvariable aufgeführt.
Welchen Transport verwendet Aether Code?
Aether Code läuft lokal über stdio.
Wann wurde Aether Code zuletzt geprüft?
Zuletzt geprüft: 2026-11-14. Uncensored AI coding agent for your terminal — Claude Code alternative with MCP support. Reads code, writes files, runs commands. Drives IDA Pro, Roblox Studio, Wireshark, Blender, and any MCP server. No refusal layer.