Agnus is a cloud IDE with a real multi-agent loop. Claude plans. DeepSeek or Codex writes the code. Every action streams live — nothing happens behind your back.
// src/app/page.tsx - ConvoOps dashboard entryimport { Suspense } from 'react';import { DataTable } from '@/components/DataTable';import { requireAuth } from '@/middleware/jwt';export default async function DashboardPage() { const session = await requireAuth(); if (!session) throw new Error('unauthorized'); const rows = await loadConversations({ userId: session.id, limit: 50, expand: ['tags', 'lastMessage'], }); return ( <main className="min-h-screen px-8 py-10"> <h1 className="text-3xl font-semibold">Conversations</h1> <Suspense fallback={<Spinner />}> <DataTable rows={rows} /> </Suspense> </main> );}// TODO(claude): rate-limit error toastsSign up and your actual code runs in a live cloud sandbox.
How it works
Link one or more GitHub accounts. Each project picks its own. Personal and work repos stay separate. No long-lived tokens — access is minted fresh per operation, expires in one hour.
8 real scaffolds: Next.js, Vite, Express, FastAPI, Supabase full-stack, Static HTML, Mobile (Expo), or Blank. Or clone directly from any GitHub repo you have access to.
Describe what you want. Claude plans and delegates. DeepSeek or Codex writes the code. Every tool call, every file diff, every approval request streams live — nothing happens behind your back.
A CI gate runs your tests before every push. Deploy to Railway or Vercel in one click, gated by that same test pass. The Scribe writes an EU AI Act compliance record after every run.
The multi-agent loop
Four roles. Every run. The Manager plans and delegates. The Worker writes the code. The Reviewer checks every delegation before it lands. The Scribe records everything. You approve before anything touches your repository.
Plans · Delegates · Decides
The Manager — always Claude — reads your request, breaks it into steps, and delegates each one to the Worker. It owns the strategy, decides the order, and calls for a Reviewer pass before anything lands. It thinks. It does not write code.
Writes · Edits · Executes
The Worker receives a specific task from the Manager and writes the code. It applies file edits, runs terminal commands, and reports back. You watch every step stream live in the Decisions panel — every file change, every shell command — before anything is committed.
Checks · Flags · Approves
When enabled, the Reviewer intercepts every Manager-to-Worker delegation before it runs. It checks the proposed task for correctness, scope, and risk — then approves it, revises it, or sends it back. You choose which model plays Reviewer and whether it runs at all.
Records · Flags · Audits
The Scribe cannot be disabled. After every agent run it writes an EU AI Act compliance record: what actions were taken, which files were touched, and a machine-parsed RISK: yes/no verdict. It is not a feature you turn on. It is the foundation everything else builds on.
See everything the Scribe recordsSupported providers
Bring your own key. Use any model you need.
Claude Sonnet · Haiku · Opus
GPT-4o · GPT-4o mini · Codex
DeepSeek-V3 · DeepSeek-R1
Gemini 1.5 Pro · Gemini Flash
Llama 3.3 70B — fast inference
Any model on OpenRouter
Point to any endpoint you control
The actual Claude Agent SDK — same engine as Claude Code
Built-in modes
Claude plans. DeepSeek or Codex writes. The classic loop — coordination and execution split across two models.
Claude handles the full task end to end without delegating. Best for complex reasoning tasks.
DeepSeek runs the full task. Fast, direct, no coordination overhead.
Set your own system prompt, pick any provider, attach any tools. Add skills — reusable knowledge blocks — to define what the agent knows.
EU AI Act compliance
The Scribe is a dedicated agent that runs automatically after every session, using a fixed hidden prompt you cannot change. It writes a compliance record — not a summary — because this is what Article 12 of the EU AI Act requires deployers to keep.
Each record is hashed and that hash is embedded in the next record. Tamper with any entry and every subsequent hash breaks — structurally, not by claim. Verify the full chain in one click, or paste any hash to trace its position forward and back. Reverting a run creates a new chain entry; nothing is ever deleted or rewritten.
Each entry hashes the one before it. Break the chain and you know exactly where.
Weekly and monthly compliance statements are generated automatically — like bank statements. Delete the project and the statements remain. The audit trail belongs to you; it does not disappear with the code.
The Scribe is the implementation. Every run produces a timestamped, hash-chained record of what the system did. Automatically. No manual logging required.
Commit and push require explicit approval. Every agent tool call streams live. You can halt, revert, or redirect at any point. The system does not proceed without you.
The compliance dashboard shows real numbers — not claims. Risk flags, statement coverage, revert history. The Decisions panel is your documented record of oversight.
Agnus is classified as a minimal-risk AI system under the EU AI Act — formally stated, not assumed. The Scribe exists so you have proof when someone asks.
The editor
Monaco — the VS Code editor engine — running against a real e2b cloud sandbox. Not a mock. Not a textarea. Every file you edit runs in a live microVM, and every agent turn is snapshotted so you can always go back.
Source control & deploy
Real git. Real CI. Real deploys. The GitHub App grants access to specific repos only — not your entire account. Tokens expire in one hour. Nothing persists longer than it needs to.
Security
Agnus does not have a shared operator key that all users draw from. You bring your own. We encrypt it with AES-256-GCM. We never see the plaintext. We never pass it between users.
Settings → Permissions shows this policy in plain language. Settings → Report lists every blocked attempt, searchable by project and agent.
Usage & billing
Every token, every job, every dollar — broken down by agent and by project. The Scribe's own DeepSeek spend is tracked separately so the total is never understated. A hard monthly cap stops new runs the moment the limit is hit.
Pricing
Bring your own AI provider keys — we enforce your budget, we don't mark up your tokens.
Free
$0
forever
Pro
$29
per month