Trusted by 2000+ Enterprises

IntelligenceDesigned To Evolve

Build applications that reason, adapt and collaborate using a modular AI platform designed for production.

One platform, six layers

Dual-engine gateway

Groq for fast agent calls, Gemini for long documents. Models are auto-detected and failover is automatic.

Hybrid GraphRAG

Vector search plus a temporal knowledge graph, so answers cite sources and follow how facts changed.

Agent swarm

Compliance, security, FinOps and architecture agents plan, use tools and check each other.

Vision

CNN feature maps for diagrams, layouts and telemetry heatmaps. Try it in the console.

Zero-trust security

Post-quantum key exchange, mTLS, encrypted vault, sandboxed scripts and audit logs.

MCP ready

Connect Claude Desktop or Cursor to query graph state and run pipelines.

How a request flows

1. Edge

Nginx serves the site and applies security headers.

2. Guard

FastAPI filters injection, redacts personal data and rate-limits by IP.

3. Retrieve

TF-IDF today; Qdrant and Neo4j in the full build.

4. Route

Groq or Gemini answers. If one fails, the other takes over.

Built with

AI

Groq, Gemini, LangGraph, PyTorch, Qdrant, Neo4j.

Backend

FastAPI, Pydantic, httpx, Fernet vault, hash-chained audit.

Delivery

Docker Compose, Kubernetes with autoscaling, GitHub Actions CI and Pages.

Roadmap

Zero-knowledge proofs, Wasm sandbox, semantic cache, JWT roles.

Security by design

Keys stay yours

Browser keys are held per tab by default and sent only to Groq or Gemini. With the backend, keys live in server environment variables.

Strict CSP

The site can only call the two AI providers and your own API. No third-party trackers or analytics.

Guardrails

Prompt-injection filter, email and phone redaction, input caps and per-IP rate limits.

Tamper-evident audit

Every swarm and MCP action is written to a SHA-256 hash chain you can verify.

Hardened containers

Non-root, read-only filesystem, no privilege escalation, Kubernetes seccomp profile.

Honest limits

Zero-knowledge proofs, Wasm sandboxing and JWT roles are on the roadmap, not shipped. See SECURITY.md.

Frequently asked

Where do my API keys go?

Straight from your browser to Groq or Gemini, or to your own backend if you set a Backend URL. Never to us.

Is it free?

The code is MIT licensed. Groq and Gemini offer free tiers, so you only need free keys. Quotas apply.

Which models does it use?

It reads the live model lists from Groq and Gemini and picks a current general model, so it keeps working when providers retire models.

What data is collected?

None by this site: no cookies, no analytics. Your messages go to the AI provider you configured.

Can I self-host it?

Yes. Clone the repo and run docker compose up --build. Kubernetes manifests are included.

Is it ready for sensitive data?

It has real safeguards, but the roadmap items above are not built. Review it against your own requirements before using confidential data.

Get in touch

Questions, feedback or collaboration: Aetheris AI is designed and built by Nikhil Chary Sriramoju.