OpenNekoRent the intelligence. Own the context.See a demoOpen source · Apache 2.0
OpenNeko is an open source AI harness built to help run your company. What takes human teams months to do, OpenNeko can automate to deliver instant results. Setup time is days or weeks, not months, and can end up saving a company millions in the first year.
Line 2's critical spare crosses its reorder point tonight.
Primary vendor is 7 days out · 385 units left · drawing ~172/wk
Drafted 2 Actions · Awaiting Approval
Rush the PO to the backup vendor
PO #4471 · arrives before stock-out
Brief the plant lead + maintenance on the ETA
Slack · #maintenance
Approve once, or set a rule and OpenNeko handles it next time.
Made for your operation
Ask them in plain language, or set a watcher that checks on a schedule and flags you when the answer changes.
In production
We built OpenNeko for asset-heavy, regulated operations. The deployments below run in defense technology and global commercial real estate, and the numbers come straight from them.
A defense technology company
Snowflake · CRM
OpenNeko runs on their own network across Snowflake and CRM, spanning 80B+ records: scoring buying intent, flagging accounts before they churn, triaging the custom-quote queue, and keeping critical components in stock. It drafts the next move; the team approves.
A global commercial real estate firm
Azure Data Lake
Their analysts answer clients' questions across hundreds of millions of data points on property research, investment, and performance. Agents now do the legwork: an analyst asks in plain language, OpenNeko queries the full dataset and drafts the insight with its evidence, and the analyst signs off.
Using OpenNeko
Ask anything about your company in plain language. OpenNeko finds the right data, works out the answer, and shows the evidence.
And it watches while you're away: anything urgent lands on your briefing with a response drafted, waiting for your approval. One loop runs it all: observe, understand, decide, act. We call it OUDA.
Line 2's critical spare crosses its reorder point tonight
Caught 2:14 AM · vendor 7 days out · PO #4471 drafted and waiting
A running read on the business. Anything that needs you sits up top.
Under the hood
Each block does one job, and they work better together. Every action you approve teaches the agent how you want things done. The full specs live in the docs.
Architecture
Ask in plain language. OpenNeko's agents break the question down and read your databases through GraphJin, which compiles it straight to SQL and computes the answer where your data already lives.
OpenNeko runs as three tiers, split by trust. A small control plane, the worker, holds your secrets, your database access, and the model gateway. Everything that runs model-written or third-party code runs sandboxed beside it, reaching the control plane through one narrow broker.
Security and Governance
The agent and its plugins run in a sandbox with no access to your keys or your database. Your model's API key never enters it. Run a local model and no data leaves your network.
Your cloud
Deploy into the AWS, GCP, or Azure account your team already uses. Your data stays inside your own perimeter.
On-prem
Self-host on your own server. It needs only Docker, with no virtualization.
Your model
Use any LLM provider, or a local model through Ollama. With a local model, no data leaves your network.
The threat model
The agent reads data and documents you don't control and runs them through a model, so OpenNeko treats it as untrusted code. In most systems that agent holds the most access: the keys, the database, the network. OpenNeko flips that: the agent runs sandboxed, and the worker holds everything.
Say a malicious record fully hijacks the model, and the agent does whatever an attacker wants. Its blast radius is only what it was already given, which is almost nothing.
A fully compromised agent can say things and request actions that still wait for your approval. An uncompromised agent has exactly the same reach, by design.
For builders
The full security model, from sandbox policies and key handling to the audit chain, is in the security docs ↗.
Who built it
Amit Deshmukh
AI Engineer · Creator of AxCrew.dev & OpenNeko · Founder @ Buddhic.ai
linkedin.com/in/amitdeshmukh ↗
Amit has spent the last 20 years working hands-on across all three.
Certified data engineer with years building data systems that handle real volume. The data layer is where OpenNeko earns its trustworthiness.
Deployed AI workflows that added or saved tens of millions to the bottom line. Built agentic systems before agents were a trend.
Security-audited Fortune 500 companies. Knows what breaks in regulated environments and what compliance requires.
Two ways to start
Self-host it in a few minutes on your own infrastructure. Or send us the problem you most want solved, and we'll show you how OpenNeko would handle it.
