Open-source platform for AI-assisted work
Give every task the context it needs.
Perseus adds current workspace context, durable memory, and reviewable records around the model or system you already use.
Local by default. You choose the model, data path, deployment, and permissions.
Token reduction measures content assembly, not provider billing or dollar savings. Retrieval is retrieval-only; throughput is not an SLA.
One platform, three jobs
Keep work moving.
Use one component or all three. Each has a small, reviewable job.
Choose a path
Start where you are.
See the product, the evidence, or the bounded Government workshare.
See where Perseus fits
An enabling component beside the mission system.
Government overview → For a hands-on lookTry Vault demo ↗
Save a decision, find it later, and prepare a short summary.
Open the demo For technical evaluatorsRead the evidence
Numbers, methods, controls, and limits in one place.
See the methods →Open evidence
See the result, then the method.
MemConflict tests changing facts, planted contradictions, and conditional preferences across eight self-hosted configurations.
Macro score in the self-run replication.
18 wrong across 3,750 questions; 1,378 were blank or abstaining (36.7%). Wrong and blank outcomes are counted separately.
Read the eight-provider report ↗Deployment
Run it where the work is.
Local, on premises, private cloud, or disconnected. The program chooses the data, keys, network, and permissions.
See the security boundary →- Data
- Stays in the environment you select for the local path.
- Keys
- You supply and keep the keys used for encryption and services.
- Authority
- The model and host keep their existing permissions. Perseus does not add mission-system authority.