Products

Two things, built on the same research.

An agent that does the work, and the memory layer underneath it. They are useful separately and they are designed to compose.

0xCopilot 

Available

desktop agent · open source · macOS & Windows

A local-first desktop agent. Give it an outcome and it plans the work, moves through your files and connected tools, and stops for your approval before anything important leaves the building.

Runs where your work is

Files, spreadsheets, connected services. Not a chat box that hands you instructions to carry out yourself.

Approval gates

Anything consequential stops and waits. You see the action before it happens, not after.

Replayable runs

Every run is a record you can re-open, inspect step by step, and hand to someone else.

Your keys, your machine

Bring your own provider key. Nothing is routed through us.

Source

Open

Keys

BYOK

Platforms

macOS · Windows

copilot.kleosresearch.xyz ↗

Kaleidoscope 

In development

memory system · signed native binary · macOS first

Scattered fragments of work, composed into one bounded view an agent can be handed. A decision you make in one tool is invisible to the next one — Kaleidoscope is the store that sits underneath all of them.

Local

The evidence store never leaves the machine. It is the most sensitive thing in the system.

Harness-neutral

One store, read by whichever agent you happen to open. Adapters rather than lock-in.

Bounded

The compiler chooses what to carry forward before the model is called, and records why.

Inspectable

A memory you cannot audit is a memory you cannot trust. You can see exactly what was carried.

Source

Proprietary · signed

Planned adapters

0xCopilot · Claude Code · Codex · Cursor

Status

Not yet released

memory.kleosresearch.xyz ↗

How they fit together

0xCopilot is an agent. Kaleidoscope is what an agent remembers. You can run the agent without the memory layer, and you can point the memory layer at an agent we did not build — that is the whole reason it is harness-neutral rather than a feature.

Keeping them separate is a research position as much as a product one. If memory only ever ran inside our own agent, we could not measure whether it helps, because we would have nothing to compare it against.