# Ekai Labs

> Ekai Labs builds the context curation layer for long-running AI agents. Our thesis: the context problem isn't memory, it's curation. Contexto, our first rail, decides what an agent sees at every step, what stays, what's compacted, and what gets pulled back when it matters.

Use llms-full.txt for the complete Ekai Labs overview plus the full Cognitive Tenants manifesto in a single file.

## Positioning

- Category: context infrastructure for AI agents
- Wedge: in-session context curation (not cross-session memory)
- Preempts: bigger context windows (a bigger window doesn't fix compaction loss)
- Roadmap: sub-agent scoping (next), multi-agent context handoff (after that)

## Products

- Contexto — a context engine for AI agents. Curates what the model sees and persists constraints through compaction. OpenClaw plug-in today, provider-agnostic in design. Repo: https://github.com/ekailabs/contexto — docs + architecture: https://getcontexto.com

## Writing

- Manifesto: https://www.ekailabs.xyz/manifesto — Cognitive Tenants: A Manifesto for Sovereign Intelligence
- Technical blog: https://getcontexto.com/blog — architecture writeups and engineering notes

## Community

- LobsterPod — builder meetups in six cities (Malaysia, Singapore, Vietnam, Bangalore, Shanghai, Toronto). https://lobsterpod.net
- Discord: https://discord.com/invite/5VsUUEfbJk

## Pages (ekailabs.xyz)

- [Home](https://www.ekailabs.xyz/): parent-company thesis page, links to manifesto, Contexto, and LobsterPod
- [Manifesto](https://www.ekailabs.xyz/manifesto): full Cognitive Tenants manifesto with bridging paragraph explaining why Contexto is the first layer

## Contact

- Email: s@ekailabs.xyz
- X (parent): https://x.com/ekailabsxyz
- X (product, Contexto): https://x.com/getcontexto
- LinkedIn: https://www.linkedin.com/company/109615134