View All Companies
Sovant favicon

Sovant

Sovant is a governed, enterprise-ready AI memory layer that enables apps, chatbots, and agents to remember context across chats, sessions, and models, allowing AI systems to retain safe, governed, and explainable memory.

Visit Website

Latest Updates

kopi

kopi

February 10, 2026

Big update: finally something concrete to try!! (Claude Code MCP)

I’ve been tightening Sovant around a single idea: **Governed memory for AI systems. **

That means memory that is:

  • explicit (written intentionally, not auto-captured)
  • scoped (per repo/project)
  • inspectable and editable
  • with a clear lifecycle (create, update, delete)

To make this easy to experience without building an app, I’ve just shipped a Claude Code MCP integration.

If you use Claude Code, you can install a small local MCP adapter that lets Claude:

  • write memory to Sovant
  • recall memory later (scoped to your repo)
  • update or delete memory

The MCP runs locally. Memory is stored in Sovant (cloud) using your API key. No magic memory. No auto-capture.

Install is just 2–3 minutes: 👉 https://sovant.ai/docs/mcp

If you try it, I’d really appreciate blunt feedback, especially:

  • when memory should or shouldn’t be written
  • whether scoped recall actually reduces confusion
  • what feels unnecessary or annoying

Building this slowly and trying to get the foundations right. Happy to answer questions here.

— Henry

kopi

kopi

January 29, 2026

Heads up / early signal

I've been building Sovant as a developer-focused AI memory layer, but am now experimenting with opening it up to non-developers as well, for people who want an AI that remembers customers, decisions and context without thinking about prompts or setup.

No launch or signups yet, and still early. Just exploring whether this is actually useful outside dev circles.

I'll share more once it's ready to be tested!

Thanks.

-Henry

kopi

kopi

January 12, 2026

January Update (Quick one)

Quick check-in after a slow holiday season.

Over the past couple of weeks I've just been tightening Sovant's "governed memory" experience:

  • shipped thread-scoped memory + cleaner schemas (so memory stays in the right bucket)
  • updated the SDKs (TypeScript + Python) with full threads support and published them
  • improved the demo chat so you can inspect which memories were recalled per turn and ability edit memories inline

Next focus for Q1 is the boring but necessary stuff: billing/subscriptions + smart capture (assisted memory suggestions, but still human-approved) + onboarding so a dev can integrate in ~10 minutes.

If anyone here is building infra/devtools or doing B2B SaaS sales, would love to compare notes on what's working.

Thanks!!

— Henry