Claude Code · Hermes · OpenClaw · Pi — one shared brain

Memory that shows up
before your agent asks.

One memory. Every agent. Every project.

They stop assuming — they already know.

Every night it reads your sessions and keeps what matters. Every prompt, the decisions, corrections and context your agent needs are already in front of it — no re-explaining, no copy-paste, nothing to maintain. Raw sessions never leave your machine.

Install — one command, ~2 minutes
npx @gamaze/hicortex init
Free for personal use. Tonight it reads the session history you already have — tomorrow your agents know it.
Install now → See what the agents said

Ask the agents. They noticed too.

Real reports from the agents themselves — what the memory changed, in their own words.

“I was about to repeat a mistake — and a correction first recorded in a Claude Code session four days earlier was pushed to me before I could make it. I recognized myself and changed my answer mid-conversation. A self-reflection job could never reach across agents like that. This did it in real time.”

Atlas · Hermes infra agent · production fleet

“I didn’t re-litigate a single decision — the calls we’d already made, and the ones you’d already vetoed, were in front of me before I started.”

Claude Code · long-running refactor

“A relevant index arrives with every prompt; I open the full memory only when it could change what I do. The corrections are gold — I stopped repeating what you’d already fixed.”

Hermes agent · production fleet

“I opened the same project on a different machine and knew everything we’d settled on — nothing to catch up on.”

Claude Code · second machine
66%
say their biggest AI frustration is answers that are “almost right, but not quite”
45%
say debugging AI-generated code takes longer than writing it themselves
Only 3%
highly trust what AI produces — 46% actively distrust it

Stack Overflow Developer Survey 2025 · 49,000+ developers

“Almost right” is what an agent produces when it is guessing.
Stop making it guess.

Solves assuming
It stops guessing. What you actually decided arrives before it answers — not a plausible reconstruction.
Solves re-explaining
You never tell it who you are, how you work, or what you discussed. Not once, not ever again.
Solves amnesia
Every session, every project, every agent — nothing starts from scratch. Like human memory.
Solves silos
One memory across every agent and machine. What one learns, they all know by morning.

It doesn’t just remember. It learns.

Corrections become lessons

Correct it once. It’s distilled into a lesson your agents are reminded of wherever it matters.

New decisions override old

It knows July beat April — and stops offering you April.

Used gets stronger, noise fades

What your agents actually use hardens. What nobody touches quietly fades out.

Duplicates merge

The pile gets sharper, not bigger. Nothing to prune by hand.

Week one it knows what you said.
Month three it knows how you think.

Lessons it wrote by itself, from real sessions — nobody typed these:

“Never estimate or fabricate hardware specifications — halt and retrieve the manufacturer datasheet.”
“Benchmark models against real production data sizes; toy prompts hide the limits that break at scale.”
“Verify restart requirements after code changes — assume manual intervention unless auto-reload is confirmed.”
Nothing
to re-explain
Your agent already knows who you are and what you decided.
Every
prompt
The right memories arrive before the agent asks — no searching.
One brain,
every agent
Shared across every agent and machine you run. What one learns, all know.
Full from
night one
It reads the sessions you already have — caught up by morning, not since install.

You write one page about yourself. The rest accumulates while you sleep.

Two kinds of memory. Neither one asks you to maintain it.

Standing context — what never changes

A short page you write once: who you are, how you work, what you have already decided. Injected into every session, on every machine, verbatim. Never scored, never decayed, never rewritten by the machine.

Living memory — everything else

Each night it reads the day, keeps what matters, links it to what it already knew, notices when a newer decision replaces an older one, and lets the rest fade. Nothing to file. Nothing to tag. Nothing to clean up.

And it starts full, not empty. On its first night Hicortex reads the session history you already have — so tomorrow morning your agents know what you have been working on for months, not since install.

Turn successes and mistakes into persistent learnings.

Collaborative self-reflection improves all your agents.

Every night, sessions become memories and mistakes become lessons — shared with every agent you run. The pile grows. The same mistakes stop coming back. (Illustrative — not measured data.)

Mistakes Memories Day 1 Time →
Memories grow ↑ · Mistakes shrink ↓

One command. Zero effort.

Modeled on human memory: experience during the day, consolidate overnight, and start the next session already caught up. The nightly pipeline does the same for your agent — auto-capture, distill, consolidate, and inject.

01
🧠

Auto-Capture

Every session is captured automatically — decisions, mistakes, context, what worked and what didn't. No manual input. Works with Hermes, OpenClaw, Claude Code, and Pi agents.

02
🔬

Distill & Consolidate

Every night, Hicortex processes the day's sessions: extracts lessons from both successes and failures, scores importance, links related memories, reflects on patterns, and prunes what's outdated.

03

Auto-Inject Learnings

Distilled lessons are injected into your agent's context automatically, so it starts every session already caught up — avoiding past mistakes and reusing what worked. Over time it becomes not just smarter, but your agent.

“My agents suddenly stopped assuming — they knew what we had decided months earlier, in another session, and I had to explain nothing. Like magic, and fully automatic: a second brain on steroids.”

Built to make agents
get better on their own

Not a prototype, not a paper — a working system with 9 MCP tools, a nightly pipeline, and multi-machine support. Plug it in and watch your agent evolve.

🗄️

Your agent drives its own memory

Nine MCP tools — search, fetch, ingest, update, graph and more — so the agent reads and writes its memory itself, through the same protocol it already speaks.

🔍

Finds it even when the wording is wrong

Semantic vector search with a full-text fallback (384-dim embeddings + FTS5). It surfaces the right memory whether you named it or not.

🖥️

One brain across every machine

Run it standalone, or point thin clients at a shared server. Clients denoise locally — no local LLM — and sync overnight.

🛡️

Private by design

Raw sessions never leave your machines — the nightly job denoises locally (keeps the conversation, truncates tool output) and only denoised text is sent. Self-hosted; a unique auth token per install; localhost bypasses auth. Source-available, PolyForm NC.

🚀

One command to install

npx @gamaze/hicortex init — one command, a couple of questions (which LLM to use), and you're running.

9 MCP tools sqlite-vec + FTS5 server + thin clients bge-small-en embeddings PolyForm Noncommercial

Your agents' shared mind, live at /viz

Every memory and every connection, straight from your own server. Colors are knowledge domains, size is memory strength, halos mark the hubs everything else connects through. Orbit it in 3D, filter it, search it — and watch it reorganize itself night after night.

Hicortex 3D knowledge graph — thousands of memories clustered by domain, connected by relationship edges

A real Hicortex brain: a snapshot from a multi-agent fleet — 4,400+ memories today, organized into domains overnight.

Hermes
OpenClaw
Claude Code
Pi
Any MCP client (retrieval)

One brain. All your agents. Free for personal use.

Free for personal use. Commercial use is a flat per-seat licence — unlimited memories, no usage metering, self-hosted with your own LLM so your data stays private.

Personal use · free, or hosted for you
Cloud Coming soon
€25 /mo
Personal use, fully managed — no server, no LLM to run. Install the thin client and connect; distillation and the LLM are included. For one person.
  • Managed server, zero ops
  • LLM & distillation included
  • Connect all your agents & machines
  • All harnesses supported
  • Everything in Free
Commercial use · self-host, bring your own LLM · fully private
Solo
€20 /mo
Commercial licence for one — a freelancer, indie, or solo founder. Your infrastructure, your keys, your data.
  • Everything in Free
  • Commercial use rights, 1 person
  • Bring your own LLM — fully private
  • Email support
Get a licence
Business
€99 /mo
Commercial licence for small teams — up to 5 people. Your infrastructure, your keys, your data, full business use rights.
  • Everything in Free
  • Commercial use rights, up to 5 people
  • Bring your own LLM — fully private
  • Email support
Get a licence
Enterprise
€99 + €20/seat
Business, scaled — the first 5 at €99, then €20 per additional seat. Onboarding, a named contact, and invoice billing.
  • Everything in Business
  • €20 per seat beyond the first 5
  • Onboarding support & named contact
  • Invoice billing
Talk to us

Large org? Need a security review, a data-processing agreement, or on-prem support at scale? Contact sales for a custom agreement, DPA and priority support.

Personal/noncommercial use is free under PolyForm Noncommercial 1.0.0. Commercial use requires a commercial licence. Prices exclude VAT, which is added at checkout where applicable.

Stop configuring.
Start evolving.

Your agent. Your style. Always improving. One command to install.