@gamaze/hicortex 0.20.1 → 0.20.3

package/README.md

@@ -1,10 +1,14 @@
-# @gamaze/hicortex — Self-Learning Memory for AI Agents
+# @gamaze/hicortex — Shared Fleet Memory for AI Agents
 
 <img src="https://raw.githubusercontent.com/gamaze-labs/hicortex/main/docs/dashboard-composition.png" alt="Hicortex dashboard — live screenshot: memory-type composition (episodes / lessons / facts / decisions)" width="800">
 
-Your agents learn from every session — successes and mistakes. Hicortex captures experiences, distills lessons, and applies them automatically. Connect multiple agents to shared memory and they improve together, overnight.
+**Many agents. One shared memory. Wisdom compounds.**
 
-Works with **Hermes**, **OpenClaw**, **Claude Code**, **Pi**, **opencode**, and any MCP-compatible agent.
+Hicortex is shared long-term memory for AI agents. Install once, and every agent you run — Claude Code, Hermes, OpenClaw, Pi, OpenCode, any MCP client — draws on one memory: sessions are captured automatically, distilled into knowledge, decisions and learnings overnight, and a compact recall index is pushed into each prompt in every supported coding agent. What one agent learns, the whole fleet knows.
+
+**Install — one command, ~2 minutes:** `npx @gamaze/hicortex init`
+
+Self-hosted: raw sessions never leave your machine. Zero LLM calls at recall. Free for personal use.
 
 **Website:** [hicortex.gamaze.com](https://hicortex.gamaze.com) · **Docs:** [hicortex.gamaze.com/docs](https://hicortex.gamaze.com/docs/)
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@gamaze/hicortex",
-  "version": "0.20.1",
+  "version": "0.20.3",
   "description": "Persistent agent identity for AI agents \u2014 a hand-edited identity layer, nightly-distilled experience, and lessons injected every session, shared across your whole fleet. Works with Hermes, OpenClaw, Claude Code, Pi, and opencode.",
   "main": "dist/index.js",
   "bin": {