# Hicortex
**Category:** ๐ง Knowledge & Memory
**Repository:** https://github.com/gamaze-labs/hicortex
**Views:** 0
**Installs:** 0
**Upvotes:** 0
**Directory Page:** https://allmcps.com/mcp/hicortex
## Description
Shared fleet memory for AI agents โ what one agent learns, the whole fleet knows.
## Claude Desktop Quick Installation
Heuristic fallback โ verify the package name and runner against the repository README before running it. Uses `npx` (confidence: low):
```json
"mcpServers": {
"hicortex": {
"command": "npx",
"args": ["-y","hicortex"]
}
}
```
## Documentation & README
# Hicortex โ AI Fleet Memory
[](https://glama.ai/mcp/servers/gamaze-labs/hicortex)
[](https://www.npmjs.com/package/@gamaze/hicortex)
[](https://www.npmjs.com/package/@gamaze/hicortex)
[](LICENSE)
[](https://nodejs.org)
**Shared memory for AI agents โ it corrects itself overnight, and what one agent learns, the whole fleet knows.** One memory across every agent, every project, every machine โ they stop assuming and start knowing.
- **One brain, every harness** โ Claude Code, Hermes, OpenClaw, Pi, OpenCode, and any MCP-compatible agent share the same memory.
- **Pushed, not pulled** โ in every supported coding agent, a compact recall index is injected on *every prompt*, so the decisions, corrections, and context an agent needs are already in front of it. No re-explaining, no copy-paste, nothing to maintain. **Zero LLM calls per turn** โ no API cost or rate-limit hit from recall.
- **Consolidates overnight** โ each night it reads the day's sessions, distills what matters, and turns it into Learnings, links, and a knowledge graph.
- **Local-first** โ raw sessions never leave the machine; only distilled memory is stored.
## Install
```bash
npx @gamaze/hicortex init
Claude Desktop: one "yes" during init.
```
Auto-detects your environment, configures one LLM (Ollama, the Claude CLI, or an API key), installs a local daemon (launchd on macOS, systemd on Linux), and registers MCP tools with Claude Code.
For multi-machine setups, point thin clients at a shared server โ no local DB or LLM on the clients:
```bash
npx @gamaze/hicortex init --server https://your-server.example.com
```
`init` auto-detects the other harnesses and installs their clients: a Pi extension (`~/.pi/agent/extensions/hicortex.ts` โ pushed recall, identity + lessons, the ten tools; or copy `pi-extension/hicortex/index.ts` there manually), an OpenCode plugin (`~/.config/opencode/plugins/hicortex.ts` โ the same trio; or copy `opencode-plugin/hicortex/index.ts` there manually), the Hermes plugin, and the OpenClaw plugin. [pi-mcp-adapter](https://github.com/nicobailon/pi-mcp-adapter) remains a generic MCP escape hatch for any harness (verified against the SSE endpoint) โ Pi no longer needs it. See the [install docs](https://hicortex.gamaze.com/docs/installation).
## How it works
```
CAPTURE (nightly) CONSOLIDATE (nightly) RECALL (every prompt)
sessions โ denoise score ยท reflect ยท link a compact index of
โ POST /distill decay ยท dedup ยท supersede relevant memories is
(one model, all phases) pushed into the prompt
โ full text lazy-loaded
```
Memories strengthen when agents use them, fade when they don't, and link to related ones automatically. Retrieval is hybrid BM25 + vector search โ zero-LLM at query time.
The first nightly run captures the last 7 days of sessions by default (not your entire history) โ run `hicortex nightly --recapture-window ` once to import more.
## Features
- **Per-prompt recall push** โ relevant memory lands in context every turn; the agent fetches full content with `hicortex_get` only when it needs it.
- **Memory analytics** at `/dashboard` โ growth, recall adoption, and a nightly digest of what was learned.
- **Knowledge graph** at `/viz` โ memories clustered by domain, connected by relationship edges.
- **Domains & tags** โ multi-tag classification with a configurable vocabulary; your categories drift with your data.
- **Learnings from reflection** โ nightly reflection extracts general, reusable Learnings, not just Experience logs.
- **Self-correcting store** โ every night, stale facts are rewritten in place with dated provenance; near-duplicates resolve into one (verbatim copies kept free, merges recoverable); superseded decisions are demoted, never re-surfaced. No zombie memory.
- **Unprompted by design** โ coding agents get recall injected via hooks; instruction-capable clients (Claude Desktop, Cursor-class) get standing instructions, so memory is used without being asked. Plain MCP clients keep full search.
- **Self-calibrating** โ recall, decay and merge boundaries report their own statistics; tuning is measured, never guessed.
- **Standing context layer** โ hand-edited "who you are / how to work" Markdown, injected every session, never decayed.
## MCP
Nine MCP tools โ `hicortex_search`, `hicortex_get`, `hicortex_recent`, `hicortex_ingest`, `hicortex_lessons`, `hicortex_index`, `hicortex_graph`, `hicortex_update`, `hicortex_delete` โ plus a `/learn` skill to save explicit learnings. [Full reference โ](https://hicortex.gamaze.com/docs/)
## Stack
TypeScript ยท Node.js 20+ ยท SQLite + sqlite-vec + FTS5 (semantic + full-text in one DB) ยท ONNX embeddings (bge-small-en, CPU) ยท MCP over HTTP/SSE ยท one configurable LLM (Ollama, Claude CLI, or any OpenAI-compatible endpoint).
## Development
```bash
git clone https://github.com/gamaze-labs/hicortex.git
cd hicortex
```
[AGENTS.md](https://github.com/gamaze-labs/hicortex/blob/HEAD/AGENTS.md) at the repository root defines the machine-checkable verification contract. "Done" means the full command chain exits with code 0. The contract mirrors what CI runs. Contributors โ human or agent โ run it before claiming work complete.
Contributions welcome โ see [CONTRIBUTING.md](https://github.com/gamaze-labs/hicortex/blob/HEAD/CONTRIBUTING.md).
## Links
- **Website:** [hicortex.gamaze.com](https://hicortex.gamaze.com)
- **Docs:** [hicortex.gamaze.com/docs](https://hicortex.gamaze.com/docs/)
- **Changelog:** [CHANGELOG.md](https://github.com/gamaze-labs/hicortex/blob/HEAD/CHANGELOG.md)
- **npm:** [@gamaze/hicortex](https://www.npmjs.com/package/@gamaze/hicortex)
- **Issues:** [gamaze-labs/hicortex/issues](https://github.com/gamaze-labs/hicortex/issues)
- **Security:** [SECURITY.md](https://github.com/gamaze-labs/hicortex/blob/HEAD/SECURITY.md)
## License
Personal and noncommercial use is free under the [PolyForm Noncommercial License 1.0.0](https://github.com/gamaze-labs/hicortex/blob/HEAD/LICENSE). Commercial use requires a per-seat license โ see [hicortex.gamaze.com](https://hicortex.gamaze.com).