mcpField
H
Hicortex — AI Fleet Memory

Hicortex — AI Fleet Memory

Local
hicortex.gamaze.comMemory & Knowledge3Updated 3w ago
RepositoryVisit website

About Hicortex — AI Fleet Memory

Hicortex is a shared memory server for AI agent fleets, designed for supported coding agents and other MCP-compatible clients. It injects relevant recall into each prompt, consolidates sessions overnight, and keeps raw sessions on the local machine.

Key features

  1. 01Push relevant memory into each prompt
  2. 02Consolidate sessions into learnings overnight
  3. 03Search with hybrid BM25 and vector retrieval
  4. 04Maintain a linked memory graph
  5. 05Track memory use and growth in a dashboard
  6. 06Correct stale and duplicate memories

Use cases

  1. 01Share decisions across agents and projects
  2. 02Recall prior context in coding sessions
  3. 03Turn daily agent sessions into reusable learnings
  4. 04Inspect memory growth and relationships

MCP support

Provides nine MCP tools for searching, retrieving, ingesting, browsing, and managing memories, plus an HTTP/SSE MCP endpoint. Supported coding agents can receive recall through hooks or integrations.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "gamaze-labs-hicortex": {
      "command": "npx",
      "args": [
        "-y",
        "@gamaze/hicortex"
      ],
      "env": {
        "HICORTEX_AUTH_TOKEN": "<HICORTEX_AUTH_TOKEN>",
        "HICORTEX_SERVER_URL": "<HICORTEX_SERVER_URL>"
      }
    }
  }
}
Run commandnpx -y @gamaze/hicortex
Environment variables to set
HICORTEX_AUTH_TOKENSecretBearer token for a remote Hicortex server (server prints it via `hicortex status`). Optional — a local server needs no token.
HICORTEX_SERVER_URLURL of a remote Hicortex server (e.g. https://your-server:8787). Optional — omit for a local server on this machine.

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@gamaze/hicortex0.25.0

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Hicortex — AI Fleet Memory

Hicortex MCP server – quality and maintenance score on Glama

Hicortex dashboard — live memory analytics

npm Downloads License: PolyForm NC Node

Shared memory for AI agents — it corrects itself overnight, and what one agent learns, the whole fleet knows. One memory across every agent, every project, every machine — they stop assuming and start knowing.

  • One brain, every harness — Claude Code, Hermes, OpenClaw, Pi, OpenCode, and any MCP-compatible agent share the same memory.
  • Pushed, not pulled — 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 — no API cost or rate-limit hit from recall.
  • Consolidates overnight — each night it reads the day's sessions, distills what matters, and turns it into Learnings, links, and a knowledge graph.
  • Local-first — raw sessions never leave the machine; only distilled memory is stored.

Install

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 — no local DB or LLM on the clients:

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 — pushed recall, identity + lessons, the ten tools; or copy pi-extension/hicortex/index.ts there manually), an OpenCode plugin (~/.config/opencode/plugins/hicortex.ts — the same trio; or copy opencode-plugin/hicortex/index.ts there manually), the Hermes plugin, and the OpenClaw plugin. pi-mcp-adapter remains a generic MCP escape hatch for any harness (verified against the SSE endpoint) — Pi no longer needs it. See the install docs.

How it works

CAPTURE (nightly)        CONSOLIDATE (nightly)             RECALL (every prompt)
sessions → denoise       score · reflect · link            a compact index of
→ POST /distill          decay · dedup · supersede         relevant memories is
                         (one model, all phases)           pushed into the prompt
                                                           → 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 — zero-LLM at query time.

The first nightly run captures the last 7 days of sessions by default (not your entire history) — run hicortex nightly --recapture-window <days> once to import more.

Features

  • Per-prompt recall push — relevant memory lands in context every turn; the agent fetches full content with hicortex_get only when it needs it.
  • Memory analytics at /dashboard — growth, recall adoption, and a nightly digest of what was learned.
  • Knowledge graph at /viz — memories clustered by domain, connected by relationship edges.
  • Domains & tags — multi-tag classification with a configurable vocabulary; your categories drift with your data.
  • Learnings from reflection — nightly reflection extracts general, reusable Learnings, not just Experience logs.
  • Self-correcting store — 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 — 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 — recall, decay and merge boundaries report their own statistics; tuning is measured, never guessed.
  • Standing context layer — hand-edited "who you are / how to work" Markdown, injected every session, never decayed.

MCP

Nine MCP tools — hicortex_search, hicortex_get, hicortex_recent, hicortex_ingest, hicortex_lessons, hicortex_index, hicortex_graph, hicortex_update, hicortex_delete — plus a /learn skill to save explicit learnings. Full reference →

Stack

TypeScript · Node.js 20+ · SQLite + sqlite-vec + FTS5 (semantic + full-text in one DB) · ONNX embeddings (bge-small-en, CPU) · MCP over HTTP/SSE · one configurable LLM (Ollama, Claude CLI, or any OpenAI-compatible endpoint).

Development

git clone https://github.com/gamaze-labs/hicortex.git
cd hicortex

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 — human or agent — run it before claiming work complete.

Contributions welcome — see CONTRIBUTING.md.

Links

License

Personal and noncommercial use is free under the PolyForm Noncommercial License 1.0.0. Commercial use requires a per-seat license — see hicortex.gamaze.com.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.