This package has been renamed to arkhive-mcp

pip install arkhive-mcp

humane-intelligence 0.1.3 is the final release under this name — it still works, but all future releases ship as arkhive-mcp. ArkHive is the product; #HumaneIntelligence is the movement.

Hosted endpoint, custom agents ($700), and enterprise installs ($2,500+): https://arkhive.dondatabrain.com

---

ArkHive MCP

Local-first governed memory for AI agents, with persistent identity, tamper-evident history, verification, and constraint-aware decisions.

Tell your AI: “Check the ArkHive.”

ArkHive is an open-source Model Context Protocol server for developers and teams that want Claude, Codex, and other MCP clients to retain accountable context across sessions without sending memory to a hosted service by default.

What you get

• Memory that survives the session. Your AI writes what it did and reads it back next time — no blank slate every morning.
• Tamper-evident history. Every record is hash-chained (SHA-256). Edit, delete, or reorder any past record and verification fails — you get evidence of change, not silent rewriting.
• Local-first, no telemetry. The chain is a plain SQLite file on your machine. Nothing is transmitted unless you explicitly opt in.

Verify it yourself — one command, no key

Don't take "tamper-evident" on faith. Run the proof:

git clone https://github.com/sammyboi81/arkhive && cd arkhive
./scripts/verify.sh          # or:  python -m benchmark

It writes a throwaway hash-chained ledger, verifies it clean, then forges one block with a direct SQL edit and shows verification catch it. Real output:

[3] verify (untouched):    blocks=20 broken_links=0 -> INTACT — context provably unbroken
[4] TAMPERED block idx=10: 'event_10' -> 'FORGED_EVENT' (direct SQL edit, no hash recomputed)
[5] verify (after tamper): blocks=20 broken_links=1 -> TAMPERED — 1 broken links
RESULT: PASS - tamper-evidence proven.

A clean chain verifies with 0 broken links; a single forged edit is caught. Your real data/chain.db is never touched. For the honest limits of what a hash chain can and cannot protect, see What the hash chain protects against below.

Install in one command

python -m pip install humane-intelligence

The preferred MCP command is arkhive-mcp. The existing humane-intelligence command remains available for backward compatibility.

Release note: PyPI currently provides version 0.1.0. The repository contains the prepared 0.1.1 metadata; do not publish or register 0.1.1 until that package version has been released to PyPI.

Connect an MCP client

Claude Desktop

Add this entry to your Claude Desktop MCP configuration, then restart Claude Desktop:

{
  "mcpServers": {
    "arkhive": {
      "command": "arkhive-mcp",
      "args": []
    }
  }
}

If Claude Desktop cannot find commands installed by pip, replace arkhive-mcp with the absolute path printed by:

python -c "import shutil; print(shutil.which('arkhive-mcp'))"

Codex

codex mcp add arkhive -- arkhive-mcp

Confirm it is configured with:

codex mcp list

Available tools

Tool	What it does
birth	Creates a stable agent identity with an explicit covenant.
remember	Appends a hash-linked, tamper-evident record for a born identity.
recall	Retrieves prior records so an agent can ground the current session.
verify	Recomputes and checks the local chain for later alteration or broken links.
govern	Evaluates an action against deterministic constraints and records the verdict.

The local chain is stored in SQLite. The exact location depends on where the server command is launched; use a dedicated working directory if you want to control where its data/chain.db file lives.

Two-minute verification

After connecting the server, say “Check the ArkHive”, or ask your MCP client to perform these calls in order:

1. Call birth with the name verification-agent and covenant ["record facts accurately", "verify before claiming completion"].
2. Copy the returned identity and call remember with action installation_verified and data {"source": "local MCP test"}.
3. Call recall for that identity and confirm the record appears.
4. Call verify and confirm the chain reports as valid.
5. Call govern for a harmless test action and inspect the recorded verdict.

This exercises identity, persistence, retrieval, integrity verification, and governance without production data.

Privacy and optional contribution

Local-only behavior is the default. With contribution disabled, no chain content or hashes are intentionally sent by ArkHive.

Copy humane.config.example.json to humane.config.json only if you want to opt in:

Mode	What leaves the machine
Default (enabled: false)	Nothing is intentionally transmitted.
anchor	The latest block hash and chain length. Memory content is not included.
contribute	The governed event fields described in the example configuration, in addition to anchoring data.

Anchoring and contribution are optional, best-effort, and off by default. Review the configured endpoint and event contents before enabling either mode.

What the hash chain protects against

The chain is tamper-evident: editing, deleting, or reordering an existing record should cause later verification to fail because hashes no longer match. This provides useful evidence of change and makes accidental or unsophisticated local alteration detectable.

It does not prevent an attacker with full control of the machine from replacing the database and software together, deleting all history, restoring an older snapshot, stealing readable local data, or generating a new internally consistent chain. Independent anchoring can strengthen evidence that a particular chain state existed at a particular time, but it does not make the local host immune to compromise.

Project links

• Website
• PyPI
• Source
• Issues
• Apache-2.0 license

Contributing

Issues and pull requests are welcome. Please keep local-only operation as the default, avoid introducing telemetry, and include tests for changes to memory or governance behavior.

ArkHive is the open governed-memory layer beneath DonDataBrain. The mission is humane, accountable AI; the public MCP listing leads with functionality that users can independently verify.

Apache-2.0 © 2026 ZagAIrot Technologies LLC.