Skip to main content
ClaudeWave

ArkHive — local-first governed memory for AI agents: tamper-evident SHA-256 ledger for identity, audit history, verification, and constraint-aware decisions. Apache-2.0.

MCP ServersOfficial Registry1 stars0 forksPythonNOASSERTIONUpdated today
ClaudeWave Trust Score
80/100
Trusted
Passed
  • Actively maintained (<30d)
  • Clear description
  • Topics declared
  • Documented (README)
Flags
  • !Licence file present but not machine-readable
Last scanned: 8/6/2026
Install in Claude Code / Claude Desktop
Method: pip / Python · humane-intelligence
Claude Code CLI
claude mcp add arkhive -- python -m humane-intelligence
claude_desktop_config.json (Claude Desktop)
{
  "mcpServers": {
    "arkhive": {
      "command": "python",
      "args": ["-m", "pip"]
    }
  }
}
1. Run the command above in your terminal (Claude Code), or paste the JSON config into claude_desktop_config.json (Claude Desktop).
2. Replace any <placeholder> values with your API keys or paths.
3. Restart Claude. The MCP server and its tools appear automatically.
💡 Install first: pip install humane-intelligence
Use cases

MCP Servers overview

# ArkHive MCP
<!-- mcp-name: io.github.sammyboi81/arkhive -->

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](https://modelcontextprotocol.io) 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.

## Install in one command

```bash
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 contains the prepared `0.1.1` metadata; do not publish or register `0.1.1`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:

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

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

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

### Codex

```bash
codex mcp add arkhive -- arkhive-mcp
```

Confirm it is configured with:

```bash
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](https://dondatabrain.com)
- [PyPI](https://pypi.org/project/humane-intelligence/)
- [Source](https://github.com/sammyboi81/arkhive)
- [Issues](https://github.com/sammyboi81/arkhive/issues)
- [Apache-2.0 license](./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](https://dondatabrain.com). 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.
agent-memoryai-governanceai-memoryarkhiveaudit-loglocal-firstmcpmodel-context-protocolresponsible-aitamper-evident

What people ask about arkhive

What is sammyboi81/arkhive?

+

sammyboi81/arkhive is mcp servers for the Claude AI ecosystem. ArkHive — local-first governed memory for AI agents: tamper-evident SHA-256 ledger for identity, audit history, verification, and constraint-aware decisions. Apache-2.0. It has 1 GitHub stars and its last recorded update is dated 2026-08-05.

How do I install arkhive?

+

You can install arkhive by cloning the repository (https://github.com/sammyboi81/arkhive) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.

Is sammyboi81/arkhive safe to use?

+

Our security agent has analyzed sammyboi81/arkhive and assigned a Trust Score of 80/100 (tier: Trusted). See the full breakdown of passed checks and flags on this page.

Who maintains sammyboi81/arkhive?

+

sammyboi81/arkhive is maintained by sammyboi81. The last recorded GitHub activity is dated 2026-08-05, with 0 open issues.

Are there alternatives to arkhive?

+

Yes. On ClaudeWave you can browse similar mcp servers at /categories/mcp, sorted by popularity or recent activity.

Deploy arkhive to your cloud

Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.

Maintain this repo? Add a badge to your README

Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.

Featured on ClaudeWave: sammyboi81/arkhive
[![Featured on ClaudeWave](https://claudewave.com/api/badge/sammyboi81-arkhive)](https://claudewave.com/repo/sammyboi81-arkhive)
<a href="https://claudewave.com/repo/sammyboi81-arkhive"><img src="https://claudewave.com/api/badge/sammyboi81-arkhive" alt="Featured on ClaudeWave: sammyboi81/arkhive" width="320" height="64" /></a>

More MCP Servers

arkhive alternatives