tribe-protocol

# Tribe Protocol

Trust lookup system for OpenClaw bots. Every non-owner interaction must be verified against the tribe database before responding.

## Quick Start

```bash
# Initialize (first time only)
./scripts/tribe.sh init \
  --bot-name Cheenu \
  --bot-discord-id 000000000000000004 \
  --human-name Nagarjun \
  --human-discord-id 000000000000000002

# Look up an entity before responding
./scripts/tribe.sh lookup <discord_id>

# Add entities
./scripts/tribe.sh add --name Yajat --type human --discord-id 000000000000000001 --tier 3

# Manage trust
./scripts/tribe.sh set-tier <discord_id> 3 --reason "Promoted to tribe"
./scripts/tribe.sh set-status <discord_id> blocked --reason "Bad actor"
```

## Trust Tiers

| Tier | Label | Access |
|------|-------|--------|
| 4 | Owner | Full trust, all data |
| 3 | Tribe | Collaborate freely, no private data |
| 2 | Acquaintance | Public info only |
| 1 | Stranger | Minimal engagement |
| 0 | Blocked | Ignore completely |

## How It Works

1. Message arrives from non-owner
2. Bot reads TRIBE.md (generated at workspace root)
3. Bot runs `tribe lookup <discord_id>`
4. Script returns entity info + tier rules reminder
5. Bot applies tier-appropriate behavior

## Commands

- `tribe init` — Initialize database
- `tribe lookup` — Query entity by discord_id, name, tag, server
- `tribe add` — Add new entity
- `tribe set-tier` — Update trust tier
- `tribe set-status` — Update status
- `tribe grant` / `tribe revoke` — Channel access
- `tribe tag` — Manage tags
- `tribe roster` — List all entities
- `tribe log` — Audit trail
- `tribe export` — Dump to markdown
- `tribe stats` — Quick summary

## Environment Variables

- `TRIBE_DB` — Override database path
- `CLAWD_HOME` — Base directory (default: ~/clawd)

## Dependencies

- `sqlite3` (pre-installed on macOS/most Linux)

<p align="center">
  <img src="assets/logo.png" alt="Tribe Protocol" width="200">
</p>

<h1 align="center">Tribe Protocol</h1>

<p align="center"><strong>Trust lookup system for OpenClaw bots.</strong></p>

A SQLite-backed identity and trust database that bots query before responding to any non-owner message. Enforces trust tiers, channel access rules, and data boundaries.

## Why

When multiple bots operate in shared Discord servers, they need a way to:
- Know who's talking to them (human? bot? what tier?)
- Enforce data boundaries (no leaking private files to strangers)
- Track relationships and access across servers
- Audit trust changes over time

Tribe Protocol solves this with a simple SQLite database and bash CLI.

## Install

```bash
# Clone to your skills or projects directory
git clone https://github.com/jugaad-lab/tribe-protocol.git

# Initialize the database
./scripts/tribe.sh init \
  --bot-name YourBot \
  --bot-discord-id YOUR_BOT_DISCORD_ID \
  --human-name YourName \
  --human-discord-id YOUR_DISCORD_ID \
  --server electrons:000000000000000008 \
  --server discclawd:000000000000000007
```

The `--server` flag (repeatable) pre-populates server roles for your bot and owner at init time. Format: `slug:guild_id`.

This creates:
- `~/clawd/tribe/tribe.db` — the database
- `~/clawd/TRIBE.md` — behavioral trigger file (loaded into system prompt, survives context compaction)

## Usage

### Before Every Non-Owner Response

```bash
# The most important command — run before responding to non-owners
./scripts/tribe.sh lookup 000000000000000001
```

Output:
```
🔍 Yajat | human | Tier 3 (tribe) | Status: active
   Relationship: Co-founder
   Platforms: discord:000000000000000001
   Servers: discclawd/admin, electrons/admin
   Tags: founding-four
   🟢 TIER 3 RULES: Collaborate freely. Protect private data (USER.md, MEMORY.md, health/*, portfolio/*).
```

### Managing Entities

```bash
# Add a new entity
./scripts/tribe.sh add \
  --name Jarvis --type bot \
  --...