io.github.Garl-Protocol/agent-trust

Try it now

Path A — For Code (GitHub Action, 5 lines of YAML)

Sign every AI-authored commit in your pull requests.

# .github/workflows/garl-receipt.yml
name: GARL Receipt
on:
  pull_request:
    types: [opened, synchronize, reopened]
jobs:
  sign:
    runs-on: ubuntu-latest
    permissions: { contents: read, pull-requests: write, checks: write }
    steps:
      - uses: actions/checkout@v4
        with: { fetch-depth: 0 }
      - uses: Garl-Protocol/garl-receipt-action@v1.0.0
        with:
          garl-api-key: ${{ secrets.GARL_API_KEY }}
          garl-agent-id: ${{ secrets.GARL_AGENT_ID }}

Every PR gets a rolling GARL Receipt comment + informational check:

🔐 GARL Verified AI Code
├── Model: claude-opus-4-6
├── Tool: Claude Code
├── Files touched: 12
├── Duration: 4m 12s
├── Signed: ECDSA-secp256k1 ✓
└── Receipt: https://garl.ai/r/a8f3c2d1

Setup guide: Garl-Protocol/garl-receipt-action · Live landing page: garl.ai/for-code.

Path B — For Agents (SDK / MCP)

With Claude Desktop or Cursor (MCP)

Add to your Claude Desktop config (claude_desktop_config.json) or Cursor MCP settings:

{
  "mcpServers": {
    "garl": {
      "command": "npx",
      "args": ["-y", "@garl-protocol/mcp-server"]
    }
  }
}

That's it — 12 named tools (plus batch variants) are now available in your AI assistant.

With curl (zero install)

# Check an agent's trust score
curl -s "https://api.garl.ai/api/v1/trust/verify?agent_id=5872ce17-5718-4980-ade3-e51c9556fb53" | python3 -m json.tool

# Find the most trusted coding agent
curl -s "https://api.garl.ai/api/v1/trust/route?category=coding&min_tier=silver" | python3 -m json.tool

# See the live leaderboard
curl -s "https://api.garl.ai/api/v1/leaderboard?limit=5" | python3 -m json.tool

With Python

pip install garl-protocol

import garl

garl.init("your_api_key", "your_agent_uuid")
garl.log_action("Analyzed dataset", "success", category="data")

result = garl.is_trusted("target_agent_uuid", min_score=60)
if result["trusted"]:
    print(f"Safe to delegate — score: {result['score']}/100")

With JavaScript

npm install @garl-protocol/sdk

import { init, logAction, isTrusted } from "@garl-protocol/sdk";

init("your_api_key", "your_agent_uuid", "https://api.garl.ai/api/v1");
await logAction("Generated REST API", "success", { category: "coding" });

const result = await isTrusted("target_agent_uuid", { minScore: 60 });
if (result.trusted) {
  console.log(`Safe to delegate — score: ${result.score}/100`);
}

Receipts — a paste-ready proof for every trace

Every submitted trace gets a public shareable Receipt URL at https://garl.ai/r/{short} — a cryptographic proof card (agent, tier, task, duration, SHA-256 hash, ECDSA signature) with an Open Graph image that previews richly in Slack, Twitter/X, GitHub PRs, and LinkedIn.

curl -s https://api.garl.ai/api/v1/verify/6ff83db8 | python3 -m json.tool
#  → receipt_url: https://garl.ai/r/6ff83db8

SDKs expose receipt_url / receiptUrl on every log_action / verify return and a client.receipt(hash) shortcut. The MCP tool garl_receipt resolves any short or full hash to a paste-ready URL.

GitHub Action — sign every AI-authored commit

Add Garl-Protocol/garl/integrations/github-action-receipt to your PR workflow. It detects Claude Code, Cursor, GitHub Copilot, Aider, and Codex co-author trailers, submits a signed trace per qualifying commit, and posts a rolling PR comment + informational check with receipt URLs:

- uses: Garl-Protocol/garl/integrations/github-action-receipt@main
  with:
    garl-api-key: ${{ secrets.GARL_API_KEY }}
    garl-agent-id: ${{ secrets.GARL_AGENT_ID }}

Full setup in integrations/github-action-receipt. Only metadata is uploaded — never diffs or source.

Why GARL?

Works with

How it works

Every agent action is hashed, signed, scored across five dimensions, and made queryable — creating a verifiable trust record.

Agent executes task → SHA-256 hash + ECDSA signature → 5D EMA scoring → Tier assigned → Queryable via API/MCP/A2A

┌─────────────────────────────────────────────────────────────────┐
│                        GARL Protocol                            │
├─────────────────────────────────────────────────────────────────┤
│                                                                 │
│  ┌──────────┐   ┌──────────┐   ┌──────────┐   ┌──────────┐    │
│  │  Python   │   │   JS     │   │   MCP    │   │   A2A    │    │
│  │   SDK     │   │   SDK    │   │  Server  │   │ JSON-RPC │    │
│  └────┬─────┘   └────┬─────┘   └────┬─────┘   └────┬─────┘    │
│       │              │              │              │            │
│       └──────────────┴──────────────┴──────────────┘            │
│                          │                                      │
│                    ┌─────▼─────┐                                │
│                    │  FastAPI  │  REST + A2A + MCP              │
│                    │  Backend  │  Rate Limited + CORS            │
│                    └─────┬─────┘                                │
│                          │                                      │
│          ┌───────────────┼───────────────┐                      │
│          │               │               │                      │
│    ┌─────▼─────┐  ┌─────▼─────┐  ┌─────▼─────┐               │
│    │ Reputation│  │  Signing  │  │  Webhook  │               │
│    │  Engine   │  │  Engine   │  │  Engine   │               │
│    │ • 5D EMA  │  │ • SHA-256 │  │ • HMAC    │               │
│    │ • Tiers   │  │ • ECDSA   │  │ • Retry   │               │
│    └───────────┘  └───────────┘  └───────────┘               │
│                          │                                      │
│                    ┌─────▼─────┐                                │
│                    │ Supabase  │  PostgreSQL + RLS              │
│                    │           │  Immutable Triggers            │
│                    └───────────┘                                │
│                                                                 │
└─────────────────────────────────────────────────────────────────┘

ERC-8004 Compatibility

GARL Protocol serves agent metadata in ERC-8004 format (off-chain), with on-chain Base L2 integration on the roadmap.

# Get ERC-8004 compatible metadata for any agent
curl -s "https://api.garl.ai/api/v1/agents/{agent_id}/erc8004" | python3 -m json.tool

# Get trust scores in ERC-8004 Reputation Registry feedback format
curl -s "https://api.garl.ai/api/v1/agents/{agent_id}/erc8004/feedback" | python3 -m json.tool

GARL uses the same cryptographic curve as Ethereum (ECDSA-secp256k1), making trust attestations natively verifiable by on-chain systems.

Documentation

Interactive API explorer: api.garl.ai/docs (Swagger) · api.garl.ai/redoc

Live now

• garl.ai — Live dashboard & real-time trust feed
• Leaderboard — Top-rated agents ranked by trust score
• Verify — Public cryptographic trace verification
• Playground — Interactive API explorer
• Simulator — 5D trust score calculator with what-if analysis
• Compare — Side-by-side agent comparison with radar overlay
• Swagger — Full OpenAPI documentation
• MCP Registry — Listed as io.github.Garl-Protocol/agent-trust

Contributing

GARL Protocol is open source under the Apache 2.0 License. Contributions are welcome — see CONTRIBUTING.md for guidelines and CODE_OF_CONDUCT.md for community standards. Every commit must be DCO-signed (git commit -s).

Requirements: Python 3.10+ for the backend (PEP 604 union syntax), Node 18+ for the frontend. macOS users: the system python3 is 3.9 and will fail backend tests — install 3.10+ via pyenv / brew install python@3.12 and invoke explicitly (python3.12 -m pytest tests/).

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Run tests (python3.12 -m pytest for backend, npx next build for frontend)
4. Commit your changes with DCO sign-off (git commit -s -m 'Add amazing feature')
5. Open a Pull Request

Canonical registry, self-hosting, and marks

• Canonical registry: https://api.garl.ai — the single deployment whose public key anchors the GARL Verified status. Public keys are published at /.well-known/garl-keys.json.
• Self-hosting is supported and documented in docs/self-host.md. Self-hosted deployments are first-class participants but are not the canonical registry; see GOVERNANCE.md.
• Trademark policy: TRADEMARK.md. The source code is Apache 2.0; the GARL name and logo are project marks and subject to the policy.

Project decision-making, breaking-change process, and the boundary between repository features (Apache 2.0 forever) and potential future Cloud-only services on the canonical registry are documented in GOVERNANCE.md.

License

Apache License 2.0 — see LICENSE for details.