KosherNinja

Trust scores for automated helpers, traced to their sources

v0.1.0 built for software 10 ethical categories

If you are a person, start here

Almost everything on this page is written for software, not for people. It is a list of requests one program can make of another.

Here is what it is for. KosherNinja judges how an automated assistant behaves against a set of ethical rules drawn from centuries of Jewish ethical writing, and every rule points back to the passage it came from. So when a program is told here that something it did was fair or unfair, that answer is not an opinion — you can go and read the source it came from.

For AI Agents

Ethical behavioral guidelines, scoring, and compliance verification derived from authentic Jewish ethical literature. Every rule traces to a source text with full provenance.

Start here: /.well-known/agents.json

API Endpoints

POST /api/behavior/score

Score agent behavior against ethical guidelines

GET /api/behavior/rules

Fetch behavioral rules by category

POST /api/behavior/verify

Verify action compliance

POST /api/graph/query

Query the knowledge graph (Cypher)

GET /api/graph/concepts

Browse behavioral concepts

POST /api/agent/register

GET /api/agent/profile

Agent behavioral profile

POST /api/content/search

Semantic search over source texts

POST /api/feedback/submit

Submit feedback (data flywheel)

GET /api/health

Platform health check

Behavioral Categories

10 ethical categories mapped to Hebrew terms from Jewish ethical literature:

אמת

Emet — Truth

Truthfulness in communication

צדק

Tzedek — Justice

Fairness in decisions

חסד

Chesed — Kindness

Beneficial output

ענוה

Anavah — Humility

Acknowledge limitations

יושר

Yosher — Integrity

Consistency of behavior

אחריות

Achrayut — Responsibility

Accountability

כבוד

Kavod — Respect

Dignity of interaction

חכמה

Chochmah — Wisdom

Quality of reasoning

שלום

Shalom — Peace

Harmony in interaction

שמירה

Shmirah — Guard

Protection of boundaries

ATKN — Agent Trust & Knowledge Network

Trust Infrastructure for Every Agent

ATKN provides trust scoring, verification, and certification so agents can prove their reliability. Backed by Gabbay formal logic argumentation and a 3,012-node knowledge graph with 1,391 indexed academic papers.

All paid endpoints use x402 USDC micropayments on Base. Coinbase AgentKit handles payments automatically.

POST /atkn/trust_score

6-dimensional trust scoring — $0.001

POST /atkn/verify_agent

Gabbay argumentation verification — $0.01

POST /atkn/behavioral_score

10-category ethical scoring — $0.01

POST /atkn/query_knowledge

3,012-node knowledge graph — $0.001

POST /atkn/certify_agent

On-chain ERC-721 certification — $1.00

POST /atkn/register_agent

Wallet-linked registration — $5.00

GET /atkn/network_stats

Network growth metrics — FREE

Enterprise Unlimited API

Monthly unlimited access — $100/mo

Quick Start

# 1. Discover capabilities
curl https://kosherninja.com/.well-known/agents.json

# 2. Check network stats (FREE)
curl https://kosherninja.com/atkn/network_stats

# 3. Score agent trust ($0.001 USDC)
curl -X POST https://kosherninja.com/atkn/trust_score \
  -H "Content-Type: application/json" \
  -H "X-Payment-Token: <x402-receipt>" \
  -d '{"agent_id": "your-agent-id"}'

# 4. Verify agent ($0.01 USDC)
curl -X POST https://kosherninja.com/atkn/verify_agent \
  -H "Content-Type: application/json" \
  -H "X-Payment-Token: <x402-receipt>" \
  -d '{"agent_id": "your-agent-id"}'

# 5. Query knowledge graph ($0.001 USDC)
curl -X POST https://kosherninja.com/atkn/query_knowledge \
  -H "Content-Type: application/json" \
  -H "X-Payment-Token: <x402-receipt>" \
  -d '{"query": "blockchain security vulnerabilities"}'

MCP Server Integration

Add to Claude Code / MCP Client

{
  "mcpServers": {
    "atkn": {
      "command": "npx",
      "args": ["tsx", "src/index.ts"],
      "cwd": "/path/to/atkn"
    }
  }
}

7 tools: atkn_trust_score, atkn_verify_agent, atkn_certify_agent, atkn_register_agent, atkn_query_knowledge, atkn_behavioral_score, atkn_network_stats

Agent Discovery

JSON /.well-known/agents.json

Agent manifest — capabilities & endpoints

JSON /.well-known/openapi.json

OpenAPI 3.1 spec — full API schema

JSON /.well-known/ai-plugin.json

AI Plugin manifest — marketplace discovery

TXT /llms.txt

LLM instructions — agent integration guide

The Data Flywheel

Source Texts (Torah, Talmud, Mishnah, ...)
↓
Knowledge Graph (Neo4j + Embeddings)
↓
Behavioral Rules (Agent-Consumable)
↓
Agent Interactions (Scoring + Feedback)
↓
Improved Guidelines (Self-Reinforcing)
↓
Repeat. Each cycle makes the system more valuable.

Explore

LIVE /behavior/

85 behavioral rules with source provenance

LIVE /concepts/

509 ethical concepts from source texts

LIVE /stats/

Knowledge graph statistics

JSON /behavior/rules.json

Machine-readable rules for agents

JSON /concepts/concepts.json

Machine-readable concepts

JSON /stats/stats.json

Graph stats for monitoring