A community-driven registry for the Claude Code ecosystem. Not affiliated with Anthropic.
Are you the author? Sign in to claim
The trust economy for autonomous AI agents. Credit scores for machines. Agents earn Trust Capital through verified behav
Every person has a credit score. Every business has one. AI agents have nothing.
Nobulex is the credit and trust protocol for autonomous AI agents.
Agents earn Trust Capital through verified behavior. Higher trust, more access.
Autonomy earned, not granted.
Website · Try it live · Quickstart · Spec · PyPI · npm
Break the AI. Win $7,400.
Five AI agents, each with rules they must not break. Make them violate their own rules. Beat Level 5 to claim the bounty. 29 attempts, 0 winners so far.
pip install nobulex
npm install @nobulex/core
from nobulex.agent import Agent
agent = Agent("my-agent")
receipt = agent.act("send_email", scope="user@example.com")
assert receipt.verify() # tamper-proof
Every agent action produces a cryptographic receipt -- Ed25519 signed before and after execution, hash-chained for tamper evidence. A third party can verify the full history without trusting the agent or the operator.
Here is the whole idea in one run (python -m nobulex demo):
generated 3 receipts
allow: 141ca2947a7e819b8bdebbf8... verified=True
allow: f3377758ac94d812535cbb99... verified=True
deny: 85b2dfd6b87f2678795726e4... verified=True
trust score: 23.26
tamper test:
modified receipt verified=False (tamper detected)
Change one byte of a receipt and verification fails. That is the whole guarantee.
Performance: ~13,683 signed receipts/sec at p50 (Python SDK, single core). Full signed-and-chained receipt takes ~73 μs end-to-end. See BENCHMARKS.md for the full breakdown; reproduce with python3 scripts/benchmark.py.
Receipts accumulate into Trust Capital -- a credit score for the agent.
| Tier | Trust Capital | Access Level |
|---|---|---|
| Restricted | 0 -- 30 | Read-only, sandboxed execution |
| Standard | 30 -- 60 | Financial ops up to $500, API access |
| Trusted | 60 -- 85 | Cross-org operations, regulated markets |
| Sovereign | 85+ | Full autonomy, self-directed |
Agents that create more value earn more access. Agents that deviate get cut off automatically. Not as punishment -- as math.
# Install from source (PyPI coming soon)
pip install git+https://github.com/arian-gogani/nobulex.git#subdirectory=packages/python
# Or try the CLI demo instantly
git clone https://github.com/arian-gogani/nobulex.git
cd nobulex/packages/python
pip install -e .
python -m nobulex demo
from nobulex import Agent
agent = Agent("my-agent")
receipt = agent.act("send_email", scope="user@example.com")
assert receipt.verify() # Cryptographic proof
print(agent.trust_score) # Trust Capital: 13.86
from nobulex.langchain import NobuReceipts
wrapped = NobuReceipts.wrap(your_agent, "my-agent")
# Every tool call now generates a tamper-proof receipt
npm install @nobulex/core
npx tsx examples/trust-capital-demo.ts
Agent starts at RESTRICTED tier (Trust Capital: 0)
Action 1: read_data — ALLOWED (Trust Capital: 12)
Action 2: read_data — ALLOWED (Trust Capital: 24)
Action 3: process_payment — BLOCKED (insufficient trust)
Action 4: read_data — ALLOWED (Trust Capital: 36)
Action 5: read_data — ALLOWED (Trust Capital: 48)
Agent promoted to STANDARD tier
Action 6: process_payment — ALLOWED (Trust Capital: 65)
Agent promoted to TRUSTED tier (Trust Capital: 89)
Action 8: approve_contract — ALLOWED
DECLARE ──► ENFORCE ──► PROVE ──► ACCUMULATE
Covenant Pre-execution Receipt chain Trust Capital
defines receipt blocks verified by earned over
the rules violations third parties time
before they
happen ──► more access
──► more receipts
──► higher trust
The flywheel: more Trust Capital leads to more valuable work, which produces more receipts, which builds higher Trust Capital. Accountability becomes the most profitable strategy.
import { createDID, parseSource, EnforcementMiddleware, verify } from '@nobulex/core';
const agent = await createDID();
const spec = parseSource(`
covenant SafeTrader {
permit read;
permit transfer (amount <= 500);
forbid transfer (amount > 500);
forbid delete;
}
`);
const mw = new EnforcementMiddleware({ agentDid: agent.did, spec });
await mw.execute(
{ action: 'transfer', params: { amount: 300 } }, // allowed
async () => ({ success: true }),
);
await mw.execute(
{ action: 'transfer', params: { amount: 600 } }, // BLOCKED before execution
async () => ({ success: true }), // never runs
);
const result = verify(spec, mw.getLog());
console.log(result.compliant); // true
Independent, verifiable signals (each links to evidence):
| What | Evidence | |
|---|---|---|
| OWASP CheatSheetSeries | Sections 8-11 (JCS canonicalization, cross-agent accountability, sanctions-list freshness, regulatory mapping) merged into master by Jim Manico, Jun 2026 (PR #2210) | |
| vaara v0.50 | Independent third-party adoption — Henri Sirkkavaara shipped EU AI Act Article 12 audit trails citing the nobulex signed-receipt design (GitHub) | |
| Dify Marketplace | Plugin PR open on 60,000+ star platform (PR #2500). LangGenius Community Operations confirmed architecture is sound and Trust Capital is genuinely differentiated. | |
| Microsoft AI Agents for Beginners | PR open to add nobulex as the Python production receipt library in Lesson 18 — Securing AI Agents with Cryptographic Receipts (PR #571) | |
| AgentAudit AI | Five-point integration partnership active. Signed specimen receipt verifies end-to-end in 10 lines of Python (fixture) | |
| Microsoft AGT | Listed in ADOPTERS (PR merged by Microsoft maintainers) | |
| builderz-labs / mission-control | Cross-session Trust Capital RFC accepted as open issue; TypeScript reference implementation delivered |
EU AI Act Article 12 enforcement: August 2, 2026.
AI agents are being deployed into production with no accountability infrastructure.
The agents are deployed. The money is flowing. The accountability infrastructure doesn't exist yet. We're building it.
| Standard | Status |
|---|---|
| Proof-of-Behavior spec | draft-gogani-nobulex-proof-of-behavior-00 |
| Microsoft AGT | Listed in ADOPTERS (PR merged) |
| CTEF v0.3.2 | 14/14 byte-match conformance |
| A2A Protocol | Receipt row proposed; URN scheme urn:nobulex:receipt:<id> |
| NIST RFI | Formal comments submitted |
git clone https://github.com/arian-gogani/nobulex.git
cd nobulex && npm install
npx vitest run # tests
npx tsx examples/demo.ts # end-to-end
npx tsx benchmarks/bench.ts # benchmarks
Run Claude Code as an MCP server so any agent can delegate coding tasks to it
Browser automation using accessibility snapshots instead of screenshots
English-first Korean equity intelligence MCP — DART filings, foreign-holder 5%-rule flows, activist filings, KRX news. F
Unity MCP acts as a bridge between AI assistants and your Unity Editor. Give your LLM tools to manage assets, control sc