# EZKL

**Canonical:** https://apis.io/providers/ezkl/  
**Website:** https://ezkl.xyz/  
**APIs profiled:** 0

EZKL (by Zkonduit Inc.) is a developer-friendly engine for verifiable AI and analytics that generates zero-knowledge proofs (ZK-SNARKs, Halo2) for machine learning model inference. Given a model in ONNX format and sample input, EZKL automatically compiles a proving circuit and produces a cryptographic proof that a computation ran correctly without revealing the underlying private data or model weights. Proofs are verifiable on-chain (EVM-compatible), in the browser, or on edge devices. EZKL ships as a command-line tool, Python and JavaScript (WebAssembly) bindings, and a Rust library, and supports tree-based models, transformers, CNNs, and RNNs. Lilith is its high-performance compute cluster for cloud-scale proof generation. The codebase was audited by Trail of Bits and is developed in the open at github.com/zkonduit/ezkl.

## Kin Score — 18.1 / 100 (emerging)

Scored 2026-08-20 under rubric 0.12.0. Trend: flat (+0.0 from 18.1).

| Facet | Score |
|---|---|
| Discoverability | 57.4 |
| Contract Quality | 0.0 |
| Governance | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 28.9 |
| Developer Ergonomics | 42.9 |
| Commercial Clarity | 0.0 |
| Access Clarity | 0.0 |

## Agent readiness — 0.0 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |

## Access

Unknown — onboarding: unknown, pricing: unknown, trial: no (confidence: low).

## Security (1)

- **Ezkl Domain Security** — TLSv1.3 · HSTS

## Tags

Company, Zero-Knowledge Proofs, Machine-Learning, Verifiable AI, ZKML, Cryptography, ONNX, Blockchain, Open-Source, SDK, CLI

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/ezkl/). Scores are computed from the provider's own public artifacts under a published rubric.