# AgentKernel

**Canonical:** https://apis.io/providers/agentkernel-si/  
**Website:** https://thrashr888.github.io/agentkernel/  
**APIs profiled:** 0

AgentKernel provides a platform for running AI coding agents in secure, isolated microVMs. It offers sub-125ms boot times, real hardware isolation, and supports multiple runtimes such as Python, Node.js, Ruby, Rust, Go, and more. Users can install via Homebrew, a script, or Cargo, and manage sandboxes with commands for creating, starting, executing, and debugging. The system includes policy management, secret handling, and integration with tools like LangChain, enabling enterprise‑level security and customizable sandbox environments.

## Kin Score — 3.0 / 100 (minimal)

Scored 2026-11-06 under rubric 0.27.0. Trend: flat (+0.0 from 3.0).

| Facet | Score |
|---|---|
| Discoverability | 44.6 |
| Contract Quality | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 0.0 |
| Developer Ergonomics | 0.0 |
| Access Clarity | 0.0 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 5.5 (matched via fallback).

## Agent readiness — 3.1 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | documented |
| 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 |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |
| Pagination Ratio | na |
| Operation Distinctiveness | na |
| MCP Tool Quality | na |

## Access

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

## Security (1)

- **Agentkernel Si Domain Security** — TLSv1.3

## Tags

Artificial Intelligence, Sandbox, MicroVM, Security, Open Source

---

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