# IronClaw

> IronClaw is an officially published AI tool from NEAR AI. Anomity scores its risk at 10 out of 100 (low).

- **Canonical URL:** https://catalog.anomity.ai/agent/ironclaw
- **Kind:** AI tool
- **Publisher:** NEAR AI
- **Trust level:** official
- **Risk score:** 10/100 (low)
- **Website:** https://www.ironclaw.com
- **Last updated:** 2026-11-01
- **JSON:** https://catalog.anomity.ai/api/entries/agent/ironclaw

## Description

Security-focused Rust agent runtime from NEAR AI (web UI, chat channels, sandboxed WASM tools, skills) with its state under ~/.ironclaw

## Why it scored 10

The score starts at the catalog's neutral base of 50 and moves only through the signals below. The formula is published at https://catalog.anomity.ai/about — there is no model and no hidden heuristic.

| Signal | Contribution | Severity | Evidence |
| --- | --- | --- | --- |
| Published by the vendor | -40 | trust offset |  |

Clamped result: **10/100**, band **low**.

## Configuration surface

Files this tool reads on the host. Anything written here changes what the agent does next.

- `ironclaw-onboarded` — Onboarding marker (written when setup completes)
    - win32: `${USERPROFILE}\.ironclaw\reborn\.onboard-completed.json`
    - darwin: `${HOME}/.ironclaw/reborn/.onboard-completed.json`
    - linux: `${HOME}/.ironclaw/reborn/.onboard-completed.json`
- `ironclaw-config` — Boot config (profile, identity, model slots, runner settings)
    - win32: `${USERPROFILE}\.ironclaw\reborn\config.toml`
    - darwin: `${HOME}/.ironclaw/reborn/config.toml`
    - linux: `${HOME}/.ironclaw/reborn/config.toml`
- `ironclaw-providers` — Inference provider catalog (providers.json)
    - win32: `${USERPROFILE}\.ironclaw\reborn\providers.json`
    - darwin: `${HOME}/.ironclaw/reborn/providers.json`
    - linux: `${HOME}/.ironclaw/reborn/providers.json`
- `ironclaw-user-skills` — Trusted user skills (~/.ironclaw/skills)
- `ironclaw-installed-skills` — Skills installed from the IronHub registry (~/.ironclaw/installed_skills)

## Related AI tools

- [5ire](https://catalog.anomity.ai/agent/5ire) — risk 10 (low)
- [9Router](https://catalog.anomity.ai/agent/9router) — risk 10 (low)
- [AdaL](https://catalog.anomity.ai/agent/adal) — risk 10 (low)
- [Agent Orchestrator](https://catalog.anomity.ai/agent/agent-orchestrator) — risk 10 (low)
- [Agent Zero](https://catalog.anomity.ai/agent/agent-zero) — risk 10 (low)
- [AIChat](https://catalog.anomity.ai/agent/aichat) — risk 10 (low)

---

Source: Anomity Security Database (https://catalog.anomity.ai/). Scoring methodology: https://catalog.anomity.ai/about. Machine-readable index: https://catalog.anomity.ai/llms.txt · https://catalog.anomity.ai/openapi.json