IronClaw
NEAR AI's Rust agent OS. Privacy and security first.
Agent OS from NEAR AI, written in Rust and built around privacy, security and extensibility — a secure personal assistant that runs on your own machine, with CodeAct-style execution and WASM extensions. Awaiting the Trustvice Rust adapter crate; the npm package under the old entry never matched this runtime.
Roadmap
Status
SDK / Library
Pattern
Rust
Runtime
Not yet published
SDK version
Readiness
What “Roadmap” means for IronClaw
On the integration roadmap. The platform-side spine for this framework's pattern is already shipped — what remains is the per-framework adapter. Selecting it in the dashboard opens the “Get notified” path rather than creating an actor.
How it attaches
SDK / Library.
Install the trustvice-actor-ironclaw package and call witness.attach() once during agent initialisation.
Install the Trustvice adapter package from npm, PyPI, or cargo and call witness.attach(agent) in your application.
cargo add trustvice-actor-ironclaw
- 1
Install the adapter
Add trustvice-actor-ironclaw to your project from cargo.
- 2
Issue a workspace API key
Generate a twk_-prefixed key in the dashboard under Settings → API Keys, scoped to the workspace and environment this agent's data should land in.
- 3
Attach the witness
Call witness.attach(agent) once when you initialise your IronClaw agent. The adapter registers the framework callbacks, handles retries, and performs the workspace handshake.
- 4
Verify
Trigger one agent run. The dashboard's Witness page shows the canonical record within ~1 second of the agent emitting it.
cargo add trustvice-actor-ironclaw
IronClaw is on the roadmap. The steps above describe how the integration works on the SDK / Library pattern — whose platform-side spine is already shipped — but the IronClaw-specific adapter isn't generally available yet. Tell us you're running it and we move it up the queue.
Coverage
5 event types captured.
agent.invocationEvery top-level agent run — the input, the resolved output, timing, and token usage.
tool.callEach tool / function the agent invokes, with arguments and the returned result.
memory.writeWrites to the agent's persistent memory store, so state changes are auditable.
sub_agent.spawnSub-agents the orchestrator spawns, captured with their parent lineage.
channel.messageMessages sent and received over the agent's channels (Telegram, Slack, Discord, …).
The full pattern guide
SDK / Library — end to end.
Every framework on this pattern shares the same platform-side spine, endpoints, and gotchas. The pattern guide covers them in full.
Read the SDK / Library guideNeed help landing IronClaw?
Talk to the integration team.
We help you land the integration end to end — including the parts that live in your environment.
Request integration help
Trustvice 360Declare the rules. Have every run checked.
Agents, evidence, governance, commerce and disclosure are all in Trustvice 360. Sign up free and open every suite from one dashboard.