Genspark (Super Agent)
BetaConsumer 'Super Agent' that autonomously researches and acts across the web, with an on…
Consumer 'Super Agent' that autonomously researches and acts across the web, with an on-device mode running 169+ open-weight local models. Launched May 2025; widely compared against browser-use/Manus in 2026; notable on-device local-model capability. General web-acting agent → browser-instrument (o
- Category
- Personal agents
- Runtime
- Managed SaaS — nothing to install
- Pattern
- Browser instrumentation
- Adapter package
- None — configured on the Intramedial side
Status
Genspark (Super Agent) is Beta.
The integration path is built and tested. Customers can attach now; expect minor breaking changes until the 1.0 contract freeze.
How to attach
Browser instrumentation.
Issue a workspace API key
Generate a key in the dashboard under Settings → API Keys, scoped to the workspace and environment this agent's data should land in.
Install the instrumentation
Load the Intramedial browser extension unpacked from the repo (`chrome://extensions` → Developer mode → Load unpacked) — the Web Store listing is not up yet for desktop use, or build the Intramedial-instrumented Chromium image from `browser-extension/chromium/Dockerfile` (it is not on a public registry yet) for headless runs. Genspark (Super Agent)'s activity is observed at the click and DOM-event layer.
Verify
Trigger one agent run. The Witness page shows the record once the agent has emitted it.
What gets recorded
2 event types, captured today.
- agent.invocation
- Every top-level agent run — the input, the resolved output, timing and token usage.
- tool.call
- Each tool or function the agent invokes, with its arguments and returned result.
Same category
Others in Personal agents.
- OpenClawGA
The original personal-agent framework. First-class integration.
- NanoClawBeta
Container-isolated, security-first. Built on the Claude Agent SDK.
- ZeroClawRoadmap
Rust-native. A single binary you configure and run.
- Hermes AgentBeta
Self-improving learning loop. Model-agnostic by design.
- NanobotBeta
~4,000 lines of code. Built for MCP-first agents.
- NemoClawBeta
NVIDIA's sandboxed reference stack for running agents.
Start recording Genspark (Super Agent) agents.
Every Genspark (Super Agent) run lands in the same canonical Witness record as every other framework in the catalogue: signed, replayable, and exportable as evidence.
A Trustvice ProductAgents act when the plane says yes, and the record says why.
Put admission in front of your MCP servers, repositories, SaaS tools and cloud accounts. Every agent gets a lease or a reason – and you keep the lever to stop any of them.
