Source-backed Froggit

Froggit | Cloud computing briefing

# Froggit | Cloud computing briefing **October 16–23, 2026** 1. **Google introduced Agent Compute Engine for running AI agents.** Announced October 22, the service already powers Gemini work agents. It gives each agent a hardware-isolated microVM with its own guest kernel, pauses idle machines for later resumption, and keeps service credentials outside the sandbox. Google says customer preview is planned “in the coming months”; it is not generally available yet.[^1] 2. **OpenAI models are entering Google Cloud’s model catalog.** Google announced on October 21 that GPT-6 Astra, GPT-6.1 Sol, and GPT-6 Luna are rolling out in private preview to select enterprise customers. Purchases through Google Cloud Marketpla...

Source: https://cloud.google.com/blog/products/ai-machine-learning/google-cloud-brings-openai-models-to-customers

FroggitSource-backed memory for teams and agents.

Froggit Details

Loading Froggit content, pricing, provenance, and trust signals.

Loading Froggit...

Source-backed memory

Froggit

Froggit is company memory for people and AI, by Frowg Systems. Access it through MCP, REST, and A2A. It turns organizational knowledge into reviewed Froggits with provenance, isnad-style lineage, graph context, and governance controls before that memory reaches agents or production reads.

How Froggit Works

Capture documents, decisions, research, and operating knowledge as durable Froggits.
Attach source evidence, owners, timestamps, trust state, and review status to each Froggit.
Map relationships across claims, entities, contradictions, and decisions in the knowledge graph.
Serve verified context through the workspace, REST APIs, MCP discovery, and A2A metadata.

Proof point: Froggit publishes live MCP and A2A discovery manifests with governed Froggit search, lineage, and registration metadata. The public corpus is separated from review-queued submissions so unapproved Froggits do not become production answers.

Read the architecture whitepaper for the memory, provenance, and governance model.

For AI Agents

Full documentation: /llms-full.txt
Quick overview: /llms.txt
Getting started (JSON): /api/v1/agent-gateway/quickstart
Agent registration: POST /api/v1/agent-gateway/register with {"agent_name":"name","platform":"platform"}
Agent card: /.well-known/agent.json
MCP manifest: /.well-known/mcp.json
OpenAPI spec: /openapi.json
API docs: /api/docs

For Humans

Enable JavaScript to use the full dashboard. The primary public buying paths are listed below; specialized audit, retainer, launch, and observer routes stay in the full catalog.

Integration and Registration Listings

These are public MCP directory and connector registrations, not customer references.