AI Intelligence Suite
What This Is
The Intelligence Suite is a collection of autonomous skills deployed on the OpenClaw platform. Each skill runs on a schedule, daily, weekly, or in real time, scanning RSS feeds, financial APIs, news sources, and public data to produce actionable intelligence briefs delivered directly to Telegram.
These are not dashboards that wait to be checked. They are push-based intelligence agents that find signals in noise and deliver them when they matter.
The June 2026 AI research update changes what "intelligence agent" means here. The suite is no longer just scheduled collection plus summarisation. It is a governed signal system with persistent memory, source provenance, retrieval checks, model routing, and explicit escalation thresholds. Recent research on agent memory, agentic software, and autonomous incident response supports the architecture: collect evidence, retain only useful durable memory, retrieve it deliberately, and preserve enough trace to audit why the agent surfaced a signal.
Active Intelligence Skills
Geopolitical & Defense
| Skill | Schedule | Purpose |
|---|---|---|
| Conflict Dashboard | Hourly | Real-time Middle East SITREP, military actions, diplomatic developments, oil/Strait of Hormuz status, casualty tracking |
| Conflict RSS Scanner | 4x daily | Automated RSS ingestion from conflict news sources, severity scoring, SQLite storage |
| AI Defense Ethics Monitor | Daily | Tracks the ethical flashpoints at the intersection of AI and military/defense, Palantir, Pentagon, OpenAI contracts |
| Defense AI Intel | Daily | Broader defense-AI industry intelligence, procurement signals, policy shifts, capability announcements |
| Middle East SITREP | Daily 7 AM | Cross-referenced intelligence from Al Jazeera, Times of Israel, BBC, with X/Twitter verification |
Financial & Portfolio
| Skill | Schedule | Purpose |
|---|---|---|
| Flash Crash Guardian | Every 5 min | Monitors portfolio for sudden >5% drawdowns; autonomous position flattening capability |
| Portfolio Tracker | Bi-hourly (market hours) | Live pricing across ASX, US equities, and ETFs, validates data freshness, flags >3% movers |
| Nexus Daily Recommendations | Daily 9 AM | Integrated NEXUS engine status + all share positions with P&L, sector exposure, and conflict cross-reference |
| Earnings Reports | Daily | Upcoming earnings calendar for held positions, alerts before market-moving announcements |
| Cost Tracker | Daily | API spend and infrastructure cost monitoring |
Tech & AI Leadership
| Skill | Schedule | Purpose |
|---|---|---|
| Tech Leaders Daily Intel | Daily 9:15 AM | Scans web for latest from tracked tech leaders, Dario Amodei, Jensen Huang, Satya Nadella, and others. Produces project proposals from signals |
| Anthropic Legal Tracker | Daily | Monitors Anthropic's legal exposure, supply chain risks, and the Pentagon standoff |
| GTC Digest | Event-driven | Categorises and summarises NVIDIA GTC announcements |
| Meta Model Intel | On-demand | Structured intelligence on Meta's AI model pipeline, Avocado AI, and competitive positioning |
| M5 Mac Watch | 2x weekly | Monitors Apple M5 Mac release announcements, only alerts on confirmed launches |
Home & Operations
| Skill | Schedule | Purpose |
|---|---|---|
| AI Vision Sentry | Hourly | Computer vision sweep of all home cameras, person/vehicle/anomaly detection |
| Home Optimus | Hourly | Smart home optimisation scoring, battery levels, energy efficiency, device health |
| Doge Home Energy | 2x daily | Home energy and efficiency reporting with HA sensor data |
| Security 360 | 4x daily | Comprehensive security assessment, network, devices, access patterns |
| Network Watchdog | Every 6h | Multi-path connectivity testing with diagnostic reasoning |
Architecture Pattern
Every intelligence skill follows the same pattern:
- Data Collection, RSS feeds, APIs (Finnhub, Yahoo Finance), web scraping, HA sensors
- Signal Processing, Severity scoring, deduplication, freshness validation
- Intelligence Synthesis, Cross-referencing multiple sources, identifying patterns
- Delivery, Push to Telegram with emoji indicators, timestamps, and source citations
- State Management, SQLite storage, JSON state files, memory logs
- Memory Governance, Provenance, retention, supersession, and stale-signal expiry
- Traceability, Source list, model route, confidence, and escalation rationale captured with each high-impact brief
All reports include 📅 Data as of: <timestamp> headers. Stale data is flagged with ⚠️. This is a standing rule across the entire suite.
Model Routing
Intelligence tasks are routed to appropriate models:
- Claude Sonnet 4.6, Most intelligence synthesis, analysis, and reporting
- Claude Opus 4.6, Complex multi-source reasoning, strategic analysis
- Local Ollama (Qwen 2.5), Lightweight classification tasks
Routing also considers serving health. If the primary model is degraded, the suite should prefer a less capable but stable path over a stalled intelligence cycle. For long-horizon monitoring, freshness beats perfection: a timely, source-grounded summary with clear uncertainty is more useful than a delayed frontier-model synthesis.
Memory and Evaluation
Persistent memory is useful only when it is selective. The suite retains durable memory for recurring entities, thresholds, known false positives, prior escalations, and user decisions. It does not retain every article or every model-generated paragraph. That distinction follows the June 2026 Agent Memory research: construction cost, retrieval cost, and stale context risk are operational design constraints.
Evaluation focuses on three questions:
- Did the agent retrieve the right prior context? For example, a new Anthropic legal article should be compared with prior supply-chain, copyright, and government-contract signals.
- Did it preserve provenance? Every high-impact claim needs source links and timestamps.
- Did it escalate correctly? False silence matters as much as false alarm; the suite is judged by whether important signals arrive while they are still actionable.
Delivery Channels
All intelligence is delivered via Telegram with topic-based routing:
- Security topic, Network audits, Security 360, vision sentry alerts
- Markets topic, Portfolio updates, flash crash alerts, earnings
- General, Daily briefs, tech leader intel, conflict SITREPs
Design Philosophy
The intelligence suite exists because information without timing is noise. A conflict escalation that you read about 6 hours late is not intelligence, it is history. A portfolio drawdown that triggers an alert at 3% instead of 15% is the difference between a managed position and a catastrophic loss.
Every skill in this suite is designed to deliver the right signal at the right time with enough context to act on. No dashboards to check. No feeds to scroll. Just push notifications when something matters.
References
- OpenClaw Architecture: Living Architecture
- AI Research 2026: Reasoning, Agents, Memory, and Production Inference
- Anthropic Legal Tracker: Skill Documentation
- AI Defense Ethics: Skill Documentation
- GTC Digest: Skill Documentation