Cascade Trend Analysis

An intelligent system for analyzing technology trends and forecasting their cascading impact. Automatically collects signals from multiple sources, groups them into trends, evaluates them using a three-dimensional model (significance, momentum, confidence), and generates analytical reports with actionable recommendations.

What the system does

• Signal collection from 5 sources: Hacker News, GitHub, arXiv, Semantic Scholar, SearXNG (246+ search engines)
• Source-aware scoring — separate formulas for each source type with web citation enrichment
• LLM classification — grouping signals into trends with automatic category detection
• 3D trend profiling — evaluation across three axes: Significance / Momentum / Confidence
• Recommendations — automatic calculation: ACT_NOW, MONITOR, RISKY_HYPE, EVERGREEN, IGNORE
• Analytical reports — cascading impact graph, impact zones, validated sources
• Role-based recommendations — specific actions for CTO, Developer, PM, Investor per impact zone
• Multilingual support — context-aware batch translation (EN, RU) with automatic language detection
• External API — REST API v1 with Personal Access Token authentication for agent integrations

Key features

Scoring and recommendations

Each trend is evaluated using a three-dimensional model:

Based on the combination of axes, the system automatically determines a recommendation and lifecycle phase (emerging → mature → fading).

Cascade analysis

An LLM agent (LangGraph + Claude) generates:

• Full analytical report with trend overview
• Cascading impact graph — how the trend propagates to adjacent domains
• Impact zones with influence scores (1-10)
• Role-based recommendations — specific actions for 4 roles (CTO, Developer, PM, Investor)
• Sources validated through web citations

Translation

Context-aware batch translation using LLM:

• Titles are translated together with descriptions and categories for accuracy
• Automatic source language detection (Cyrillic / Latin)
• Sentence case normalization
• 2 LLM calls per analysis instead of 30-80 (batched short texts with deduplication)

External API

REST API v1 for external agents and integrations:

• GET /api/v1/trends — paginated list with sorting (score, momentum, significance, confidence)
• GET /api/v1/trends/top — Top 5 by 3 criteria (new, fast_growing, highest_scored)
• GET /api/v1/trends/{id} — trend details with signals and latest analysis
• GET /api/v1/signals — signal list with filters
• Authentication: Personal Access Tokens (PAT)
• Per-token rate limiting, feature toggle via settings

Architecture (v0.26.0+)

Frontend (React + TanStack Router + shadcn/ui)
    ↕ REST API
Go API (chi router, port 4010) — full HTTP layer
    ↕ Postgres job queues (LISTEN/NOTIFY)
Python workers — collector, analytics, analysis-worker,
                 refine-worker, lab-worker, admin-worker, embedding-svc

Legacy note: python-api FastAPI process was retired in May 2026
(Phase 3c6). All HTTP endpoints are now native Go; LLM/ML work
flows through dedicated worker processes via the jobs queue.

Backing storage: PostgreSQL + pgvector (prod) / SQLite WAL (dev).
    ├── Crawler → 5 source adapters → signals table
    ├── Scoring → source-aware + web citation enrichment
    ├── Classifier → LLM trend grouping + categorization → trends table
    ├── Scorer → 3D model (Significance/Momentum/Confidence) → recommendations
    ├── Analyzer → LangGraph + Claude → reports + impact zones
    ├── Recommendations → role-based actions (CTO/Dev/PM/Investor)
    ├── Translator → context-aware batch translation → translations table
    └── External API v1 → PAT auth + rate limiting
External:
    ├── SearXNG (self-hosted meta-search, Docker)
    ├── Claude API (Anthropic) — analysis + classification + translation
    └── pgvector — vector similarity (HNSW cosine; numpy fallback on SQLite)

Quick start

# 1. Clone and dependencies
git clone git@gitlab.dev.borisovai.tech:soft/trend-analisis.git
cd trend-analisis
python -m venv venv
venv\Scripts\activate          # Windows
pip install -r requirements.txt
cd frontend-cascade/app && npm install && cd ../..

# 2. Configuration
cp .env.example .env
# Required: ANTHROPIC_API_KEY, JWT_SECRET

# 3. Run (API :8000 + Frontend :5173)
python dev.py

More details: docs/guides/QUICKSTART.md

API

Full documentation: docs/api/ENDPOINTS.md

Tech stack

Documentation

License

Proprietary. All rights reserved.

Version: 0.8.0 | February 2026

Rendering aborted due to complexity issues. If this is valid markdown, please feel free to open an issue and attach the original markdown to the issue.