By sergesha
AI-powered technology scout: monitors news via SearXNG, stores summaries with semantic search in Redis, generates HTML dashboards.
Collect tech news for configured topics. Searches SearXNG, summarizes, classifies (kind), scores match % and theme temperature, stores in Redis, and writes a timestamped JSON data document. HTML/YAML views are produced separately by scripts (render-dashboard / export_yaml.py).
Interactively create or edit a tech radar topic configuration. Asks the user to describe a technology, proposes keywords/queries, runs probe searches to validate, and saves a YAML config.
Render a Tech Radar HTML dashboard from a collect-news JSON data document by running the bundled render.py script. Use when the user asks to build, generate, or refresh the dashboard.
Show a stored Tech Radar result in a requested format (JSON default, or YAML/HTML). Defaults to the latest run; with a date, returns the run closest to it. Runs the bundled show.py script and returns its output — usable by humans and by external agents requesting results over a2adapt.
External network access
Connects to servers outside your machine
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
AI-powered technology scout for Claude Code: monitors news and research across the web for topics you configure, scores and stores them with semantic search, and renders an interactive HTML dashboard.
This repository is both a Claude Code marketplace (.claude-plugin/marketplace.json)
and the plugin it ships (plugin/).
/plugin marketplace add sergesha/claude-tech-radar
/plugin install tech-radar@tech-radar
Or auto-enable per project in .claude/settings.json:
{
"enabledPlugins": { "tech-radar@tech-radar": true },
"extraKnownMarketplaces": {
"tech-radar": { "source": { "source": "github", "repo": "sergesha/claude-tech-radar" }, "autoUpdate": true }
}
}
plugin/docker-compose.yaml:
SearXNG + Dragonfly cache) and starts it on session start via a hook (using
${CLAUDE_PLUGIN_ROOT}), so it is self-contained.python3 (standard library only — used by the render/export/show scripts).redis-memory-mcp server (semantic memory) self-installs on first use./tech-radar:configure-topic — create or edit a topic to monitor/tech-radar:collect-news — collect fresh news → canonical reports/radar-<ts>.json/tech-radar:render-dashboard — build the interactive HTML dashboard (Alpine + Tailwind)/tech-radar:show-result — show a stored run as JSON / YAML / HTML (latest or closest to a date)The plugin ships an example topic at plugin/examples/local-llm.yaml. Your own
topics live in your project's topics/*.yaml (not in this repo). Each topic
defines its description, keywords, queries, languages, optional preferred sources,
research_keywords (adjacent theory), and optional positioning (for competitive
stance classification).
Releases are automated with release-please:
Conventional Commits on main drive the version bump + CHANGELOG, and merging the
release PR tags vX.Y.Z and updates both plugin/.claude-plugin/plugin.json and
.claude-plugin/marketplace.json.
npx claudepluginhub sergesha/claude-tech-radar --plugin tech-radarPersistent cross-session memory for AI agents. Two storage modes: semantic vector search (mem_*) for knowledge found by meaning, and key-value store (kv_*) for instant lookup. Auto-expiry via TTL + volatile-lru eviction.
Memory compression system for Claude Code - persist context across sessions
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.