AI on Radar
Subscribe
Topic intelligence

Cross-source radar trends, not isolated headlines.

Topics connect real clusters, entities, source mix, and published decisions. Empty states are real; no trend is invented when the signals are not strong enough yet.

Topics
8,995
current graph
Top trend
46
terrylica/cc-skills: Claude Code Skills Marketplace: plugins, skills for ADR-driven development, DevOps automation, ClickHouse management, semantic versioning, and productivity workflows
TopicCategorySignalsMomentumLast seenTrend
terrylica/cc-skills: Claude Code Skills Marketplace: plugins, skills for ADR-driven development, DevOps automation, ClickHouse management, semantic versioning, and productivity workflows
terrylica/cc-skills
Developer Tools161Jun 23, 2026Score46
amitpatole/agent-vision: Eyes for AI coding agents 👁️ — render → perceive → report → fix → re-render. A machine-graded visual feedback loop (DOM/contrast/OCR-grounded + optional vision LLM) agents consume to self-correct before claiming done.
amitpatole/agent-vision
Developer Tools161Jun 23, 2026Score46
Karan0310/prompt-architect: AI agent that generates LLM-specific prompts. 8 models, deep knowledge base, real-time streaming, agent refinement. Free, open source, runs in your browser.
Karan0310/prompt-architect
Developer Tools161Jun 23, 2026Score46
ajensenwaud/maturana: Maturana: secure, open-source personal agent platform built on Codex
ajensenwaud/maturana
Developer Tools161Jun 23, 2026Score46
PWDevens/job-search-ai-agent: A fully local, open-source job-search assistant powered by ChromaDB, CrewAI, and local LLMs (Phi-4-mini / Llama-3 / Mistral via Ollama). No cloud APIs. No data leaving your machine.
PWDevens/job-search-ai-agent
Developer Tools161Jun 23, 2026Score46
redeyefit/myndaix-runtime: A deterministic Python spine that orchestrates AI agents (CLI + API) over a durable ledger, with git-worktree isolation and capability-aware dispatch. Clone-and-run demo; design hardened by cross-family review.
redeyefit/myndaix-runtime
Developer Tools161Jun 22, 2026Score46
vkmtx/veil-mcp: Agent-native shell as an MCP server — quiet-by-default, addressable detail, effects-as-data, opt-in sandbox/trace. Built for LLM agents (Claude Code), not humans at a terminal.
vkmtx/veil-mcp
Developer Tools161Jun 22, 2026Score46
qte77/ai-agents-research: Field research and feature analysis for AI coding agents — sandboxing, orchestration, plugins, community tooling, SDLC patterns.
qte77/ai-agents-research
Developer Tools161Jun 22, 2026Score46
coder/blink: Blink is a self-hosted platform for building and running custom, in-house AI agents.
coder/blink
Developer Tools161Jun 22, 2026Score46
RyanDev1st/llm-and-engine: LLM tool-calling research workspace with training, evaluation, backend tools, and chess-engine demos.
RyanDev1st/llm-and-engine
Developer Tools161Jun 22, 2026Score46