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
9,016
current graph
Top trend
45
SWE-agent/mini-swe-agent: The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
TopicCategorySignalsMomentumLast seenTrend
SWE-agent/mini-swe-agent: The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!
SWE-agent/mini-swe-agent
Developer Tools161Jun 29, 2026Score45
LeventeNagy/relay-coding-agent: Open-source desktop coding agent (Electron) with first-class support for non-mainstream/Chinese LLM providers — DeepSeek, Qwen, GLM, Kimi, MiniMax, and more. Chat + a full code workspace with file edits, scoped command execution, MCP plugins, and human-in-the-loop permissions. Early beta.
LeventeNagy/relay-coding-agent
Developer Tools161Jun 29, 2026Score45
netease-youdao/LobsterAI: Open-source, desktop-grade AI agent that gets real work done — data analysis, slides, docs, video & web research. Built on OpenClaw; runs tools on your real desktop and takes commands from your phone via WeChat, Feishu, DingTalk & Telegram.
netease-youdao/LobsterAI
Developer Tools161Jun 29, 2026Score45
gefsikatsinelou/MetaSearchMCP: Open-source metasearch backend, MCP server, and AI search API for LLM agents. Python FastAPI search gateway with Google search via SerpBase and Serper, multi-engine search aggregation, structured JSON output, provider fallback, deduplication, and SearXNG alternative architecture for agent workflows.
gefsikatsinelou/MetaSearchMCP
Developer Tools161Jun 29, 2026Score45
TangGV/hermes-self-iteration-skill: Hermes Agent self-iteration skill: autonomous analysis, improvement, verification, and continuous maturation.
TangGV/hermes-self-iteration-skill
Developer Tools161Jun 29, 2026Score45
inkatze/planwright: Autopilot for spec-driven development: a standalone, opinionated Claude Code framework
inkatze/planwright
Developer Tools161Jun 29, 2026Score45
agustinusnathaniel/maestria: Portable workflow patterns for Agents. Ships my learned best practices as a plugin so I don't have to re-teach them every session.
agustinusnathaniel/maestria
Developer Tools161Jun 29, 2026Score45
frkline/lemon: 🍋 Local macOS menu-bar agent that runs Claude Code from your Linear or GitHub issue queue, with on-device Gemma triage.
frkline/lemon
Developer Tools161Jun 28, 2026Score45
albertogrande/nema: AI-native docs platform: agents draft, humans approve, provenance is git-diffable data. Alpha.
albertogrande/nema
Developer Tools161Jun 28, 2026Score45
bounded-systems/prx: The agent-run work-unit CLI: capability-scoped agents whose every privileged effect is verified against its signed owner, driving a work unit through one signed pipeline to a merged PR.
bounded-systems/prx
Developer Tools161Jun 28, 2026Score45