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
A near-autonomous AI chemist improves a challenging reaction in medicinal chemistry
TopicCategorySignalsMomentumLast seenTrend
A near-autonomous AI chemist improves a challenging reaction in medicinal chemistry
No linked entity yet
Signals161Jun 17, 2026Score46
Spaider-studio/spaider: MCP-native knowledge-graph memory for AI agents
Spaider-studio/spaider
Developer Tools161Jun 17, 2026Score46
shenyangs/AgentBase: Local-first TypeScript agent runtime platform with traces, policy-gated tools, context snapshots, replay/eval, memory/wiki, Studio, and conformance tests.
shenyangs/AgentBase
Developer Tools161Jun 17, 2026Score46
Agent finder for GitHub Copilot now available
No linked entity yet
Signals161Jun 17, 2026Score46
avasol/galadriel-public: A self-hosted Claude agent that actually remembers — verbatim memory palace at zero retrieval cost, Discord + web UI, and 90%-cheaper repeat calls via prompt caching.
avasol/galadriel-public
Developer Tools161Jun 17, 2026Score46
OpenDCAI/One-Eval: Automated system for LLM evaluation via agents. Doc as below:
OpenDCAI/One-Eval
Developer Tools161Jun 17, 2026Score46
caltrackaiteam-pixel/make-claude-perform: The unified Claude Code framework — synthesizing the best of superpowers, everything-claude-code, GSD, claude-flow, and trailofbits into one non-conflicting harness
caltrackaiteam-pixel/make-claude-perform
Developer Tools161Jun 17, 2026Score46
josharsh/pixelpi: A minimal browser-agent harness - six tools, any model. pi for the browser.
josharsh/pixelpi
Developer Tools161Jun 17, 2026Score46
shyftai/GTMOS: GTM Operating System — outbound sales, lead gen, campaigns. Brief it. Build it. Ship it. Measure it.
shyftai/GTMOS
Developer Tools161Jun 17, 2026Score46
StewAlexander-com/continuous-ai: Give your local LLM a memory. A fully offline Ollama runtime that remembers across sessions, critiques its own answers, and can self-tune via LoRA — on Apple Silicon, no cloud.
StewAlexander-com/continuous-ai
Developer Tools161Jun 17, 2026Score46