AI / LLM radar: agents and agent frameworks
Momentum based on available 7-day snapshots for AI / LLM: measured with two snapshots, estimated otherwise. Each value shows its own source window. This page reads stored snapshots only.
Radar filters
Tool ranking
Mixed ranking: measured growth takes priority; entries without two snapshots are estimated. Raw values keep their source-specific window, shown under each tool; a change requires at least two snapshots from the last 7 days.
- 1Active
cumora
AgentWhere agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.
githubmeasured growthOpen source ↗
3 430GitHub stars+249 (+7.8 %) - 2Active
taste-skill
AgentTaste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
githubmeasured growthOpen source ↗
82 205GitHub stars+643 (+0.79 %) - 3Active
Vibe-Research
AgentVibe-Research: Your Personal Trading Research Agent · A股/美股/港股 的个人投研 Agent:每日复盘、资讯雷达、个股数据、板块中心、我的持仓、研究记录、回测。Vibe-Research 把数据和功能配齐,由你自己的 Agent 驱动投资研究。基于开源的 Codex Harness 打造。
githubmeasured growthOpen source ↗
2 318GitHub stars+120 (+5.5 %) - 4Active
TradingAgents
AgentTradingAgents: Multi-Agents LLM Financial Trading Framework
githubmeasured growthOpen source ↗
102 338GitHub stars+440 (+0.43 %) - 5Active
LlamaFactory
AgentUnified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
githubmeasured growthOpen source ↗
74 511GitHub stars+26 (+0.03 %) - 636 578GitHub stars—
Learning resources
Ranked by measured growth, normalized across sources. These resources remain available separately and do not take part in the main tool ranking.
- 1ActiveOpen source ↗
learn-claude-code
AgentBash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
githubResourcemeasured growth75 687GitHub stars+196 (+0.26 %)