Skip to content
Signals
deepseek-ai/deepseek-harness adds ~63,162 stars this week — breakout in TypeScriptTrendNexus signalsmattpocock/skills adds ~33,390 stars this week — breakout in ShellTrendNexus signalseternity4719/HowToLiveBetter adds ~18,590 stars this week — breakout in HTMLTrendNexus signalsgarrytan/gstack adds ~15,583 stars this week — breakout in TypeScriptTrendNexus signalsGraphify-Labs/graphify adds ~15,392 stars this week — breakout in PythonTrendNexus signalsodysseus-dev/odysseus adds ~12,736 stars this week — breakout in PythonTrendNexus signalsPanniantong/Agent-Reach adds ~12,010 stars this week — breakout in PythonTrendNexus signalsaddyosmani/agent-skills adds ~10,654 stars this week — breakout in JavaScriptTrendNexus signalsRisk watch: thedaviddias/Front-End-Checklist trends cooling with security score 90TrendNexus signalsRisk watch: meilisearch/meilisearch trends cooling with security score 88TrendNexus signalsHealthiest in cohort: puppeteer/puppeteer holds PVI 83 — sustainability leaderTrendNexus signals

livekit/agents

Establishedrank #199

A framework for building realtime voice AI agents 🤖🎙️📹

14.6k+194 · 7d 3.9k 219est. Apache-2.0Pythonpushed 1h ago
Compare View on GitHub

Composite

72

conf 65%

Momentum

61

conf 60%

Vitality (PVI)

74

conf 67%

Community

70

conf 60%

Security & maint.

87

conf 85%

Ecosystem influence

76

conf 60%

Opportunity

63

conf 60%

Breakout · 7d

34%

conf 71%

Executive summary

agents is currently classified as established with a composite score of 72/100. Momentum (61) and vitality (74) are aligned — growth is backed by sustained maintenance. Estimated 7-day gain of 194 stars against a 14.6k-star base. Risk is assessed as low; the interpretable model puts its probability of entering the top trend cohort within 7 days at 34%.

Video breakdown

@gptaiclips on YouTube
OpenAI Will Pay You $100K to Break Its AI Agents #shortsOpenAI Will Pay You $100K to Break Its AI Agents #shorts2mo agoI Gave Claude an Entire Reverse-Engineering Playbook #shortsI Gave Claude an Entire Reverse-Engineering Playbook #shorts2mo agoYour AI Model Isn't the Problem—Your Coding Harness IsYour AI Model Isn't the Problem—Your Coding Harness Is2mo ago

90-day trajectory

+985 · 30d
2026-07-112026-10-08

Score breakdown

Every input, weight and normalized value — nothing hidden. Inputs marked est. are estimated until the full ingestion pipeline lands.

Momentum

Star velocityest.25%64
Star accelerationest.15%42
Fork velocityest.10%56
Contributor growthest.10%92
Issue activity growthest.10%100
PR activity growthest.10%69
External mention velocityest.10%12
Release event impactest.5%68
Trending-rank persistenceest.5%49

Model tn-interpretable-1.0.0 · confidence 60% · coverage 100%

Project Vitality Index

Commit consistency20%100
Release cadenceest.15%57
PR responsivenessest.15%81
Issue responsivenessest.15%46
Contributor diversityest.10%87
Maintainer continuityest.10%73
Documentation qualityest.5%76
Dependency freshnessest.5%86
Security hygieneest.5%51

Model tn-interpretable-1.0.0 · confidence 67% · coverage 100%

Security & maintenance

Release recency25%100
License clarity20%92
Maintenance status25%100
Dependency stalenessest.15%46
Bus factorest.15%78

Model tn-interpretable-1.0.0 · confidence 85% · coverage 100%

Ecosystem influence

Dependent repositoriesest.30%88
Quality-weighted dependentsest.20%58
Documentation citationsest.15%68
Contributor overlapest.15%69
Registry adoptionest.10%75
Topic centralityest.10%100

Model tn-interpretable-1.0.0 · confidence 60% · coverage 92% · missing: packageRegistryAdoption