frameworks
Agent engineering frameworks
Open-source frameworks for building, orchestrating and evaluating LLM agents, tracked across GitHub, npm and PyPI.
- Tracked
- 18
- GitHub stars tracked
- 698,018
- GitHub REST API
- Last sync
- 2h ago · quarantined
Agent engineering, measured
Every figure here says where it came from
buildagentic tracks 46 open-source frameworks, language models and inference machines across 7 sources. Every value resolves to the source that reported it, the moment it was observed, and how it was measured. A figure that fails validation is withheld rather than shown — withheld means we refused to publish it, not that it is zero.
- Datasets
- 3
- Tracked entities
- 46
- Sources
- 7
- Last observation
- 1h agoappend-only
AgnoStars43,100+13GitHub REST API · 2h agoLettaStars25,382+11GitHub REST API · 2h agoDeepEvalStars19,359+18GitHub REST API · 2h agoRagasStars16,259+5GitHub REST API · 2h agoPydantic AIStars21,085+18GitHub REST API · 2h agosmolagentsStars30,260+18GitHub REST API · 2h agoMastraStars29,400+14GitHub REST API · 2h agoVercel AI SDKStars27,805+16GitHub REST API · 2h agoGuardrailsStars7,587+1GitHub REST API · 2h agoInstructorStars14,101+2GitHub REST API · 2h agoDSPyStars38,971+7GitHub REST API · 2h agoHaystackStars26,943+4GitHub REST API · 2h agoSemantic KernelStars28,745+4GitHub REST API · 2h agoAutoGenStars61,743+7GitHub REST API · 2h ago
models
Language and embedding models
Language, embedding and speech models tracked across Hugging Face Hub download activity and OpenRouter context windows and pricing.
- Tracked
- 18
- downloads, 30 days
- 56,610,638
- Hugging Face Hub
- Last sync
- 2h ago
hardware
Local inference hardware
GPUs, accelerators and SoCs for running models locally, with VRAM, memory bandwidth, power draw and list price.
- Tracked
- 10
- GB of VRAM catalogued
- 792
- Last sync
- 1h ago
Biweekly
What changed, and what it means
New roles, the movements worth noticing across the datasets, and the occasional note on what broke. No filler.