Smoke dataset
A fixture dataset that exercises the ingestion, validation and freshness machinery.
4 tracked
Directory
Agent engineering frameworks
This directory tracks 18 open-source agent-engineering frameworks across GitHub activity, package downloads and release cadence. Every figure carries the source that reported it and the moment it was observed. Values that fail validation are withheld rather than shown, and the last verified snapshot stays on the page until a clean sync replaces it.
Live
300 fields
- github
- 142/142 current
- 4h
- npm
- 25/25 current
- 4h
- pypi
- 64/64 current
- 4h
- pypistats
- 0/15 current
- 4h
Moved since last reading
- LangChain
- +55
- 147,178
- LangGraph
- +50
- 42,384
- CrewAI
- +39
- 59,111
- DSPy
- +28
- 38,388
Stars from GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Movement is measured between two real observations; values that failed validation are withheld rather than shown.
- Frameworks
- 18
- Stars tracked
- 683,970
- With download data
- 10/18
- Last sync
- 4h agoquarantined
AgnoStars42,358+5GitHub REST API · 4h agoLettaStars24,923+25GitHub REST API · 4h agoDeepEvalStars18,476+20GitHub REST API · 4h agoRagasStars15,862+6GitHub REST API · 4h agoPydantic AIStars20,220+20GitHub REST API · 4h agosmolagentsStars29,530+24GitHub REST API · 4h agoMastraStars28,378+24GitHub REST API · 4h agoVercel AI SDKStars27,001+25GitHub REST API · 4h agoGuardrailsStars7,456+3GitHub REST API · 4h agoInstructorStars13,951+4GitHub REST API · 4h agoDSPyStars38,388+28GitHub REST API · 4h agoHaystackStars26,618+7GitHub REST API · 4h ago
| Select to compare | Framework | Stars | Downloads/wk | Last commit | Language | Licence | Open roles | 7-day stars | Checked |
|---|---|---|---|---|---|---|---|---|---|
| AgnoAgno | 42,358 | 520,626 | python | Apache-2.0 | — | 7-day stars: 7 readings, 42.3K to 42.4K. | Current4h ago | ||
| smolagentsHugging Face | 29,530 | 132,630 | python | Apache-2.0 | — | 7-day stars: 7 readings, 29.4K to 29.5K. | Current4h ago | ||
| Haystackdeepset | 26,618 | — | python | Apache-2.0 | 2 | 7-day stars: 7 readings, 26.6K to 26.6K. | Current4h ago | ||
| LettaLetta | 24,923 | — | python | Apache-2.0 | — | 7-day stars: 7 readings, 24.8K to 24.9K. | Current4h ago | ||
| DeepEvalConfident AI | 18,476 | — | python | Apache-2.0 | — | 7-day stars: 7 readings, 18.4K to 18.5K. | Current4h ago | ||
| RagasVibrant Labs | 15,862 | — | python | Apache-2.0 | — | 7-day stars: 7 readings, 15.8K to 15.9K. | Current4h ago | ||
| GuardrailsGuardrails AI | 7,456 | — | python | Apache-2.0 | — | 7-day stars: 7 readings, 7.4K to 7.5K. | Current4h ago |
Sources: GitHub REST API, npm registry downloads, PyPI registry metadata, pypistats.org downloads. Every value carries the moment it was observed; figures that failed validation are withheld rather than shown. SLA: current within 48h, ageing to 168h, stale beyond 336h.
indexable · canonical /frameworks?license=apache-2.0
Also tracked
Other datasets
Same engine, same provenance rules — every figure carries the source that reported it and when.
Language and embedding models
Language, embedding and speech models tracked across Hugging Face Hub download activity and OpenRouter context windows and pricing.
18 tracked
Local inference hardware
GPUs, accelerators and SoCs for running models locally, with VRAM, memory bandwidth, power draw and list price.
10 tracked