Agent engineering frameworks
Open-source frameworks for building, orchestrating and evaluating LLM agents, tracked across GitHub, npm and PyPI.
18 tracked
Directory
Smoke dataset
The smoke dataset tracks five fixture projects across stars, contributors and licence. Every figure carries the source it came from 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
12 fields
- smoke
- 0/12 current
- 704h
Moved since last reading
Nothing changed between the last two readings.
Stars from Smoke fixture. Movement is measured between two real observations; values that failed validation are withheld rather than shown.
- Projects
- 4
- Stars tracked
- 3,185
- Last sync
- 29d agoquarantined
Bravo OrchestratorStars980Smoke fixture · 1mo agoAlpha RuntimeStars1,420Smoke fixture · 1mo agoCinder EvalStars610Smoke fixture · 1mo agoEcho GatewayStars175Smoke fixture · 1mo ago
No hiring column here. The job-board classifier extracts framework names, so the join can only speak about frameworks — for these entities we have not measured demand, rather than measured it to be zero.
| Project | Stars | Contributors | Licence | Checked |
|---|---|---|---|---|
| Bravo Orchestratorbravo | 980 | 24 | Apache-2.0 | Stale1mo ago· past SLA |
Source: Smoke fixture. Every value carries the moment it was observed; figures that failed validation are withheld rather than shown. SLA: current within 24h, ageing to 72h, stale beyond 168h.
noindex,follow · canonical /data/smoke
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