RepoRadar
Leave a Tip
Item detail

machinefi/trio-retina

machinefi/trio-retina is an Apache-2.0 Python framework that normalizes detections from YOLO, VLMs, Grounding DINO, and related perception models into one queryable world-state plus event stream, giving edge-AI, robotics, and video-analytics builders a shared middle layer instead of bespoke glue for every detector.

Open source →Back to radar
Score8.5
Popularity7.0
Riskconditional
TierSilver
Score breakdown
Usefulness8.0
Novelty8.0
Momentum7.0
Maturity6.3
Open-source/build8.4
Evidence7.2
Workflow potential9.6
Setup ease6.4

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for developers building camera, robotics, digital-twin, or edge-vision systems who need structured events and a stable interface between perception models and downstream logic.

Who should use it

edge-AI teams turning camera feeds into actionable eventsrobotics builders who want one stable perception interfacevideo-analytics developers who need webhook-friendly event streamsLLM or world-model experiments that need structured scene state instead of raw boxes

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

It can be pointed at live cameras or RTSP feeds, so privacy expectations and surveillance rules depend on how you deploy it.

Evidence links

Closest alternatives / related signals

computer-visionedge-aieventsroboticspython