computer vision agents

52 tagged computer vision, measured the same way as everything else here.

Browse within: agent-tools 27ffmpeg 27Multi-Agent 13marketplace 13vlm 9RAG 6video-analytics 6video-search 6

gstreamer

01

NVIDIA-AI-Blueprints/video-search-and-summarization

Agent Claude Code

GStreamer and media pipeline specialist for VIOS. Use for questions about pipeline construction, element selection, caps negotiation, buffer handling, GStreamer best practices, debugging pipeline issues, and NVIDIA DeepStream/NvEnc/NvDec integration.

1.8k 2d ago A 51 tokens

vios-api

02

NVIDIA-AI-Blueprints/video-search-and-summarization

Agent Claude Code

VIOS REST API agent. Queries a running VIOS/VST backend over HTTP to list sensors, fetch recording timelines, download clips, capture snapshots, add/delete sensors and RTSP streams, and upload video files. Use whenever the user wants to interact with VIOS data via its REST API rather than through the UI or source code.

1.8k 2d ago A 71 tokens

vios-release-note

03

NVIDIA-AI-Blueprints/video-search-and-summarization

Agent Claude Code

Generate a complete VIOS multi-arch release note for a given build drop version. Fetches container images from GitLab compose.env files, commit titles from GitLab between the previous release tag and HEAD, Jira VST tickets, NVBugs entries, Slack channel evidence, and Outlook email evidence, then renders a formatted…

1.8k 2d ago A 285 tokens

agent-zero

04

oxbshw/watch-skill

Agent

Agent "agent-zero" from oxbshw/watch-skill, covering watch skill in agent zero, install, configure, smoke test (3 steps) and notes.

320 yesterday A 0 tokens original MIT

aider

05

oxbshw/watch-skill

Agent

Agent "aider" from oxbshw/watch-skill, covering watch skill in aider, install, use it, a recording of a bug and notes.

320 yesterday A 0 tokens original MIT

jetbrains

06

oxbshw/watch-skill

Agent

Agent "jetbrains" from oxbshw/watch-skill, covering watch skill in jetbrains ides, install, configure junie, configure ai assistant and smoke test (3 steps).

320 yesterday A 0 tokens original MIT

kornia/bubbaloop

Agent

Use when the user wants to extend bubbaloop's daemon, MCP server, RBAC, agent runtime, or tool set — adding a new MCP tool, modifying tier mapping, extending the multi-agent runtime, working on the alignment-notes gaps, or refactoring core internals. Knows the crate layout, rmcp 0.15 macro syntax, the…

28 2mo ago A 102 tokens original Apache-2.0

kornia/bubbaloop

Agent

Use when the user wants to create, scaffold, validate, or refactor a bubbaloop node (sensor/actuator/processor/gateway). Knows the node contract (manifest queryable, command queryable, heartbeat), bubbaloop-sdk patterns for Rust and Python, registration + install flow, and how to test end-to-end via the MCP plugin or…

28 2mo ago A 86 tokens original Apache-2.0

bubbaloop-operator

09

kornia/bubbaloop

Agent

Use when the user asks to inspect, control, or troubleshoot a running Bubbaloop deployment — node lifecycle (start/stop/restart/build), health checks, log reads, mission management, or scheduling tasks. Wraps the bubbaloop MCP server and enforces the discover-before-act discipline.

28 2mo ago A 67 tokens original Apache-2.0

paper-researcher

10

mxslr/mlcraft

Agent

Read-only research agent that finds, reads, and critically appraises academic papers and benchmarks for an ML/AI task. Returns a structured literature brief - SOTA methods, the realistic accuracy/AUC ceiling, dataset pitfalls, and which reported numbers are likely inflated by data leakage or ROI-cropping. Use during…

8 1mo ago A 87 tokens original MIT

cv-problem-solver

11

Borda/vision-delivery

Agent

Computer-vision problem solver. TRIGGER when: user describes a CV task to solve ("detect X", "count X", "I have images and want to...", "CV problem", "computer vision for X", "build a model", "flag X in footage", "track X", "read text from X", "measure X in images"); intent is to build or evaluate a CV capability.…

4 21d ago A 174 tokens original Apache-2.0

Borda/vision-delivery

Agent

Computer-vision economics consultant. TRIGGER when: user invokes $estimate-economics in Codex or /sentinel:estimate-economics in Claude Code, asks for annotation or labeling cost, training cost, managed vs self-hosted cost, build-vs-buy, scale economics, deployment crossover, or selected the "managed at scale" /…

4 21d ago A 172 tokens original Apache-2.0

job-evaluator

13

southlab-ai/Claude-Plugin-Marketplace

Agent

Evaluates Upwork jobs for red flags, client quality, budget fairness, and fit before applying. Use when the user asks "is this job worth it", "should I apply", "evaluate this job", "check this posting", or wants to compare multiple jobs.

2 27d ago A 58 tokens original MIT

profile-reviewer

14

southlab-ai/Claude-Plugin-Marketplace

Agent

Reviews and optimizes your Upwork profile against current market demand. Use when the user asks to "review my profile", "optimize my profile", "improve my Upwork profile", "what should I change on my profile", or wants to align their profile with market trends.

2 27d ago A 61 tokens original MIT

proposal-writer

15

southlab-ai/Claude-Plugin-Marketplace

Agent

Crafts tailored Upwork proposals for specific job postings. Use when the user wants help writing a proposal, cover letter, or application for an Upwork job. Trigger with "write a proposal", "help me apply", "draft a cover letter", or when discussing a specific job they want to apply to.

2 27d ago A 66 tokens original MIT