33.8KGitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “multi-modal-llms”
1–16 / 18
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 18
10KGitHub
Nori Skillsets
tilework-tech
System for managing collections of agent skills. Switch between skillsets seamlessly!
148GitHub
136GitHub
365GitHub
Mlflow
mlflow
The open source AI engineering platform for agents, LLMs, and ML models. MLflow enables teams of all sizes to debug, evaluate, monitor, and optimize production-quality A…
26.7KGitHub
OpenLLM
bentoml
Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.
12.4KGitHub
BentoML
bentoml
The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
CodingSkill source unconfirmed
8.7KGitHub
Claude Codex Bridge
SeemSeam
Visible multi-agent CLI workspace for mixing Codex, Claude, Gemini, Kimi, Qwen, Cursor, Copilot, Pi, OpenCode, and other AI coding agents
3KGitHub
Smallcode
Doorman11991
AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.
CodingSkill source unconfirmed
1.9KGitHub
Spacebot
spacedriveapp
An AI agent for teams, communities, and multi-user environments.
CodingSkill source unconfirmed
2.3KGitHub
OpenMonoAgent.AI
StartupHakk
(BETA) AI shouldn't have a meter. Unlimited tokens. Forever. Your machine. Your agent. Use it from anywhere. Terminal-native coding agent powered by local LLMs — 100% op…
CodingSkill source unconfirmed
1.6KGitHub
Agentic Coding Flywheel Setup
Dicklesworthstone
Bootstraps a fresh Ubuntu VPS into a complete multi-agent AI development environment in 30 minutes: coding agents, session management, safety tools, and coordination inf…
CodingSkill source unconfirmed
1.5KGitHub
Kimchi
getkimchi
Terminal coding agent powered by Kimchi's multi-model orchestration
CodingSkill source unconfirmed
1.3KGitHub
code-review-and-quality
addyosmani
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code…
90.4KGitHub
run-load-test
omnigent-ai
Run the Omnigent load test and produce a results file explaining the latencies. Load when the user wants to load-test / stress-test / benchmark Omnigent under concurrenc…
9.6KGitHub