skill
Agent Skills Specification
An open format for packaging instructions and resources that agents can discover and apply.
Catalog
One record. Every relevant type.
Search 48 reviewed records without duplicating projects across categories.
48 records
app + agent
cfker01 Operations Worker
A Cloudflare management Worker for health, status aggregation, audit events, API keys, and MCP access.
app + agent
Claude Code
An agentic coding tool that works from the terminal and integrates with development workflows.
skill + agent
Model Context Protocol Servers
Reference implementations and community servers that expose tools and resources through MCP.
app + agent
OpenAI Codex
A coding agent for software development tasks across local tools, repositories, and cloud workflows.
app + agent
OpenHands
An open-source platform for software development agents that work through code, terminals, and browsers.
benchmark
SWE-bench
A benchmark for evaluating language models on real software engineering issues from open-source repositories.
app
TableAI Catalog
A reviewed directory of AI applications, skills, agents, benchmarks, and technical writing.
benchmark
Terminal-Bench
A benchmark for measuring AI agents on practical tasks completed in terminal environments.
benchmark
AgentBench
A benchmark suite designed to evaluate language models acting as agents across varied environments.
app + agent
Aider
An open-source pair programming agent designed to edit code in local Git repositories.
app + benchmark
Arize Phoenix
An open-source observability and evaluation platform for language-model and machine-learning applications.
skill + agent
Browser Use
An open-source library that connects AI agents to browser automation workflows.
benchmark + agent
BrowserGym
A framework and benchmark family for evaluating web agents in browser-based environments.
app + agent
Cline
An open-source coding agent that operates inside Visual Studio Code with user-approved tool actions.
app + agent
Continue
An open-source platform for building and using AI coding assistants in developer environments.
skill + agent
CrewAI
A framework for coordinating role-based AI agents, tasks, tools, and production workflows.
skill + benchmark
DeepEval
An open-source evaluation framework for testing language-model systems with metrics and datasets.
app + agent
Dify
An open-source platform for composing, deploying, and operating language-model applications and agents.
app + agent
Flowise
An open-source visual platform for building language-model workflows and agent systems.
app + skill
Gradio
An open-source Python library for creating web interfaces and demos for machine-learning models.
skill
Guardrails AI
A framework and hub for validating, constraining, and monitoring language-model inputs and outputs.
skill + agent
Haystack
An open-source framework for production retrieval, search, question-answering, and agent pipelines.
app
Helicone
An open-source observability platform for monitoring and analyzing language-model application traffic.
app + skill + benchmark
Inspect AI
An open-source framework for building and running language-model evaluations.
skill
Instructor
A library for obtaining validated structured outputs from language models using typed application schemas.
skill + agent
LangChain
A framework and ecosystem for building applications that use language models, tools, retrieval, and agents.
app + agent
Langflow
A visual framework for creating and serving AI workflows with reusable Python components.
app + benchmark
Langfuse
An open-source platform for traces, prompt management, evaluations, metrics, and datasets for LLM applications.
skill + agent
LangGraph
A low-level orchestration framework for stateful, controllable agents and long-running workflows.
app + skill
LiteLLM
A model gateway and SDK that provides a consistent interface across many language-model providers.
skill + agent
LlamaIndex
A framework for connecting language-model applications and agents to private and external data.
app + benchmark
LM Evaluation Harness
A framework for evaluating language models across a broad collection of academic tasks.
skill + agent
Microsoft AutoGen
A framework for creating agentic AI applications with single-agent and multi-agent patterns.
app + agent
n8n
A workflow automation platform with extensible integrations and AI-oriented nodes and agents.
app
Ollama
A local runtime and command-line application for downloading and running language models.
app
Open WebUI
A self-hosted web interface for interacting with local and remote language-model services.
skill + agent
OpenAI Agents SDK
A lightweight SDK for agent loops, tools, handoffs, guardrails, sessions, and tracing.
app + benchmark
OpenAI Evals
An open-source framework and registry for evaluating language models and model systems.
benchmark
OSWorld
A benchmark for multimodal agents that operate full computer environments through visual interaction.
skill + agent
Playwright MCP
An MCP server that gives agents structured browser automation through Playwright accessibility data.
app + benchmark
Promptfoo
An open-source command-line and web toolkit for testing prompts, models, agents, and red-team scenarios.
skill + agent
Pydantic AI
A Python agent framework built around typed dependencies, structured outputs, tools, and model portability.
skill + benchmark
Ragas
An open-source framework for evaluating retrieval-augmented generation systems and AI workflows.
skill + agent
Semantic Kernel
A model integration SDK for building agents and AI applications in several programming languages.
app + skill
Streamlit
An open-source Python framework for rapidly building interactive data and AI applications.
agent + benchmark
SWE-agent
A research system that enables language models to resolve software engineering tasks in repositories.
benchmark
WebArena
A realistic web environment for evaluating autonomous agents on reproducible tasks.
No matching records
Clear one or more filters to broaden the catalog.