AI directory search

Search across educators, skills, and resources.

Use this when you know the topic you need: Claude Code, MCP, evals, RAG, agents, product, coding, prompting, foundations, or model internals.

11 matches for "Open source"

Educators

Simon Willison profile photo

Simon Willison

Simon Willison on LLMs · Beginner to advanced

Consistently useful notes, demos, model comparisons, and warnings about practical LLM use without product marketing gloss.

Skills

LLM tools, Prompting, AI safety, Local models, Model selection

Mervin Praison profile photo

Mervin Praison

PraisonAI · Intermediate

A practical open-source builder path for learners who want agent patterns, examples, and tool integrations they can inspect directly.

Skills

AI agents, Multi-agent workflows, MCP, RAG, Open source

Providers and platforms

Arize AI profile photo

Arize AI

Phoenix · Intermediate

Useful for debugging and evaluating LLM applications once you move beyond prototypes.

Topics

Observability, Evals, Tracing, RAG debugging

Langfuse profile photo

Langfuse

Langfuse Docs · Intermediate

Good operational material for tracing, scoring, and improving production LLM apps.

Topics

Observability, Prompt management, Evals, Tracing

Promptfoo profile photo

Promptfoo

Promptfoo Docs · Intermediate

Very practical for regression testing prompts, model changes, and LLM outputs.

Topics

Prompt testing, Evals, Red teaming

Resources

LangChain Open Deep Research

GitHub repo · LangChain · Intermediate to advanced

You want a configurable open-source deep-research agent that works across search tools, MCP servers, and multiple model providers.

deep research, agents, mcp, search, multi-provider

PraisonAI

GitHub repo · Mervin Praison · Intermediate

You want an open-source agent framework with examples, tutorials, memory, RAG, and MCP support you can inspect directly.

agents, multi-agent workflows, mcp, rag, open source

Phoenix by Arize video thumbnail

Phoenix by Arize

Open source tool and docs · Arize AI · Intermediate

You need to trace, inspect, and evaluate LLM app behavior.

evals, observability, tracing

Promptfoo Intro video thumbnail

Promptfoo Intro

Open source docs · Promptfoo · Intermediate

You need regression tests for prompts, models, and LLM outputs.

evals, prompt testing, red teaming

Your First AI Agent: A Practical Guide to OpenClaw

Practical guide · Matthew Berman · Beginner to intermediate

Use this when you want a current agent walkthrough with a concrete tool and a faster path from reading to running something.

ai agents, open source, openclaw, tutorial, builder workflows

PraisonAI

GitHub repo · Mervin Praison · Intermediate

Use this when you want Mervin Praison's material for ai agents and related AI skills.

AI agents, Multi-agent workflows, MCP, RAG, Open source