Front page / Concepts
Concepts
The ideas behind today’s AI tools: what each one is, how to use it today in ChatGPT or Claude, where it goes wrong, and which listings use it well.
01
Where each one stands
Our judgment of each idea's standing, with the GitHub stars its repositories gained this week as bars.
Established · 7
- MCP and tool use+4.8k
- Agentic loops+1.2k
- Knowledge graphs (GraphRAG)+1.2k
- Retrieval (RAG)+1.2k
- Prompt engineering+1.1k
- Vibe coding+835
- Workflows, not agents+543
Rising · 7
- Spec-driven work+16k
- Agent skills+6.9k
- Memory+6.4k
- Multi-agent orchestration+5.5k
- Computer use+5.2k
- Context engineering+3.4k
- Evals and verification+914
02
Rising
Adopted faster each month; the vendors are building for it and new tools keep appearing.
| Concept | What it is | Since | Stars, week | Listings |
|---|---|---|---|---|
| Context engineering | The model only knows what is in front of it. | 2025-06 | +3.4k6 repositories | 6 |
| Agent skills | A skill is a folder with a short description and instructions, sometimes with reference files and scripts, that an assistant loads only when the description matches what you asked. | 2025-10 | +6.9k5 repositories | 5 |
| Multi-agent orchestration | Instead of one assistant doing everything in one context, several agents take roles: one plans, others research or write in parallel, one reviews. | 2025-06 | +5.5k5 repositories | 6 |
| Memory | By default every chat starts from nothing. | 2025-04 | +6.4k6 repositories | 6 |
| Evals and verification | An eval is a check you run on the assistant's output, repeatedly, so you know how often it is right instead of remembering the last time. | 2025-04 | +9144 repositories | 5 |
| Computer use | A computer use agent sees the screen and clicks, types and scrolls like a person, so it can work in any website or app that has no connector: filling forms, pulling numbers from a dashboard, checking a competitor's checkout flow. | 2025-07 | +5.2k6 repositories | 6 |
| Spec-driven work | Write down what you want before anything gets built: the goal, the constraints, the acceptance criteria, the open questions. | 2025-07 | +16k6 repositories | 6 |
03
Established
Settled practice: the methods are known, the tools are mature, and the question is how well you use it.
| Concept | What it is | Since | Stars, week | Listings |
|---|---|---|---|---|
| MCP and tool use | Tool use is the model calling a function instead of guessing: look this up, run this query, create this ticket. | 2025-06 | +4.8k6 repositories | 6 |
| Agentic loops | An agent is a model running in a loop: it plans, takes a step, looks at what happened, and decides the next step, until the job is done or it is stuck. | 2025-04 | +1.2k5 repositories | 5 |
| Workflows, not agents | A workflow is a fixed sequence of steps where the model fills in each step: classify the ticket, draft the reply, check the tone, file it. | 2024-12 | +5435 repositories | 5 |
| Retrieval (RAG) | Retrieval augmented generation means the assistant looks things up in your documents before answering, and answers from what it found rather than from memory. | 2023-11 | +1.2k6 repositories | 6 |
| Knowledge graphs (GraphRAG) | Documents are flat; the things in them are connected: this customer uses that feature, which this ticket is about, which that decision changed. | 2024-07 | +1.2k6 repositories | 6 |
| Prompt engineering | Crafting the wording of a request so the model answers well: role statements, step by step instructions, examples, output formats. | 2025-06 | +1.1k5 repositories | 5 |
| Vibe coding | Vibe coding is building software by describing what you want to an AI and letting it write the code, often without reading the code yourself. | 2025-11 | +8354 repositories | 4 |
Placement here is editorial and never paid, and nothing on this page moves a listing's rank.