MakerAI Suite v3.3 — The AI Ecosystem for Delphi

🌐 Official Website: https://makerai.cimamaker.com

Free Pascal / Lazarus port available — Full port of MakerAI Suite for FPC 3.2+ (12 LLM drivers, RAG, Agents, MCP, Embeddings). See the fpc branch.

---

MakerAI is more than an API wrapper

Most AI libraries for Delphi stop at wrapping REST calls. MakerAI is different.

Yes, MakerAI includes native, provider-specific components that give you direct, full-fidelity access to each provider's API — every model parameter, every response field, every streaming event, exactly as the provider defines it.

But on top of that, MakerAI is a complete AI application ecosystem that lets you build production-grade intelligent systems entirely in Delphi:

• RAG pipelines (vector and graph-based) with SQL-like query languages (VQL / GQL)
• Autonomous Agents with graph orchestration, checkpoints, and human-in-the-loop approval
• MCP Servers and Clients — expose or consume tools using the Model Context Protocol
• Native ChatTools — bridge AI reasoning with deterministic real-world capabilities (PDF, Vision, Speech, Web Search, Shell, Computer Use)
• FMX Visual Components — drop-in UI for multimodal chat interfaces
• Universal Connector — switch providers at runtime without changing your application code

Whether you need a simple one-provider integration or a multi-agent, multi-provider, retrieval-augmented production system, MakerAI covers the full stack — natively in Delphi.

---

🚀 What's New in v3.3

TAiCapabilities — Unified Model Configuration System

The biggest architectural change in v3.3 is the TAiCapabilities system, which replaces scattered per-provider flags with a unified, declarative model of what each model can do and what a session needs:

• ModelCaps — what the model natively supports (e.g. [cap_Image, cap_Reasoning])
• SessionCaps — what capabilities the current session requires
• Gap analysis — when SessionCaps exceeds ModelCaps, MakerAI automatically activates bridges (tool-assisted OCR, vision bridges, etc.) without changing your code
• ThinkingLevel — unified reasoning depth control (tlLow, tlMedium, tlHigh) across all providers that support extended thinking

Models Updated (February 2026)

| Provider | New / Updated Models | |----------|----------------------| | OpenAI | gpt-5.2, gpt-image-1, o3, o3-mini | | Claude | claude-opus-4-6, claude-sonnet-4-6, claude-3-7-sonnet | | Gemini | gemini-3.0, gemini-2.5-flash, gemini-2.5-flash-image | | Grok | grok-4, grok-3, grok-imagine-image | | Mistral | Magistral (reasoning), mistral-ocr-latest | | DeepSeek | deepseek-reasoner (extended thinking) | | Kimi | kimi-k2.5 (extended thinking) |

Agents — Durable Execution & Human-in-the-Loop

• TAiFileCheckpointer — persists agent graph state to disk; resume workflows after crashes or restarts
• TAiWaitApprovalTool — suspends a node and waits for human approval before continuing
• TAIAgentManager.OnSuspend event for building approval UIs
• ResumeThread(ThreadID, NodeName, Input) to continue suspended workflows

RAG — Graph Document Management

• New uMakerAi.RAG.Graph.Documents.pas — full document lifecycle management (ingest, chunk, embed, link) directly into the knowledge graph

Cross-Provider Reasoning Fixes

• reasoning_content is now correctly preserved and re-sent in multi-turn tool call conversations for all providers that require it (DeepSeek-reasoner, Kimi k2.5, Groq reasoning models)

Other Additions

• TAiEmbeddingsConnection — abstract connector for swappable embedding providers
• TAiAudioPushStream — push-based audio streaming utility
• Demo 027 — Document Manager
• Demo 012 — ChatWebList (chat with web-based content)

---

🏗️ Architecture

┌──────────────────────────────────────────────────────────────────┐
│  Your Delphi Application                                         │
└────┬──────────────────┬─────────────────┬────────────────────────┘
     │                  │                 │
┌────▼────┐   ┌─────────▼──────────┐  ┌──▼────────────────────────┐
│ ChatUI  │   │ Agents             │  │ Design-Time               │
│ FMX     │   │ TAIAgentManager    │  │ Property Editors          │
│ Visual  │   │ TAIBlackboard      │  │ Object Inspector support  │
│ Comps   │   │ Checkpoint/Approve │  └───────────────────────────┘
└────┬────┘   └─────────┬──────────┘
     │                  │
┌────▼──────────────────▼──────────────────────────────────────────┐
│  TAiChatConnection  — Universal Connector                        │
│  Switch provider at runtime via DriverName property             │
└──────────────────────────────┬───────────────────────────────────┘
                               │
┌──────────────────────────────▼───────────────────────────────────┐
│  Native Provider Drivers  (direct API access, full fidelity)     │
│  OpenAI · Claude · Gemini · Grok · Mistral · DeepSeek · Kimi    │
│  Groq · Cohere · Ollama · LM Studio · GenericLLM                │
└──────────────────────────────┬───────────────────────────────────┘
                               │
     ┌─────────────────────────┼────────────────────────┐
     │                         │                        │
┌────▼────────┐   ┌────────────▼────────┐   ┌───────────▼─────────┐
│  ChatTools  │   │  RAG                │   │  MCP                │
│  PDF/Vision │   │  Vector (VQL)       │   │  Server (HTTP/SSE   │
│  Speech/STT │   │  Graph (GQL)        │   │  StdIO/Direct)      │
│  Web Search │   │  PostgreSQL/SQLite  │   │  Client             │
│  Shell      │   │  HNSW · BM25 · RRF  │   │  TAiFunctions bridge│
│  ComputerUse│   │  Rerank · Documents │   └─────────────────────┘
└─────────────┘   └─────────────────────┘

---

📡 Supported AI Providers

MakerAI gives you two ways to work with each provider, which you can mix freely:

Direct Provider Components

Full, provider-specific access to every API feature. Use when you need complete control:

| Component | Provider | Latest Models | |-----------|----------|---------------| | TAiOpenChat | OpenAI | gpt-5.2, o3, o3-mini | | TAiClaudeChat | Anthropic | claude-opus-4-6, claude-sonnet-4-6 | | TAiGeminiChat | Google | gemini-3.0, gemini-2.5-flash | | TAiGrokChat | xAI | grok-4, grok-3 | | TAiMistralChat | Mistral AI | Magistral, mistral-large | | TAiDeepSeekChat | DeepSeek | deepseek-reasoner, deepseek-chat | | TAiKimiChat | Moonshot | kimi-k2.5 | | TAiGroqChat | Groq | llama-3.3, deepseek-r1 | | TCohereChat | Cohere | command-r-plus | | TAiOllamaChat | Ollama | Any local model | | TAiLMStudioChat | LM Studio | Any local model | | TAiGenericChat | OpenAI-compatible | Any OpenAI-API endpoint |

Universal Connector

Provider-agnostic code. Switch models or providers by changing one property:

AiConn.DriverName := 'OpenAI';
AiConn.Model := 'gpt-5.2';
AiConn.ApiKey := '@OPENAI_API_KEY';  // resolved from environment variable

// Switch to Gemini without changing anything else
AiConn.DriverName := 'Gemini';
AiConn.Model := 'gemini-3.0-flash';
AiConn.ApiKey := '@GEMINI_API_KEY';

---

📊 Feature Support Matrix

| Feature | OpenAI (gpt-5.2) | Claude (4.6) | Gemini (3.0) | Grok (4) | Mistral | DeepSeek | Ollama | |:--------|:---:|:---:|:---:|:---:|:---:|:---:|:---:| | Text Generation | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | Streaming (SSE) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | Function Calling | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | JSON Mode / Schema | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | Image Input | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | | PDF / Files | ✅ | ✅ | ✅ | ⚠️ | ✅ | ❌ | ⚠️ | | Image Generation | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ | | Video Generation | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | | Extended Thinking | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⚠️ | | Speech (TTS/STT) | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ⚠️ | | Web Search | ✅ | ✅ | ✅ | ✅ | ❌ | ❌ | ❌ | | Computer Use | ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | | RAG (all modes) | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | MCP Client/Server | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | | Agents | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |

Legend: ✅ Native | ⚠️ Tool-Assisted bridge | ❌ Not Supported

---

🧩 Ecosystem Modules

🧠 RAG — Retrieval-Augmented Generation

Two complementary retrieval engines with their own query languages:

Vector RAG — semantic and hybrid search over document embeddings:

• HNSW index for approximate nearest-neighbor search
• BM25 lexical index for keyword matching
• Hybrid search with RRF (Reciprocal Rank Fusion) or weighted fusion
• Reranking and Lost-in-the-Middle reordering for LLM context
• VQL (Vector Query Language) — SQL-like DSL for complex retrieval queries:

  MATCH documents SEARCH 'machine learning'
  USING HYBRID WEIGHTS(semantic: 0.7, lexical: 0.3) FUSION RRF
  WHERE category = 'tech' AND date > '2025-01-01'
  RERANK 'neural networks' WITH REGENERATE
  LIMIT 10
  

• Drivers: PostgreSQL/pgvector, SQLite, in-memory

Graph RAG — knowledge graph with semantic search over entities and relationships:

• Nodes and edges wit