MakerAI Suite v3.7 — The AI Ecosystem for Delphi

🌐 Official Website: https://makerai.cimamaker.com 📖 Manual: https://www.gustavoenriquez.com/book-makerai — available in English and Spanish

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 (dual-era: stateless spec 2026-07-28 + legacy handshake)
• 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 v3.7

Computer Use, Refreshed on Both Live Providers

Both vendor APIs changed under our feet, and one of them had gone silently dead. Claude was broken: the driver still declared computer_20251124, a tool type the Anthropic API now rejects for every model. It is now computer_toolset_20260801, which takes no parameters and explodes the old single computer tool into 17 individually named tools. OpenAI joins natively with gpt-6-astra and the parameterless computer tool, which sends a whole batch of actions per turn — the driver runs them in order and answers with one final screenshot.

Both APIs converged on the same design: the tool declares no screen dimensions (the model infers them from the screenshot) and coordinates come back as pixels of the image you sent.

GLM (Zhipu AI / Z.ai) — New Provider

TAiGLMChat brings a 14th provider: OpenAI-compatible endpoint, explicit thinking control (the API ships it ON by default, the driver decides), reasoning_content captured and re-sent across turns, and free tiers (glm-4.7-flash, glm-4.6v-flash).

Correctness Pass

RAG on pgvector (OFFSET was trimming instead of paginating; the vector did not survive the round trip), token and cache accounting across OpenAI, Claude and MakerAi streams, a race where the model travelled through the global registry, tool-calling continuation off the main thread, and reasoning no longer leaking into the user-visible answer.

---

What's New in v3.6

MCP Specification 2026-07-28 — Stateless, Dual-Era

The Model Context Protocol dropped sessions and the initialize handshake. MakerAI implements the new stateless revision on both sides and keeps talking to legacy peers: clients probe with server/discover and fall back automatically; the server serves modern per-request _meta requests statelessly while the legacy handshake and session gating keep working. Includes the MRTR pattern, so a tool can pause and ask the user for confirmation (OnInputRequired on the client, TAiAuthContext.InputResponses on the server).

Observability — OpenTelemetry Tracing

TAiTelemetry exports OTLP traces to any standard collector (Jaeger, Grafana Tempo, Langfuse, Arize Phoenix) following the GenAI semantic conventions. Spans cover chat turns with token usage, tool executions, agent graphs and nodes, RAG retrieval and MCP requests — with W3C traceparent propagated through MCP _meta, so a client and a server in different processes share one distributed trace. Opt-in, zero overhead when disabled.

A2A — Agent-to-Agent Protocol (first Delphi implementation)

If MCP is the agent-to-tool layer, A2A (Linux Foundation) is the agent-to-agent layer. TAiA2AServer publishes any agent graph as a standard A2A agent (Agent Card + JSON-RPC), TAiA2AClient consumes remote agents, and TAiA2ARemoteAgentTool federates: a node in your graph can delegate its work to a remote agent — including one written in another language or framework. Demo: 072-A2AFederation.

Guardrails & Evals

TAiGuardrails intercepts every tool call before it executes (allowlists, blocklists, forbidden argument patterns, programmatic veto) — blocked calls never run and the LLM gets the reason so it can replan. TAiEvalRunner brings systematic evaluation: fluent test cases against any target, deterministic checks plus optional LLM-as-judge, with ToJSON reports for CI.

First Automated Regression Suite

Tests/RegressionSuite/ — 17 in-process cases covering MCP, agents, A2A, guardrails and evals. No API keys, under a second, exit code for CI. Built on TAiEvalRunner itself.

---

What's New in v3.5

Typed ModelConfig Channel

Capability configuration now lives in a single typed surface: ModelConfig.ModelCaps / SessionCaps / Tool_Active / ThinkingLevel moved out of the string-based Params/RTTI channel, with per-field user pins and transparent compatibility migration — existing code keeps working unchanged.

Full-Duplex Voice Suite

• TAiGrokRealtimeChat — xAI Grok Voice speech-to-speech (function calling, session resumption with replay, binary audio transport, ephemeral tokens)
• TAiOpenAiRealtimeTranslate — continuous streaming speech translation (one WebSocket per direction; demo 071-VoiceBridgeTranslate)
• TAiRealtimeVoiceBase — shared full-duplex base; voice events flow through the universal TAiRealtimeConnection
• gpt-transcribe / gpt-live-transcribe — OpenAI's Whisper successors, fully integrated

August 2026 Provider Refresh — All 9 Cloud Providers, Runtime-Tested

Claude 5 family (adaptive thinking, FastMode, compaction, server-side fallbacks) · Gemini 3.5/3.6 + Nano Banana GA · Mistral Voxtral TTS + OCR 4 · Kimi K3 · DeepSeek V4 (explicit thinking control) · Cohere Command A+ · Groq qwen3.6 · xAI grok-4.3/4.5/build — with retired-model cleanup and compatibility aliases throughout.

Grok Native Video & Image Generation

TAiGrokChat now generates video with grok-imagine (async job + polling + mp4 as TAiMediaFile, new VideoDurationSeconds property) and images with grok-imagine-image — activated by cmVideoGeneration/cmImageGeneration or the [cap_GenVideo]/[cap_GenImage] gaps.

---

What's New in v3.4

Delphi 13.1 Florence Support

v3.4 is fully tested and compatible with Delphi 13.1 Florence (CompilerVersion 37.1), in addition to the existing range from Delphi 10.4 Sydney through Delphi 13 Florence.

Selective Driver Registration

The biggest infrastructure change in v3.4: TAiChatConnection no longer force-loads all providers at startup. Each driver now self-registers only when explicitly imported, eliminating unnecessary initialization overhead:

// Load only what you need
uses uMakerAi.Chat.AiConnection, uMakerAi.Chat.OpenAi, uMakerAi.Chat.Claude;

// Load all drivers at once (legacy behavior)
uses uMakerAi.Chat.Initializations;

Real-Time STT — TAiRealtimeConnection

New universal connector for real-time speech-to-text via WebSocket:

• TAiRealtimeConnection — provider-agnostic STT connector; switch providers via DriverName
• TAiOpenAiRealtimeSTT — full OpenAI Realtime API implementation (24 kHz PCM16, VAD modes, streaming transcription)
• Pure-Pascal WebSocket client with native TLS via Windows SChannel — no extra DLLs required
• Thread-safe PCM16 resampler; supports push-based audio streaming from any source

GPT-Transcribe — Next-Gen OpenAI Transcription (Whisper successors) 🆕

OpenAI's new transcription models (Aug 2026) are fully integrated — better accuracy on real-world audio, accents, numbers, specialized terminology and loud background noise:

Model	Use case	Word Error Rate
gpt-live-transcribe	Live low-latency STT (Realtime WebSocket)	9.60% (vs 11.65% Whisper)
gpt-transcribe	Completed files and batch workloads	8.98% (vs 15.21% Whisper)

• TAiOpenAiRealtimeSTT now defaults to gpt-live-transcribe, with new context properties: TranscriptionPrompt (free-form topic), TranscriptionKeywords (domain terms), Languages (multi-language guided autodetection) and LowDelay
• TAiOpenAiAudio gains tmGptTranscribe / tmGptLiveTranscribe with TranscriptionKeywords + TranscriptionLanguages for REST/batch transcription
• Legacy models (whisper-1, gpt-4o-transcribe) remain available — they're still required for subtitles (SRT/VTT), word timestamps and diarization (gpt-4o-transcribe-diarize), which the new models don't support; the components degrade formats safely per model
• VoiceBridge demos (062–065) migrated: live channels use gpt-live-transcribe with contextual prompts and guided language detection; diarized channels stay on gpt-4o-transcribe-diarize

Grok Voice — Real-Time Speech-to-Speech (xAI) 🆕

Full-duplex voice conversation with xAI's Grok Voice models (grok-voice-think-fast-2.0) over a single WebSocket — the user speaks, Grok listens, reasons and answers back with voice:

• TAiGrokRealtimeChat — complete driver for wss://api.x.ai/v1/realtime (OpenAI Realtime-compatible protocol, 24 kHz PCM16)
• TAiRealtimeVoiceBase — new base class for full-duplex voice drivers; adds OnAssistantText, OnAssistantTextDelta, OnAudioChunk, OnAudioDone (shared with TAiMakerAiRealtimeChat)
• Live user transcription (OnTranscriptDelta / OnTranscriptCompleted), server VAD, streamed assistant text and TTS audio
• Function calling by voice: assign a TAiFunctions component (local functions + MCP) and Grok invokes your Delphi code mid-conversation — the driver handles the whole round-trip (execution on worker threads, function_call_output, continuation)
• xAI native tools: EnableWebSearch / EnableXSearch — executed server-side by xAI
• Session options: Voice (eva, ara, rex, sal, leo or custom voice_id), Instructions, ReasoningEffort (high / none for lower latency), OutputSpeed, Keyterms (transcription biasing), PronunciationReplace (TTS corrections), automatic regional language hints (es→es-MX, pt→pt-BR)
• ForceMessage() — scripted TTS utterance bypassing the model (IVR prompts, disclosures)
• Session resumption: EnableResumption + ConversationId — reconnect and the server replays the cached turns (transcripts, tool calls and outputs; 30-min window)
• Binary audio transport: BinaryAudio := True — raw PCM over WebSocket binary frames, ~33% less bandwidth than base64
• Ephemeral tokens for mobile/browser clients: MintEphemeralToken() on your backend + EphemeralToken on the client — the API key never leaves the server
• file_search over xAI Collections (FileSearchCollections) and remote MCP servers via CustomToolsJson
• Works through TAiRealtimeConnection too — just set DriverName := 'Grok'

uses uMakerAi.Realtime.AiConnection, uMakerAi.Realtime.Grok;

Voice := TAiRealtimeConnection.Create(nil);
Voice.DriverName   := 'Grok';
Voice.ApiKey       := '@GROK_API_KEY';
Voice.Language     := 'es';
Voice.OnTranscriptCompleted := HandleUserText;   // what the user said
Voice.OnAssistantText       := HandleGrokText;   // what Grok answered
Voice.OnAudioChunk          := HandleGrokAudio;  // Grok's voice (PCM16 24 kHz)
Voice.Connect;
// ... stream microphone audio via Voice.SendAudioChunk(Data) ...
// For file-based audio (non-continuous), close the turn explicitly:
// Voice.CommitAudio; TAiGrokRealtimeChat(Voice.Instance).CreateResponse;

cmSmartDispatch — Intelligent Chat Routing

New ChatMode value for automatic two-pass routing:

• Pass 1 — classifies the user intent and rewrites the prompt for the target capability (image generation, speech synthesis, web search, etc.)
• Pass 2 — dispatches to the appropriate bridge or tool based on classification
• Works with all existing ChatTools (IAiImageTool, IAiSpeechTool, IAiWebSearchTool, etc.)

Models Updated (May 2026)

Provider	New / Updated Models
OpenAI	gpt-5.4, gpt-5.4-mini, gpt-5.5, gpt-image-1
Claude	claude-opus-4-7 (Adaptive Thinking), claude-sonnet-4-6, claude-haiku-4-5
Gemini	gemini-3.1-pro, gemini-3-flash, gemini-3.1-flash-lite, gemini-3.1-flash-image
Grok	grok-4-fast, grok-3, grok-code-fast-1
Mistral	magistral-medium/small, devstral, voxtral
Groq	llama-4-scout/maverick, kimi-k2, qwen3, compound-beta
Kimi	kimi-k2, kimi-k2.5, kimi-k2-thinking
Cohere	command-a-03-2025, command-a-reasoning, command-a-vision

Agent Improvements

• TAiAgentManager.Run declared virtual — proper subclassing now supported
• jmAll join node fix — FJoinInputs cleared after each execution; eliminates premature firing on retries and loops
• TChatInput.EnterAsSend — new property (default False): Enter sends the prompt, Shift+Enter / Ctrl+Enter inserts a line break
• TChatBubble — eliminated spurious vertical scrollbar (ShowScrollBars := False)

Bug Fixes

• Claude Opus 4.7 Adaptive Thinking — temperature, top_p, top_k and the thinking block are now correctly omitted for claude-opus-4-7 models. Anthropic manages sampling internally for these models; sending these parameters caused HTTP 400 errors.
• RegisterDefaultParams — Max_Tokens key — corrected in 10 drivers (Claude, Gemini, Mistral, Groq, DeepSeek, Grok, Kimi, LMStudio, GenericLLM, Ollama). The wrong key MaxTokens was never resolved by RTTI to the Max_tokens property, causing Max_Tokens to be silently ignored when set via RegisterDefaultParams.
• ApplyParamsToChat — locale-independent float parsing — TryStrToFloat now tries invariant format (dot decimal) first, then falls back to the system locale. Both Temperature=0.7 and Temperature=0,7 are valid regardless of regional settings.

Bug Fixes (March 2026)

• MCP concurrent tool calls — race condition (uMakerAi.MCPClient.Core.pas): When a model responded with two or more tools from the same MCP server in a single turn, ParseChat launched all tool calls as parallel TTasks. Since TMCPClientStdIo shares a single process/pipe per instance (no synchronization), concurrent calls corrupted the JSON-RPC communication, causing intermittent failures. Fixed by adding FCallLock: TCriticalSection to TMCPClientCustom — calls to the same server are now serialized while calls to different servers still run in parallel.

• EAggregateException on tool errors — Claude driver (uMakerAi.Chat.Claude.pas): The local _CreateTask procedure in TAiClaudeChat.ParseChat lacked the try/except present in the base class. Any exception raised inside a tool task (MCP timeout, network error, etc.) escaped unhandled, causing TTask.WaitForAll to wrap it in an EAggregateException and crash the application. Fixed to match base class behavior: exceptions are caught, reported via OnError, and the tool receives an error response so the conversation can continue.

---

🏗️ 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    │
│  GLM · 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 │   └─────────────────────┘
└─────────────┘   └─────────────────────┘

┌──────────────────────────────────────────────────────────────────┐
│  Realtime Voice — parallel WebSocket stack                       │
│  TAiRealtimeConnection · OpenAI STT · Grok Voice S2S · MakerAI   │
│  Pure-Pascal RFC 6455 + TLS (SChannel / OpenSSL / Android)       │
└──────────────────────────────────────────────────────────────────┘

---

📡 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-6-astra, gpt-5.6-sol/-terra/-luna, gpt-5.5, gpt-image-1
TAiClaudeChat	Anthropic	claude-opus-5, claude-sonnet-5, claude-fable-5, claude-haiku-4-5
TAiGeminiChat	Google	gemini-3.5-flash, gemini-3.6-flash, gemini-3.1-pro
TAiGrokChat	xAI	grok-4.3, grok-4.5, grok-build, grok-imagine (image/video)
TAiMistralChat	Mistral AI	mistral-large/medium/small, magistral, devstral, voxtral (STT/TTS)
TAiDeepSeekChat	DeepSeek	deepseek-v4-flash, deepseek-v4-pro
TAiKimiChat	Moonshot	kimi-k3, kimi-k2.7-code, kimi-k2.6
TAiGLMChat	GLM (Zhipu / Z.ai)	glm-4.7, glm-5.3, glm-5v-turbo, free tiers: glm-4.7-flash / glm-4.6v-flash
TAiGroqChat	Groq	llama-3.3-70b, openai/gpt-oss-120b, qwen3.6, whisper-large-v3
TCohereChat	Cohere	command-a-plus, command-a-03-2025, north-mini-code
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-5.6';
AiConn.ApiKey := '@OPENAI_API_KEY';  // resolved from environment variable

// Switch to Gemini without changing anything else
AiConn.DriverName := 'Gemini';
AiConn.Model := 'gemini-3.6-flash';
AiConn.ApiKey := '@GEMINI_API_KEY';

// Or to GLM (Zhipu / Z.ai) — glm-4.7-flash is free
AiConn.DriverName := 'GLM';
AiConn.Model := 'glm-4.7-flash';
AiConn.ApiKey := '@GLM_API_KEY';

---

📊 Feature Support Matrix

Feature	OpenAI (gpt-6-astra)	Claude (5)	Gemini (3.6)	Grok (4.5)	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)	✅	❌	✅	❌	❌	❌	⚠️
Realtime Voice (WebSocket)	✅ STT	❌	⚠️	✅ S2S	❌	❌	❌
Web Search	✅	✅	✅	✅	❌	❌	❌
Computer Use ¹	✅	✅	⚠️	❌	❌	❌	❌
RAG (all modes)	✅	✅	✅	✅	✅	✅	✅
MCP Client/Server	✅	✅	✅	✅	✅	✅	✅
Agents	✅	✅	✅	✅	✅	✅	✅

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

¹ Computer Use is opt-in. cap_ComputerUse hands the model the real mouse and keyboard, so no model enables it by default — you add the capability yourself (see the Computer Use section below). Native support: OpenAI gpt-6-astra; Claude claude-opus-4-8 / -opus-5 / -sonnet-5 / -fable-5. Gemini is marked ⚠️ because the registry still points at the gemini-2.5-computer-use-preview model, which has not been re-verified since the 3.5/3.6 generation shipped.

---

🧩 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 with embeddings and metadata
• MakerGQL — Graph Query Language based on ISO/IEC 39075:2024 (GQL standard):

  MATCH (p:Person)-[r:WORKS_AT]->(c:Company)
  WHERE c.city = 'Madrid' DEPTH 2
  RETURN p, r, c
  

• Dijkstra shortest path, centrality analysis, hub detection
• Export to GraphViz DOT, GraphML (Gephi), native JSON format
• Document lifecycle management (ingest → chunk → embed → link)

🤖 Agents — Autonomous Orchestration

Graph-based multi-agent workflows with full thread safety:

• **`TAIAgentMana