ai-agents

A curated full-stack LLM engineering playbook — from AI infrastructure and model lifecycle to agents, MCP, memory, and evaluation.

Production-ready microservices framework for AI inference over RPC. It provides a Gateway for client requests, an Orchestrator that schedules work, a Registry for model metadata, Workers that run inference, and a full observability stack (Prometheus, Grafana, Loki, Jaeger) — all wired together with Docker Compose.

Deterministic context database for AI agents. Same query → same context, every time.

Persistent memory and identity protocol for AI systems with evidence-aware recall and inspectable memory.

Memory architectures that evolve with your agent

CLI, MCP server, and TypeScript library that extracts text, layout, and page images from PDFs for AI agents — when extraction goes wrong, it says so per page and says what to do next.

Production-ready memory framework for AI agents. Dual-agent synthesis, self-evolution, composite scoring, multi-tenant isolation. REST API, Python SDK, CLI.

Lightning-fast RAG for AI agents. ONNX-powered, 4-layer fusion, MCP server. No PyTorch.

A standalone memory engine for AI agents in .NET, with hybrid retrieval, graph memory, pluggable providers, and behavior-shaped memories.

The blazingly fast in-memory vector database 🚀

The Anal-Queen of AI Browser Automation 🏴‍☠️ A beautifully fucked-up Skynet-powered browser automation script that harnesses neural brainfuck and machine learning chaos to give zero shits about anything while somehow still working perfectly.

Token-lean web microfetch for LLM agents: any URL → clean markdown via CLI, MCP server, and Claude Code plugin. Real browser-cookie auth, passkeys, anti-bot reach, on-by-default prompt-injection defense, plus on-device multimodal ASR/OCR. A single Rust binary — not a browser.

AOI: a model-agnostic perception layer giving computer-use agents adaptive video + audio perception with zero retraining, plus DynaCU-Bench (100 dynamic browser tasks). Paper + benchmark + code.

CLI for exporting Claude Code/Codex sessions to Hugging Face with privacy redaction, MCP memory, and share-ready dataset workflows.

AI-native NoSQL + vector database with built-in semantic search for RAG, AI agents & LLM memory — the async Python client. Self-hosted Pinecone alternative.

Automated comic cataloging tool that identifies issues directly from cover images using a vision-language model, then cross-references results with the Grand Comics Database and the ComicVine API to generate structured, high-confidence collection data with minimal manual entry.

📞 Локальный AI-секретарь, тех. поддержка и менеджер по продажам с клонированием голоса XTTS v2, real-time распознаванием речи (Vosk/Whisper) и offline LLM (vLLM + Qwen/Llama и тп). Полноценная админ-панель (Vue 3), Telegram-бот, виджет для сайта, fine-tuning pipeline. Self-hosted, приватность данных, СМС и телефонные звонки .