Hierarchical agent loops with recursive self-organization.
Open-source проекты ИИ
Подборка заметных open-source проектов в области ИИ на GitHub: LLM, агенты, RAG, локальное развёртывание, изображения и речь… Всего проектов: 1047.
Ищете проекты, которые можно бесплатно развернуть на Cloudflare, Vercel, Netlify и других платформах? Смотрите Бесплатный деплой: подборка
Все 1047🧠 Большие языковые модели 26🤖 ИИ-агенты 164🧩 Платформы разработки приложений 23📚 RAG и базы знаний 46💬 Чат-интерфейсы и клиенты 41🖥️ Локальный инференс и развёртывание 87👨💻 ИИ для программирования 99🛠️ Фреймворки и SDK 47🔌 MCP и экосистема инструментов 34🎨 Генерация изображений 25🎬 Генерация видео 17🎙️ Речь и аудио 44👁️ Компьютерное зрение 28📄 Разбор документов и парсинг 24🗄️ Векторные базы данных 25🏋️ Обучение, дообучение и MLOps 75🧪 Оценка, наблюдаемость и безопасность 81🚪 API-шлюзы и прокси 12🔎 Поиск и глубокие исследования 15⚙️ Библиотеки глубокого обучения 56🏷️ Данные и разметка 31🔬 ИИ для отраслей и науки 34⚡ Инструменты для повышения продуктивности 13
Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool
Track AI API quotas across Synthetic, Z.ai, Anthropic (Claude Code), Codex, GitHub Copilot & Antigravity in real time. Lightweight background daemon (<50MB RAM), SQLite storage, Material Design 3 dashboard. Zero telemetr
Automated modeling and machine learning framework FEDOT
LLMFlows - Simple, Explicit and Transparent LLM Apps
Open-source self-hosted AI agent runtime and multi-agent framework for autonomous agent swarms. Agent memory, MCP tools, schedules, delegation, and 23+ LLM providers (Claude, GPT, Gemini, OpenRouter, Ollama). A practical
Self-hosted AI Agents Platform for AI Native companies. Claude Code, Codex, Gemini, OpenCode agents. Apache 2.0.
Open weights language model from Google DeepMind, based on Griffin.
Your thinking deserves a map: an infinite canvas where LLM conversations grow into an editable thought graph. Wires are the context.
Jarvis AI Assistant - Voice-powered AI assistant for Mac
Think before doing, prove before saving. Vestige is a local, deterministic safety kernel for AI agents. Every memory write and agent action is recorded in Strata, an append-only log, so you can see exactly what your agen
Create 🐍 Python AI Actions and 🤖 Automations, and deploy & operate them anywhere
Context Engine for your long-running AI agents
The fastest developer workflow for every AI coding agent. Live status, quick prompts, worktrees, and diff review from one tmux TUI.
Open framework for confidential AI
AI gateway with multi-channel agents, with own billing and monitoring.
Open-source database & workspace for AI agents — structured data, durable knowledge, reusable skills, runnable apps, and human review on the writes that matter. Local-first and self-hostable.
Open Model Engine (OME) — Kubernetes operator for LLM serving, GPU scheduling, and model lifecycle management. Works with SGLang, vLLM, TensorRT-LLM, and Triton
Multi-harness control plane for Claude Code, Codex, Cursor, and OpenCode: quota-aware rotation across multiple Claude/Codex subscriptions, shared thread context, and cross-model review.
Electronic invoice processing and reimbursement preparation tools: collect PDF/OFD/XML invoices from mailbox batches, identify OCRs, classify archives and generate Excel aggregates; provide Windows/macOS desktop with DSH plugins.
The action firewall for AI agents. Enforce policy and human approval before risky tool calls, shell commands, workflows, and production changes, with auditable evidence.
Caura (formerly MemClaw) — governed shared memory for AI agent fleets. Multi-agent, multi-tenant, MCP-native. Trust tiers, keystone policies, audit trails, knowledge graph, self-improving retrieval. Apache 2.0.
Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.
Cut AI context cost without trusting the compressor. Every reduction is reversible, byte-exact recoverable, and carries an auditable receipt. Local-first, works through proxy, MCP, SDK, or agent wrapper.