ToolAI.io · Канал GitHub

Популярные AI-проекты на GitHub

Отслеживайте активные AI-репозитории с открытым исходным кодом по темам LLM, агентов, MCP, RAG и программирования, с количеством звёзд и проверенными сведениями о проектах.

Данные публичного репозитория

Индекс проекта

118 Проекты
Скриншот Genkit: Open-Source Framework for Agentic AI Applications
Агенты и мультиагенты

Genkit: Open-Source Framework for Agentic AI Applications

genkit-ai/genkit

Genkit is an open-source framework built and used in production by Google's Firebase for developing full-stack, AI-powered applications. It provides cross-language SDKs and unified APIs for integrating various AI models to build chatbots, automations, and recommendation systems.

★ 6,3K⑂ 816TypeScript
Apache-2.0Q98
Скриншот Plano: AI-Native Proxy Server and Data Plane for Agentic Apps
Агенты и мультиагенты

Plano: AI-Native Proxy Server and Data Plane for Agentic Apps

katanemo/plano

Plano is an AI-native proxy server and data plane built in Rust that centralizes LLM routing, agent orchestration, observability, and guardrails, allowing developers to focus on core agent logic rather than infrastructure plumbing.

★ 7K⑂ 484Rust
Apache-2.0Q98
Скриншот TruLens: Evaluation and Tracking for LLM Experiments and AI Agents
Агенты и мультиагенты

TruLens: Evaluation and Tracking for LLM Experiments and AI Agents

truera/trulens

TruLens is an open-source, OpenTelemetry-native evaluation and tracking library for LLM applications and AI agents, enabling developers to trace every step, score performance with LLM judges, and compare app versions.

★ 3,5K⑂ 319Python
MITQ98
Скриншот QwenPaw
MCP и вызов инструментов

QwenPaw

agentscope-ai/qwenpaw

A self-hostable personal AI assistant that runs locally or in the cloud, featuring multi-channel connectivity, extensible skills, and a three-layer memory system.

★ 33,9K⑂ 3KPython
Apache-2.0Q98
Скриншот EvalScope
RAG и системы знаний

EvalScope

modelscope/evalscope

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

★ 3,2K⑂ 440Python
Apache-2.0Q98
Скриншот OpenAgents
Агенты и мультиагенты

OpenAgents

openagents-org/openagents

An open-source platform providing a collaborative operating system for AI agents, enabling unified workspace management, multi-agent coordination, and network integration without vendor lock-in.

★ 4K⑂ 403TypeScript
Apache-2.0Q98
Скриншот NVIDIA NeMo Speech
LLM и базовые модели

NVIDIA NeMo Speech

nvidia-nemo/speech

A scalable generative AI framework built for researchers and PyTorch developers working on Automatic Speech Recognition (ASR), Text-to-Speech (TTS), and Speech LLMs.

★ 17,9K⑂ 3,5KPython
Apache-2.0Q98
Скриншот Open SWE: An Open-Source Asynchronous Coding Agent by LangChain
Агенты и мультиагенты

Open SWE: An Open-Source Asynchronous Coding Agent by LangChain

langchain-ai/open-swe

Open SWE is an open-source framework for building internal coding agents. Built on LangGraph and Deep Agents, it provides cloud sandboxes, Slack/Linear/GitHub invocation, subagent orchestration, and automatic PR creation for engineering organizations.

★ 10,5K⑂ 1,2KPython
MITQ98
Скриншот BrowserOS: The Open-Source Agentic Browser
Агенты и мультиагенты

BrowserOS: The Open-Source Agentic Browser

browseros-ai/browseros

BrowserOS is a free, open-source Chromium fork with a built-in AI agent, accompanied by BrowserOS neo, a secondary browser designed specifically for AI agents. It enables local-first browser automation, supporting multiple LLM providers and MCP-compatible tools.

★ 12,9K⑂ 1,4KTypeScript
AGPL-3.0Q98
Скриншот Honcho
Агенты и мультиагенты

Honcho

plastic-labs/honcho

Memory infrastructure for building stateful AI agents that understand changing people, agents, groups, projects, and ideas over time.

★ 6,5K⑂ 788Python
AGPL-3.0Q98
Скриншот Headroom: Context Compression Layer for AI Agents
MCP и вызов инструментов

Headroom: Context Compression Layer for AI Agents

headroomlabs-ai/headroom

Headroom is a local-first context compression layer that reduces token usage for AI agents by compressing tool outputs, logs, files, and RAG chunks before they reach the LLM. It offers library, proxy, and MCP server modes and claims to preserve answer accuracy while cutting tokens by 15-95% depending on workload.

★ 65K⑂ 4,9KPython
Apache-2.0Q98
Скриншот Firecrawl
Агенты и мультиагенты

Firecrawl

firecrawl/firecrawl

An open-source web context API to search, scrape, and interact with the web at scale, converting web data into clean Markdown or structured JSON for AI agents and LLMs.

★ 161,1K⑂ 9,1KTypeScript
AGPL-3.0Q98

Страница 6 / 10 · 118 проектов

Недавно обновлено

cherry-studioCherryHQ/cherry-studio★ 51,5K siyuansiyuan-note/siyuan★ 46,2K career-opscareer-ops-hq/career-ops★ 70,2K tensorflowtensorflow/tensorflow★ 198,8K streamlitstreamlit/streamlit★ 45,7K pytorchpytorch/pytorch★ 102,8K

Наибольшее число звёзд

ECCaffaan-m/ECC★ 248,8K Hermes Agentnousresearch/hermes-agent★ 227,1K tensorflowtensorflow/tensorflow★ 198,8K AutoGPTSignificant-Gravitas/AutoGPT★ 187,1K ollamaollama/ollama★ 180,2K markitdown — Document conversion and extractionmicrosoft/markitdown★ 174,9K