MCP y llamadas a herramientas
astrbotdevs/astrbot
AstrBot is an open-source, all-in-one AI agent chatbot platform and development framework that integrates mainstream instant messaging platforms, large language models, plugins, and agent capabilities for building production-ready conversational AI applications.
★ 38,5K⑂ 2,7KPython
AGPL-3.0Q98
Agentes y multiagente
run-llama/llama_index
LlamaIndex is an open-source Python data framework for building LLM applications with private data, offering data connectors, indexing structures, and advanced retrieval interfaces. It is complemented by LlamaParse, an enterprise platform for agentic OCR, parsing, extraction, and indexing.
★ 51,4K⑂ 7,9KPython
MITQ98
MCP y llamadas a herramientas
mempalace/mempalace
A local-first, open-source AI memory system that stores conversation history and project files as verbatim text for semantic retrieval, achieving 96.6% R@5 on LongMemEval without requiring LLMs or API calls.
★ 58K⑂ 7,5KPython
MITQ98
Agentes y multiagente
mem0ai/mem0
Mem0 is an open-source memory layer for AI agents and assistants, enabling personalized, long-term memory across user sessions. It provides multi-level memory retention, hybrid retrieval, and temporal reasoning through Python and npm SDKs, a self-hosted server, or a managed cloud platform.
★ 62,5K⑂ 7,3KPython
Apache-2.0Q98
Agentes y multiagente
mintplex-labs/anything-llm
An all-in-one, local-first AI application for chatting with documents, building AI agents, and running a private, multi-user ChatGPT-like experience with zero setup friction.
★ 64,5K⑂ 7,1KJavaScript
MITQ98
MCP y llamadas a herramientas
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
Agentes y multiagente
openhands/openhands
A self-hosted developer control center for running, managing, and automating coding agents across local, remote, and cloud environments.
★ 83,1K⑂ 10,7KTypeScript
MITQ98
Agentes y multiagente
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
Inferencia, implementación y tiempo de ejecución
huggingface/transformers
A model-definition framework for state-of-the-art machine learning models across text, vision, audio, and multimodal domains, supporting both inference and training.
★ 163,3K⑂ 34,1KPython
Apache-2.0Q98
Agentes y multiagente
infiniflow/ragflow
RAGFlow is an open-source Retrieval-Augmented Generation engine that combines document ingestion, retrieval, grounded citations, configurable language and embedding models, and agent capabilities to provide context for LLM applications.
★ 86,7K⑂ 10,2KGo
Apache-2.0Q98
MCP y llamadas a herramientas
maximhq/bifrost
Bifrost is a Go-based AI gateway that provides a unified, OpenAI-compatible API for 23+ AI providers. It supports routing, fallbacks, load balancing, semantic caching, governance, observability, multimodal requests, plugins, and Model Context Protocol integrations.
★ 7K⑂ 984Go
Apache-2.0Q98
Ajuste fino, entrenamiento y datos
oumi-ai/oumi
Oumi is a Python-based platform for preparing data, training and fine-tuning open-weight foundation models, evaluating results, running inference, and deploying models. It provides configuration recipes and a consistent CLI for local, cluster, and cloud workflows.
★ 9,4K⑂ 784Python
Apache-2.0Q98