MCP y llamadas a herramientas
thinkinaixyz/deepchat
DeepChat is an open-source, local-first AI agent desktop client built in TypeScript and Electron. It integrates cloud LLMs, local models, MCP services, installable Skills, ACP agents, and remote control for messaging apps, following the Tape.systems philosophy to keep agent sessions recoverable and inspectable.
★ 6,2K⑂ 712TypeScript
Apache-2.0Q98
Agentes y multiagente
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
Agentes y multiagente
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
LLM y modelos fundacionales
clearml/clearml
ClearML is an open-source MLOps/LLMOps suite providing auto-magical CI/CD to streamline AI workloads. It integrates experiment management, data management, pipeline orchestration, scheduling, and model serving into a single comprehensive platform.
★ 6,8K⑂ 789Python
Apache-2.0Q98
Agentes y multiagente
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
Agentes y multiagente
flyteorg/flyte
Flyte is an open-source orchestration framework for reliably building, scaling, and deploying machine learning pipelines, models, and agents using pure Python.
★ 7,2K⑂ 861Go
Apache-2.0Q98
Agentes y multiagente
omnigent-ai/omnigent
Omnigent is an open-source meta-harness that provides a unified orchestration layer for various AI coding agents, allowing users to swap harnesses, enforce governance policies, run cloud sandboxes, and collaborate in real-time across multiple devices.
★ 8,3K⑂ 1,3KPython
Apache-2.0Q98
Inferencia, implementación y tiempo de ejecución
xorbitsai/inference
A powerful and versatile library designed to serve language, speech recognition, and multimodal models. It allows users to swap GPT for any LLM by changing a single line of code and run models on cloud, on-prem, or locally via a unified, production-ready inference API.
★ 9,5K⑂ 853Python
Apache-2.0Q98
Agentes y multiagente
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
RAG y sistemas de conocimiento
lancedb/lancedb
An open-source, developer-friendly embedded retrieval library and multimodal AI lakehouse designed for fast, scalable, and production-ready vector search, built on the Lance columnar format.
★ 11,1K⑂ 994Rust
Apache-2.0Q98
Agentes y multiagente
dataelement/bisheng
BISHENG is an open-source LLM application DevOps platform designed for next-generation enterprise AI applications, offering comprehensive features like GenAI workflow orchestration, RAG, Agent management, and enterprise-grade system controls.
★ 11,8K⑂ 1,9KPython
Apache-2.0Q98
MCP y llamadas a herramientas
langchain4j/langchain4j
An idiomatic, open-source Java library for building LLM-powered applications on the JVM, offering a unified API over popular LLM providers and vector stores with support for tool calling, MCP, agents, and RAG.
★ 12,8K⑂ 2,4KJava
Apache-2.0Q98
