ToolAI.io · Chaîne GitHub

Nouveaux projets AI sur GitHub

Découvrez les nouveaux projets AI open source ajoutés sur GitHub, avec les informations du dépôt, les instructions de configuration, les licences et les ressources associées.

Données du dépôt public

Index du projet

130 Projets
Capture d’écran de OpenConnector
MCP et appels d’outils

OpenConnector

oomol-lab/open-connector

An open-source authentication gateway that connects over 1,000 SaaS providers to AI agents through SDK, CLI, MCP, HTTP, and OpenAPI interfaces.

★ 4,1K⑂ 311TypeScript
Apache-2.0Q98
Capture d’écran de trigger.dev
MCP et appels d’outils

trigger.dev

triggerdotdev/trigger.dev

An open-source platform for building and deploying fully-managed AI agents and workflows in TypeScript, featuring long-running tasks, retries, queues, observability, and elastic scaling.

★ 15,9K⑂ 1,4KTypeScript
Apache-2.0Q98
Capture d’écran de EvalScope
RAG et systèmes de connaissances

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
Capture d’écran de Neo.mjs
MCP et appels d’outils

Neo.mjs

neomjs/neo

A self-evolving software organism that combines a multi-threaded frontend application engine with an end-to-end AI engineering team operating via cross-model swarm coordination, persistent memory, and runtime application embodiment.

★ 3,3K⑂ 231JavaScript
MITQ98
Capture d’écran de ReMe: Memory Management Kit for Agents
Agents et multi-agents

ReMe: Memory Management Kit for Agents

agentscope-ai/reme

ReMe is a local-first memory layer for AI agents that transforms conversations and resources into readable, editable, and searchable Markdown memory files.

★ 3,3K⑂ 283Python
Apache-2.0Q98
Capture d’écran de TruLens: Evaluation and Tracking for LLM Experiments and AI Agents
Agents et multi-agents

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
Capture d’écran de Atmosphere: Real-Time Transport and Governance Framework for JVM AI Agents
MCP et appels d’outils

Atmosphere: Real-Time Transport and Governance Framework for JVM AI Agents

atmosphere/atmosphere

Atmosphere is a Java-based real-time framework for building, streaming, and governing AI agents. It provides a unified broadcaster pipeline for WebSocket, SSE, long-polling, and gRPC, alongside built-in governance, human-in-the-loop workflows, and multi-protocol support including MCP, A2A, and AG-UI.

★ 3,8K⑂ 760Java
Apache-2.0Q98
Capture d’écran de OpenAgents
Agents et multi-agents

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
Capture d’écran de CSGHub: Open-Source LLM Asset Management Platform
Agents et multi-agents

CSGHub: Open-Source LLM Asset Management Platform

opencsgs/csghub

CSGHub is an open-source, on-premise platform for managing the full lifecycle of Large Language Model assets, including models, datasets, spaces, and code, offering functionality comparable to a private Hugging Face.

★ 4,2K⑂ 525Vue
Apache-2.0Q98
Capture d’écran de ha-mcp: The Unofficial Home Assistant MCP Server
MCP et appels d’outils

ha-mcp: The Unofficial Home Assistant MCP Server

homeassistant-ai/ha-mcp

A comprehensive Model Context Protocol (MCP) server enabling AI assistants to interact with, configure, build, and debug Home Assistant smart home setups using natural language.

★ 4,3K⑂ 177Python
MITQ98
Capture d’écran de Lemonade: Local AI Server for GPU and NPU Inference
MCP et appels d’outils

Lemonade: Local AI Server for GPU and NPU Inference

lemonade-sdk/lemonade

Lemonade is an open-source local AI server that enables users to run optimized Large Language Models (LLMs), speech, and image generation models directly on their own GPUs and NPUs, providing a free and private alternative to cloud APIs.

★ 5,2K⑂ 436C++
Apache-2.0Q98
Capture d’écran de Potpie
Agents et multi-agents

Potpie

potpie-ai/potpie

Potpie transforms a codebase and software development lifecycle into a living context graph for AI agents, indexing code, structure, decisions, source history, and team knowledge to enable context-aware coding, planning, and debugging.

★ 5,5K⑂ 642Python
Apache-2.0Q98

Page 1 / 11 · 130 projets

Récemment mis à jour

codex — Coding agent and developer workflowsopenai/codex★ 106,5K NemoClaw — Agent runtime and deployment toolingNVIDIA/NemoClaw★ 22,2K XERJxerj-org/xerj★ 1,4K LangWatchlangwatch/langwatch★ 3,5K OrchestKityonatangross/orchestkit★ 222 hal0hal0ai/hal0★ 67

Les plus étoilés

Hermes Agentnousresearch/hermes-agent★ 227,1K markitdown — Document conversion and extractionmicrosoft/markitdown★ 174,2K skills — Reusable agent skills and workflowsanthropics/skills★ 169,9K Hugging Face Transformershuggingface/transformers★ 163,3K Firecrawlfirecrawl/firecrawl★ 161,1K LangChainlangchain-ai/langchain★ 143,6K