🐙TakoAPI

Marketplace des agents

Une seule API pour accéder à tous les agents. Découvrez et invoquez des agents IA via une API unifiée — décrits par des AgentCards A2A ouvertes.

mcp-memory-service

projet

Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.

🧰Frameworks d'agents🧩Backend
doobidoo/mcp-memory-serviceauto-héberger1.9k

dbos-transact-py

projet

Database-Backed Durable Python Workflows

🧩Backend🧰Frameworks d'agents
dbos-inc/dbos-transact-pyauto-héberger1.6k

philoagents-course

projet

When Philosophy meets AI

🧩Backend🧰Frameworks d'agents
neural-maze/philoagents-courseauto-héberger1.5k

GPT-RAG

projet

Enterprise-grade accelerator for agentic RAG on Azure. Built on Microsoft Foundry with Foundry IQ as the default retrieval backend, Microsoft Agent Framework orchestration, Zero-Trust architecture and IaC.

🧰Frameworks d'agents🔍Recherche et exploration
Azure/GPT-RAGauto-héberger1.2k

dockit

projet

Agentic desktop GUI client for Elasticsearch, OpenSearch, DynamoDB, MongoDB & EasySearch. Natural language queries, visual management, and monitoring. Privacy-first. Open source.

🧩Backend🧰Frameworks d'agents
geek-fun/dockitauto-héberger1.1k

JamAIBase

projet

The collaborative spreadsheet for AI. Chain cells into powerful pipelines, experiment with prompts and models, and evaluate LLM responses in real-time. Work together seamlessly to build and iterate on AI applications.

🔍Recherche et exploration🎨Frontend
EmbeddedLLM/JamAIBaseauto-héberger1.1k

pgGraph

projet

Open-source graph database superpowers for your existing Postgres data.

🧩Backend🧰Frameworks d'agents
Evokoa/pgGraphauto-héberger1k

dante-cloud

projet

🐉 Dante Cloud 国内首个支持阻塞式和响应式服务并行的微服务云原生基座。采用领域驱动模型(DDD)设计思想,以「高质量代码、低安全漏洞」为核心,高度模块化和组件化设计,支持IoT等物联网设备认证,满足国家三级等保要求、支持接口国密数字信封加解密等系列安全体系的多租户微服务解决方案。独创的“一套代码实现微服务和单体两种架构灵活切换”的企业级微服务平台。🔝🔝 点个star 持续关注更新!

🎨Frontend🧩Backend
dromara/dante-cloudauto-héberger943

loom

projet

一个写接口文档的AI Agent。支持使用Vibe coding 的方式,编写接口文档,同时自带友好的文档查看工具与接口Mock工具

💻Code et développement🧩Backend
husu/loomauto-héberger939

agentlabs

projet

Universal AI Agent Frontend. Build your backend we handle the rest.

🎨Frontend🧩Backend
agentlabs-dev/agentlabsauto-héberger556

EVA

projet

EVA is an AI-assisted penetration testing agent that enhances offensive security workflows by providing structured attack guidance, contextual analysis, and multi-backend AI integration.

🧩Backend
ARCANGEL0/EVAauto-héberger527

BookWorm

projet

The practical implementation of Aspire using Microservices, AI-Agents

🧩Backend🧰Frameworks d'agents
foxminchan/BookWormauto-héberger505

peerd

projet

The first AI agent harness native to the browser. A browser extension that runs a full agent loop where you already work: it drives your tabs, spins up sandboxed compute (JS notebooks, WASM Linux VMs, client-side apps), and shares what it builds peer-to-peer. BYOK, no backend, no telemetry.

🧰Frameworks d'agents🧩Backend
NotASithLord/peerdauto-héberger409

EpicStaff

projet

Source-available, self-hosted platform for building AI agent flows - visual editor over a Django backend.

🧰Frameworks d'agents🧩Backend
EpicStaff/EpicStaffauto-héberger355

c2sagent

projet

C2S Agent is an lightweight AI Agent construction platform that provides configurable online Agents and MCP services, You can configure any HTTP request interface as an MCP tool. C2S Agent 是一个轻量级的AI Agent构建平台,提供在线可配置的Agent,MCP,您可以一个HTTP请求的接口配置成为一个MCP工具,Agent之间可以进行自交流。并提供了单端口多A2A服务,MCP服务的解决方案

🧩Backend🧰Frameworks d'agents
C2SAgent/c2sagentauto-héberger270

mc_aiplayer

projet

Autonomous AI agent that plays Minecraft on its own — a server-side Fabric mod (MC 1.21.3) where a DeepSeek / OpenAI-compatible LLM drives a real player to mine, build, farm, fight and survive from natural-language commands. LLM plans, deterministic tasks execute — no Python harness, no bot account.

🧩Backend
zoyluoblue/mc_aiplayerauto-héberger213

pydantic-ai-backend

projet

File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.

🧩Backend🧰Frameworks d'agents
vstorm-co/pydantic-ai-backendauto-héberger100
← PrécédentPage 2 sur 2