Awesome AI AgentsAI Agent Development

memodb-io/Acontext

⭐ 3691 Go added to this list on 2025-12-15 repository created 2025-07-16

Acontext is a context data platform designed for building cloud-native AI agents. It provides a comprehensive solution to store contexts and artifacts, perform context engineering, observe agent tasks and user feedback, and enable agent self-learning by distilling skills from completed tasks. The platform offers a unified dashboard to view messages, artifacts, skills, and success rates, making it easier to manage and improve AI agents. Core features include multi-modal message storage (Session), a background task agent to collect task status and preferences, context editing in a single call, a filesystem for artifacts (Disk), a Notion-like space for agents to organize skills (Space), and experience agents that distill, save, and search skills. The platform is designed to help build scalable and observable agent products that can automatically improve their success rates. The architecture consists of a client layer with Python and TypeScript clients, a backend with a FastAPI-based API and core logic, and infrastructure components including PostgreSQL, S3, Redis, and RabbitMQ. A web dashboard provides a user interface for monitoring and managing the platform. Acontext supports local backend setup using Docker and requires an OpenAI API key. It is actively maintained with continuous integration workflows and has a community on Discord for support and collaboration. The platform is multilingual, with documentation available in several languages. Overall, Acontext is a powerful tool for developers and organizations looking to enhance their AI agents with advanced context management, observation, and learning capabilities, enabling more intelligent and adaptive agent behavior.

https://github.com/memodb-io/Acontext

agentagent-development-kitagent-observabilityagent-tasksai-agentai-agentsanthropicartifactscloud-nativecommunitycontext-data-platformcontext-editingcontext-engineeringdashboarddata-platformdiscorddockerexperience-agentfastapifilesystemllmllm-observabilityllmopsmemorymulti-modal-message-storagemultilingual-documentationnotion-for-agentsobservable-agent-productopenaiopenai-apipostgresqlrabbitmqrediss3scalable-agent-productself-evolvingself-learningskills-distillationsuccess-ratetask-agentuser-feedback

Also in AI Agent Development

kepano/obsidian-skills

Obsidian Skills provides a collection of agent skills enabling AI agents to interact with Obsidian vaults, facilitating content creation and editing of Markdown, Bases, and JSON Canvas files, as we...

Panniantong/Agent-Reach

Agent-Reach allows AI agents to access web content from major social media and video platforms through a CLI, without API fees, enhancing their perceptual capabilities.

JCodesMore/ai-website-cloner-template

This project provides a reusable Next.js template for reverse-engineering and cloning any website into a modern codebase using various AI coding agents.

huggingface/smolagents

Smolagents is a minimalistic Python library by Hugging Face for creating intelligent agents that think and act by generating and executing Python code, supporting multiple LLMs, modalities, and tool integrations.

alibaba/page-agent

Page Agent is a JavaScript in-page GUI agent enabling natural language control of web interfaces without browser extensions or headless browsers, supporting various LLMs.

TencentCloud/TencentDB-Agent-Memory

TencentDB Agent Memory provides a local, 4-tier progressive pipeline for AI agent long-term memory, enhancing performance and reducing token usage without external API dependencies.

titanwings/distilly

A meta-skill that distills messages, documents, interviews and public sources about a person into a source-grounded Person Profile, packaged as an Agent Skill for coding agents and chat bots.

coze-dev/coze-studio

Coze Studio is an all-in-one AI agent development platform that simplifies the creation, debugging, and deployment of AI agents through visual tools and supports no-code and low-code development approaches.