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...
Awesome AI Agents › AI Agent Development
CaviraOSS/OpenMemory
OpenMemory is an open-source, self-hosted long-term memory system designed to enhance AI systems by providing persistent, explainable memory capabilities. Unlike traditional vector databases, OpenMemory employs a cognitive architecture that organizes memories into multiple types such as semantic, episodic, procedural, emotional, and reflective. This multi-sector memory approach allows the system to track the importance of memories over time, automatically decay less relevant memories, and build associations between related memories, improving recall accuracy and efficiency. The system supports user isolation by providing separate memory spaces for each user, making it suitable for multi-user environments. It is framework-agnostic, meaning it can integrate with any large language model (LLM) or AI agent system, and supports both local and cloud-based embeddings, including OpenAI and Gemini. OpenMemory also features a VS Code extension that tracks coding activity, compresses context to reduce token usage, and enables AI assistants to access project history seamlessly. Architecturally, OpenMemory uses Hierarchical Memory Decomposition (HMD), which ensures one canonical node per memory with multiple embeddings per memory sector and single-waypoint linking between memories. This design enhances recall accuracy while reducing computational costs. The system is highly performant, with an average response time of 115 ms for 100k nodes and a throughput of 338 queries per second, outperforming many competitors. OpenMemory also excels in memory decay stability, recall accuracy, and explainable recall paths, providing a robust and transparent memory system for AI applications. It is licensed under Apache 2.0, supports multi-tenant user namespaces, and offers cost-effective hosting options. Overall, OpenMemory is a comprehensive solution for adding sophisticated long-term memory to AI systems quickly and efficiently, with strong community support and extensibility.
https://github.com/CaviraOSS/OpenMemory
Also in AI Agent Development
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.