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
oceanbase/powermem
PowerContext, published by OceanBase as PowerMem 2.0, gives agents durable project-scoped context so that a later session can recover a decision, an outcome, the current state or the next step without relying on chat history. The system runs locally: a server listening on 127.0.0.1:8000 stores entries in a SQLite database in the platform user data directory, and around it sit an async Python client, a Core SDK, a CLI and host plugins. Installation goes through uv with a command such as uv tool install powercontext[cli,server], after which powercontext setup codex or powercontext setup dsh installs the matching plugin for the Codex CLI or the DeepSeek Harness from the same release tag, and powercontext server run starts the service. The powercontext doctor commands check the package, the server and each host integration. Runtime or database failures mark the server not ready, while a failing inference configuration is reported as degraded without removing the server from traffic. The interfaces are separated by role: the Codex and DeepSeek Harness plugins restore relevant project memory while coding and let the user explicitly remember, revise or retire entries, the CLI installs plugins and manages, inspects and diagnoses the server, the Python client calls the Source and Memory API of the server from an application, the Core SDK embeds the contracts or supplies custom adapters inside a Python system, and HTTP plus MCP endpoints let a non-Python process or another agent host talk to a running server. Python projects install only the extra they import, from builtin, client, server, cli and tracing-otlp. The README reports a LOCOMO benchmark run over all 1,540 questions in ten conversations at 90.78 percent accuracy, 1.38 second p95 search latency and roughly 1.65k answer tokens per question, against 52.9 percent and 26k tokens for a full-context baseline. Apache 2.0 licensed.
https://github.com/oceanbase/powermem
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.