An AI agent is a program that uses a language model to decide what to do next, calls tools such as a browser, a code interpreter or an API, and repeats until the task is done. The projects here range from frameworks for building your own agents to finished agents that write code, browse the web or run business workflows.
Compare three things. Which models it can use: a single provider, or any OpenAI-compatible endpoint including local ones. How it limits what the agent may do: sandboxing, approval steps and permission lists. And whether it keeps memory between steps and sessions. An agent that runs code or shell commands should run in a sandbox, so check that before giving it access to your machine.
The best DeepSeek Harness plugin for context insight and management, with context dashboard / browser / sidebar and context command, for context statistics, composition, breakdown, evolution details, understanding how the context is made of, and how it evolves. 一站式 DeepSeek Harness 上下文可视化插件，Context 面板及浏览器和侧边栏与 Context 命令，透视上下文组成、演进、压缩、剪枝等事件与动作。
A self-learning system for Claude Code that captures corrections, positive feedback, and preferences — then syncs them to CLAUDE.md and AGENTS.md.
Open-source BigSet — self-hostable live datasets populated by TinyFish web agents
🏄🏼♂️ The blackboard for coding agents - agentic development environment for claude code, codex, cursor, opencode, grok and more.
Lightweight coding agent written in Rust, optimized for memory footprint and performance
A project-based course repository for developing AI agents using LangChain v1+ and LangGraph: search agents, RAG systems, reflection agents, and code interpreters.
Karpathy's LLM-Wiki vision, fully realized — wiki-centric full-lifecycle AI research platform powered by Claude Code
一款包含了 Prompt管理，Skill管理，Agent管理的一站式AI工具箱，助你高效管理提示词，一键分发skills ，一站式管理Agent资产，并实现云同步，备份，版本管理 | An all-in-one AI toolbox for prompt, agent, and skills management. Reuse prompts, distribute skills with one click, manage agent assets, and support cloud sync, backup, and version control
编程笔记、 AI 学习、观影指南、读书笔记、生活感悟、游戏记录
Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning
Permanent memory for AI agents. A 426-token prompt, a script, plug and play.
Bub it. Build it. A hook-first runtime for agents that live alongside people.
AI-powered OSINT agent with interactive REPL, MCP server, and CLI. 19 tools. Works with Claude, GPT-4, or local models. For authorized security research only.
🦭 会记忆、能持续推进目标、会动态编排多 Agent 的跨端桌面 AI 助手，也可服务化常驻 NAS / 云端 | A cross-device desktop AI agent with memory, autonomous goals, dynamic workflows, and headless deployment
Generate hands-on, multi-part technical tutorials on demand, with LLM skills tuned to make content approachable. Then you work through them yourself, by hand ✋
Open-source LLM/VLM load balancer and serving platform for self-hosting LLMs (and VLMs) at scale 🏓🦙 Alternative to projects like llm-d, Docker Model Runner, etc but with less moving parts and simple deployments built around ggml ecosystem. Runs on CPU and GPU.
Add expert Swift Concurrency guidance to your AI coding tool (Agent Skills open format): safe concurrency, performance optimization, and Swift 6 migration.
Building blocks for rapid development of GenAI applications
🚀 The open-source, multi-tenant platform for self-building knowledge graphs and simulation
Real-time visualization of Claude Code agent orchestration — see your agents think, branch, and coordinate as they work.
Use Astra as orchestrator and Luna for subagents in Codex
Full computer-use for AI agents. Self-learning workflows. Native macOS. No screenshots required.