trueforge
The open-source agent harness - the runtime layer that turns an LLM into a working agent.
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 open-source agent harness - the runtime layer that turns an LLM into a working agent.
Open-source Cursor-like AI coding agent for VS Code — agentic chat, multi-provider LLMs (OpenAI, Ollama, llama.cpp), semantic search, and MCP support
Harness Engineering 学习指南 — 从概念理解到独立实践的深度学习档案
Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing.
⭕️ AstroWind: A free template using Astro v7 and Tailwind CSS v4. Astro starter theme.
Agent OS: the agent gets smarter on its own. We just hold the line: Interview-gated, staged evaluation, budgeted evolution loop. MCP server, 14 runtimes: Claude Code, Codex CLI, Gemini CLI, OpenCode, Copilot, Kiro and more.
📌 异步线程池框架,支持线程池动态变更&监控&报警,无需修改代码轻松引入。Asynchronous thread pool framework, support Thread Pool Dynamic Change & monitoring & Alarm, no need to modify the code easily introduced.
Production-safe dynamic tracing and diagnostics for Java applications—attach to live JVMs with no restart or recompilation.
The most comprehensive Claude Code guide: agentic workflows, hooks, skills, MCP servers, quizzes, and production-ready templates. 430K+ lines.
MaiSaka, an LLM-based intelligent agent, is a digital lifeform devoted to understanding you and interacting in the style of a real human. She does not pursue perfection, nor does she seek efficiency; instead, she values warmth, authenticity, and genuine connection.
Multi agent system for AI-driven software development. Combine LLM with DevOps tools to convert natural language requirements into working software. Supports any development language and extends the existing code.
It's like v0, but in your Cursor / Claude Code / Windsurf: search 10,000+ React/Tailwind components, generate new UI with AI, and publish your own — right from your editor. Magic MCP is now the 21st MCP; this package keeps old configs working. Setup: 21st.dev/mcp
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
⚙️ All-in-One menu bar app, hide 💻MacBook Pro's notch, dark mode, AirPods, Shortcuts
Anthony Fu's curated collection of agent skills.
Build databases, automations, apps & agents with AI — no code. Open source platform available on cloud and self-hosted. GDPR, HIPAA, SOC 2 compliant. Best Airtable alternative.
多模型协作工作流引擎 — /ccg:go 一个命令,AI 自动分析意图、选择策略、编排 Codex + Gemini + Claude 协作执行
data load tool (dlt) is an open source Python library that makes data loading easy 🛠️
Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
A workshop that teaches you how to build your own coding agent. Similar to Roo code, Cline, Amp, Cursor, Windsurf or OpenCode.
Emdash is the Open-Source Agentic Development Environment (🧡 YC W26). Run multiple coding agents in parallel. Use any provider.
Data visualization Skill for AI Agents, turning data into polished, interactive HTML charts. 面向 AI Agents 的数据可视化 Skill,将数据快速生成精致、可交互的 HTML 图表。
(Replaces Next.js/Nuxt) 🔨 Build mission-critical applications with stability and development freedom.
Autoharness — a self-learning skill layer for Claude Code — distills skills from your real sessions, updates them as you work, and prunes the ones that stop getting used. No daemon, no benchmark.