Open-source projects tagged “agents”

A local MCP server that routes prompts from Cursor, VS Code, Windsurf or Claude Desktop to ChatGPT, Claude, Gemini, Perplexity, BYOK APIs or local Ollama models.

Open-source web data platform that turns websites into structured APIs for scraping, crawling, search, monitoring and AI extraction.

A macOS app for browsing, editing, and organizing AI coding agent skills and agents across Claude Code, Cursor, Codex, Windsurf, and Amp.

A step-by-step educational project that builds Retrieval-Augmented Generation from scratch in JavaScript using local LLMs and no cloud APIs.

Companion code repository for the book AI Agents: The Definitive Guide, with Jupyter notebooks covering agent patterns, tooling, evaluation, memory, and security.

Desktop, mobile, web and CLI app for running and orchestrating multiple coding agents such as Claude Code, Codex and OpenCode in parallel worktrees.

Turns any Agent Skill into RL-ready terminal tasks in the Harbor format, using Codex agents inside Docker containers.

A CLI and web workbench that compiles raw documents into an interlinked, LLM-maintained markdown wiki, using PageIndex tree retrieval for long files.

Companion code for the book Designing Multi-Agent Systems, including PicoAgents, a multi-agent framework built from scratch for teaching.

A local browser-based review surface that lets you annotate agent plans, markdown, HTML and code diffs, then send feedback back to coding agents.

A deep research skill and pipeline for Claude Code and OpenAI Codex that gathers web and scholarly sources into a persistent, searchable markdown vault and writes cited reports.

A plugin and skill set that lets AI coding agents generate, check and fabricate CAD models from plain-language requests.

Self-hosted Kubernetes-based infrastructure that runs untrusted code in lightweight VM sandboxes, controlled via a CLI, HTTP API and Python SDK.

An open source MCP server that connects AI agents, IDEs and apps to databases with prebuilt tools or custom tool definitions.

ASPIRE is a framework where coding agents iteratively refine reusable robot skills for simulated and real-robot manipulation tasks instead of training model weights.

A sandbox platform that runs agent and user code in isolated Firecracker microVMs, controlled through an HTTP API.