OPEN SOURCE

The MCP ecosystem crossed 22,000 servers in early 2026. Most are noise. Here are the open-source servers that have earned a permanent slot in our config, with copy-paste setup for Claude Code, Cursor, and Codex.

Four Claude-Design-adjacent repos entered the trending week with a combined 8,300+ stars. Huashu-design, open-codesign, awesome-claude-design, cc-design. Here is what is actually happening, and why the pattern matters.

Alibaba's flagship open-weight coding model. 480B total parameters, 35B active (MoE). Native 256K context, scales to 1M. Apache 2.0 license. State-of-the-art agentic coding.

DeepSeek's reasoning-first model built for agents. First model to integrate thinking directly into tool use. Ships alongside V3.2-Speciale, which rivals GPT-5 and Gemini 3.0 Pro.

Qwen3.6-27B keeps pulling developers back because it sits in the awkward, useful middle: strong enough for real local coding tasks, small enough for serious workstation testing, and cheap enough to benchmark honestly.

Updated 2026 comparison of Aider and Claude Code using official docs and current workflow patterns: architecture, control surfaces, cost behavior, and where each fits best.

OpenAI's open-source terminal coding agent built in Rust. Runs locally, reads your repo, edits files, and executes commands. Powered by o3 and o4-mini models.

Open-source terminal coding agent from Moonshot AI. Powered by Kimi K2.5 (1T params, 32B active). 256K context window. Agent Swarm runs up to 100 parallel sub-agents.

Open-source autonomous coding agent inside VS Code. Creates files, runs commands, and can use a browser for UI testing and debugging with your permission.

Open-source autonomous coding agent inside VS Code. Creates files, runs commands, and can use a browser for UI testing and debugging with your permission.

Multi-agent orchestration framework built on the OpenAI Agents SDK. Define agent roles, typed tools, and directional communication flows. Production-focused, open-source.

Type-safe Python agent framework from the Pydantic team. Brings the FastAPI feeling to AI development. Composable tools, durable execution, and full IDE autocomplete.

Constrained generation library for LLMs. Uses finite state machines to mask invalid tokens during generation. Guarantees schema-compliant output with zero retries.

Open-source AI orchestration framework by deepset. Modular pipelines for RAG, agents, semantic search, and multimodal apps. Pipeline-as-graph architecture with explicit control.

The easiest way to run LLMs locally. One command to pull and run any model. OpenAI-compatible API. 52M+ monthly downloads. Supports GGUF, Safetensors, and custom Modelfiles.

Desktop app for discovering, downloading, and running local LLMs. Clean chat UI, OpenAI-compatible API server, and automatic GPU detection. MLX engine optimized for Apple Silicon.

Open-source ChatGPT alternative that runs 100% offline. Desktop app with local models, cloud API connections, custom assistants, and MCP integration. AGPLv3 licensed.

Open-source OpenAI API replacement. Runs LLMs, vision, voice, image, and video models on any hardware - no GPU required. 35+ backends. Distributed mode for scaling.

DeepSeek's R1 and V3 models deliver frontier-level performance under an MIT license. Here's how to use them through the API, run them locally with Ollama, and decide when they beat closed-source alternatives.

Meta's Llama 4 family brings mixture-of-experts to open source with Scout and Maverick. Here's how to run them locally, access them through APIs, and decide when they beat the competition.