Token efficient Claude Code full Python rebuild. AI Coding Agent in 310K LoC Python.
Python sandboxes for llms
Unified execution environment for Python code, shell commands, and programmatic MCP tool calls.
High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript/Python SDKs, and Docker deployment.
UEFN Toolbelt: 362 Python automation tools across 55 categories, with a PySide6 dashboard and an experimental, authenticated same-user loopback bridge for local AI control. Complements Epic's official UEFN MCP; Toolbelt is not exposed through Epic's MCP server.
Cowork/Claude Code skill for Unreal Engine 5 development via MCP, pixel streaming, and Python editor scripting
Modular plugin marketplace for Claude Code and agentic CLIs, with validated, spec-driven skills, agents, commands, and workflows for Java, TypeScript, Python, PHP, AWS, and AI.
OpenBrowser is a framework for intelligent browser automation. It combines direct CDP communication with a CodeAgent architecture, where the LLM writes Python code executed in a persistent namespace, to navigate, interact with, and extract information from web pages autonomously.
Agent Skill evaluation harness for paired variants, trace artifacts, and runner adapters
Protocol-layer harness for DeepSeek: Python witness stack — posterior verification that keeps the protocol honest. dsh doctor --node probes included.
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into searchable, timestamped evidence and proves work with deterministic contracts, not model opinion. DeepWatch is the agent workspace built on DeepSeek Harness. Python + npm, MCP, CLI, REST, Web.
Agent Skills marketplace: framework-aware skills for code review, documentation, test-plan generation, AI-writing detection, architectural analysis, and git workflows — for Python, Go, Rust, Elixir, React, Remix, and iOS/Swift. Works with Claude Code, Codex, and any agent that supports Agent Skills.
Code, Build and Evaluate agents - excellent Model and Skills/MCP/ACP/A2A Support
LSP plugins for Claude Code — Bash/Shell, C/C++/Objective-C, C#, Clojure, Dart/Flutter, Elixir, Gleam, Go, Java, Kotlin, Lua, Nix, OCaml, PHP, Python, Ruby, Rust, Swift, Terraform, TypeScript/JavaScript, YAML & Zig

Give your AI agent eyes and hands on any desktop — cross-platform accessibility API with MCP server
Interactive terminals for AI agents, built for what you can't --yes away. SSH+MFA, GRUB/U-Boot, debconf installers, SOL/serial consoles, fsck, cryptsetup, pdb/gdb, apt, certbot, pwsh and even Vim in tmux-backed sessions. Agent-driven, human-assisted for secrets/MFA. Single-file Python. Agent Skill. CI with 700+ tests. BSD License.
The open-source memory and observability layer for AI agents — persistent memory, loop detection, hash-chained audit trails, and a live dashboard, automatic on pip install.

Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, and custom agents — swap harnesses without rewriting, enforce policies and sandboxing, and collaborate in real time from any device.
Cross-language-safe code-intelligence MCP for AI agents -- 13 languages, family-gated call graph (CodeGraph 745 vs TSA 6 cross-language mis-wires, v1.21.0 same-session -- ~124x by count, ~390x by rate; re-verifying vs current develop). Run miswire-audit on your repo. 8 facade tools, TOON output, 100% local. Python.
Free, MIT alternative to paid Django schema review. Blast radius on every PR, schema drift, N+1 across functions, ER diagrams, MCP server. No DB, no Django boot, no Pro tier.
AI said it finished. Flyto2 shows the proof.
A workflow framework for statistical package development
MCP server for build123d to improve AI cognition when creating 3D CAD models
MCP server for TouchDesigner — build, wire, and debug networks with AI. Plus git-diffable externalization.