Open Source

A coding-agent skill that shows three style previews for you to pick from, then builds a zero-dependency single-file HTML deck — and converts existing .pptx files with images and notes intact.

SlidesPresentationHTML

JavaScript30k2.4k125

Genesis-Embodied-AI/genesis-worldApache-2.0

Genesis World: The Unified Multi-Physics Simulation Platform for Physical AI

Genesis AI's open simulation platform for physical AI: one Pythonic API over a multi-physics engine (rigid, FEM, MPM, PBD, SPH, Stable Fluid, IPC), the Nyx path tracer, and Quadrants, a cross-platform Python-to-GPU compiler. It is built to be the evaluation engine for robot foundation models rather than a data factory: 30,000 parallel environments at 43M FPS, and under a zero-shot real-to-sim protocol, sim-vs-real evaluation agreement of Pearson 0.8996 with mean maximum rank violation 0.0166. Apache 2.0, 29.9k stars.

SimulationPhysics EngineEmbodied AI

Python30k2.9k224

langchain-ai/deepagentsMIT

Deep Agents: an off-the-shelf agent harness reverse-engineered from Claude Code

The README opens by calling itself an off-the-shelf agent harness: MIT licensed, Python (plus deepagents.js), built on LangGraph, so streaming, durability and checkpoints are inherited rather than rewritten. The key to reading it is the acknowledgement - inspired by Claude Code, trying to figure out what makes it general and pushing that further - which makes this a reverse-engineering exercise: take a closed coding agent that is known to work well, open it up, and ask what actually lets it handle long tasks. Its answer is four bundled things: a pluggable-backend file system (the artefacts of long tasks are files, not messages, so context keeps only pointers), sub-agents each with their own window (context isolation and compression, not extra helpers), long-thread summarisation with tool output offloaded to disk, and on-demand Skills. Also sandboxed shell execution, cross-session persistent memory, human-in-the-loop approval/edit/reject before a tool call runs, and any MCP server as a tool. Model agnostic: frontier APIs, open weights hosted on Baseten or Fireworks, and self-hosted Ollama/vLLM/llama.cpp all work, with three lines of create_deep_agent giving you a planning, file-reading-and-writing agent. The security section is unusually blunt - it follows a trust-the-LLM model, boundaries must be enforced at the tool and sandbox layer, and you should not expect the model to restrain itself. 29.7k stars. Not run yet; sub-agent isolation quality and summarisation information loss are unverified, so this is graded as pending reproduction.

Agent HarnessCoding AgentSub-Agents

Python30k4.2k139

ahujasid/mcp-for-blenderMIT

MCP for Blender: 32 tools that make Blender a 3D workspace an LLM can drive

Formerly blender-mcp, a third-party community plugin (the README states on its first screen that it is not made by Blender), MIT licensed, Python, and the highest-starred entry among 3D MCP servers. The PyPI package is now mcp-for-blender, yet uvx blender-mcp still runs and existing configs need no change. Two components only: an addon inside the Blender process runs a socket server that actually executes commands (the only place with bpy, the current scene and the UI thread), while a separate MCP server process translates protocol, joined by JSON over TCP on localhost:9876 by default. The source defines 32 @mcp.tool() decorators across four layers - perception (get_scene_info, get_object_info, get_viewport_screenshot returning an MCP Image, closing an act-then-look loop), reference lookup (bpy_api_lookup and describe_node_type so the model queries instead of guessing socket order and enum names), execution (execute_blender_code as the escape hatch, set_texture, export_scene to GLB/FBX), and asset retrieval and generation (Poly Haven with semantic search, importing the .blend source and writing attribution properties; Poly Pizza with about 10,600 low-poly models, size normalisation and automatic CC-BY credit; Sketchfab; Hyper3D Rodin text-to-3D and image-to-3D; Tencent Hunyuan3D distinguishing the mainland ai3d endpoint from the international hunyuan one). On security, arbitrary code execution is the design rather than a bug: an optional safe mode (BLENDER_MCP_SAFE_MODE=1) statically validates scripts before running, blocking file access, subprocesses, network and persistent code while modelling, rendering, saving, import and export pass normally, and blocked scripts return to the model with the reason so it can retry. Content telemetry is off by default, and a dedicated disable_telemetry tool can only turn collection off. 29.2k stars. Not run with Blender locally yet, so this is graded as pending reproduction.

MCPBlender3D Generation

Python29k2.7k202

OthmanAdi/planning-with-filesMIT

planning-with-files: Persistent file-based planning for AI coding agents — crash-proof markdown plans that survive /clear, compaction and crashes

planning-with-files (27k+ stars, MIT): persistent file-based planning for AI coding agents and long-running tasks — keeps task_plan.md / findings.md / progress.md on disk and lifecycle hooks re-inject the plan into context every turn, so the plan survives /clear, compaction and crashes; a Stop hook forms a deterministic completion gate that holds the agent until the plan reports complete. Project measurements: the on-disk plan cut a 13.3-turn re-orientation to 5.0 turns, 3-of-3 blind A/B wins, 96.7% assertion pass rate. Covers 60+ agents via the Agent Skills standard, with native plugins for Claude Code, Codex CLI, Pi, Hermes, OpenCode and DeepSeek Harness, plus localized skill variants (AR/DE/ES/zh-CN/zh-TW). Pattern follows Manus's "Markdown as working memory on disk"; parallel tasks get isolated .planning/ dirs; /plan-attest locks the plan with SHA-256.

Agent SkillsPlanningHarness

Shell27k2.3k117

morluto/reaMIT

REA: one MCP and CLI that puts reverse engineering inside coding agents

MIT-licensed reverse-engineering MCP server and CLI. One npx rea-agents setup pulls Hopper/Ghidra/IDA, pwntools, JADX, Binwalk and CDP behind a single tool contract and registers it into Claude Code, Codex or Cursor, covering twelve target classes from native binaries, JS/Electron, .NET, Android and firmware to EVM bytecode and websites. Its stance is evidence-first: observed and inferred edges are labelled separately, missing evidence is reported as unknown rather than empty or false, provider bindings are immutable with no silent fallback, and REA never kills a process it cannot prove it owns.

Reverse EngineeringMCPAI Coding

TypeScript27k3.0k85

getpaseo/paseoNOASSERTION

Paseo: One Self-Hosted Cockpit for Claude Code, Codex, Copilot and More Coding Agents

Self-hosted multi-agent orchestration (20.9k stars): Claude Code, Codex, Copilot, OpenCode, Pi, Antigravity and Muse Code behind one interface on your own machines; a local daemon (WebSocket + 33 MCP tools) orchestrates them while Electron desktop, Expo iOS/Android, web and CLI clients connect; git-worktree parallel isolation, local-ONNX voice, an end-to-end encrypted relay for remote follow-up, plus a plugin registry, skills and Hub ecosystem. Apache-2.0.

AI CodingCoding AgentAgent orchestration

TypeScript21k2.5k56

earthtojake/text-to-cadMIT

Text-to-CAD: the open-source plugin and skill suite that gives coding agents CAD superpowers

text-to-cad turns parametric CAD into a local agent skill: plain language or an image becomes a STEP model with STL/3MF/GLB exports, plus DFM review, dimensioned drawings, URDF/SRDF/SDF robot descriptions and 3D printing, sheet metal and CNC integrations. Kernel is build123d on OCP; the shape is twelve skills plus the cadgen engine and a local CAD Viewer. MIT, about 20.6k stars.

CADAgent SkillsMCP

Python21k2.0k100

walkinglabs/learn-harness-engineeringMIT

Learn Harness Engineering: a project-based course on making AI coding agents reliable

An open-source, project-based course (14 lectures, 8 projects, 15 languages) on building the instructions/state/verification/scope/lifecycle subsystems that make frontier models reliable inside real repos — includes reverse-engineered harness breakdowns of Pi, Claude Code, Codex and DeepSeek, plus loop- and graph-engineering advanced lectures. MIT licensed, ships a harness-creator skill and a zero-dependency audit script.

HarnessAI CodingAgent

TypeScript19k2.0k83

GLips/Figma-Context-MCPMIT

Framelink MCP for Figma: design files compressed into usable context, not screenshots

Also known as Figma-Context-MCP, npm package figma-developer-mcp, TypeScript, MIT, and a third-party implementation rather than the Dev Mode MCP server Figma ships itself. It exposes only two tools: get_figma_data (read-only) and download_figma_images (removable with –skip-image-downloads, and confined to writing inside –image-dir). The narrow surface is deliberate; the engineering sits in the fetch → simplify → serialize pipeline behind it. Simplify uses composable extractors (layout, text, visuals, component, plus the allExtractors, layoutAndText, contentOnly, visualsOnly and layoutOnly bundles) to compress the raw Figma response into semantic layout and styling in a single tree walk, with maxDepth and nodeFilter, and outputs tree (default, cheapest in tokens), yaml or json. The part worth copying is that compression effectiveness is a metric computed on every call: rawSizeKb against simplifiedSizeKb, rawNodeCount against simplifiedNodeCount, component/instance/text/image node counts, namedStyleCount (the source comment states a high count is a design-system maturity signal), hasVariables (whether Figma Variables are used at all), and separate fetch/simplify/serialize timings; the same hooks drive MCP progress notifications and heartbeats so a large file taking tens of seconds does not look hung. Judgement shows in the details: node IDs accept both the plain and the deeply nested instance shape, the depth parameter description says do not use it unless the user explicitly asks, the proxy default deliberately avoids installing EnvHttpProxyAgent when no proxy variables exist so a stale variable cannot route traffic through an intermediary returning 403, and stdio mode warns at startup when –image-dir is unset. Credentials come from FIGMA_API_KEY or FIGMA_OAUTH_TOKEN; telemetry can be disabled with –no-telemetry or DO_NOT_TRACK=1 and secrets are redacted from reports. 15.9k stars. It generates no frontend code - the output is design facts, and translating them into React, Vue or SwiftUI is your coding agent job. Not yet run against a Figma file of our own, and no screenshot-versus-structured-data accuracy comparison, so this is graded as pending reproduction.

MCPFigmaDesign-to-Code

TypeScript16k1.3k65

img2threejs/img2threejsApache-2.0

img2threejs: Rebuilding Reference Images as Code-Only Procedural Three.js Models

An agent skill for Claude Code, Codex and OpenCode that rebuilds a reference image as a code-only procedural Three.js model: an eight-pass sculpting pipeline with deterministic gates, shipping a diffable TypeScript factory instead of a mesh.

Image-to-3DThree.jsProcedural Generation

Python15k1.3k59

web-infra-dev/midsceneMIT

Midscene.js: A Vision GUI Agent and E2E Testing Framework

ByteDance Web Infra open-source vision GUI agent and E2E testing framework. It locates elements from screenshots instead of selectors and drives Web, Android, iOS, HarmonyOS and desktop through one API, shipping YAML cases, TypeScript nodes, replayable reports and CLI skills for coding agents. An agent-harness layer, not an AI-coding tool.

Agent HarnessGUI AgentE2E Testing

TypeScript15k1.2k70

As an Amazon Associate, we earn from qualifying purchases.