Top Open-Source GitHub Projects : OpenPencil, Orchard, XERJ, librecalculator, BRUTAL & Remory #301

Author: ManuAGI - AutoGPT Tutorials · Watch on YouTube

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: Top Open-Source GitHub Projects : OpenPencil, Orchard, XERJ, librecalculator, BRUTAL & Remory #301 · Channel: ManuAGI - AutoGPT Tutorials · 14:34 · Watch on YouTube

Topics: AI agents, Cybersecurity and software security, Software engineering with AI, Open source and software ecosystems

Summary

The video presents 20 open-source GitHub projects, ranging from Claude Code plugins and scientific agent skills to agent orchestration, search, security, and memory tools. It also covers developer products for design, project management, CAD, game development, calculators, and desktop workflows. A sponsored segment introduces JetBrains AI in IDEs, a workspace for running and reviewing coding agents. The roundup ends with Agent Play, which replays coding-agent sessions as an interactive map and timeline.

Key points

Anthropic’s Claude Code Plugins Directory offers internal and community plugins that can bundle commands, agent skills, and MCP servers.
Jan Scientific Agent Skills provides research-oriented skills for biology, chemistry, medicine, and drug discovery, connecting to databases and tools.
Rooflo and ECC aim to improve coding-agent orchestration and workflows, while XERJ lets agents search indexed files through an Elasticsearch-compatible API.
Text to CAD enables agents to create and edit parametric CAD models, and Agent Substrate runs agent workloads on Kubernetes.
Open Shell provides policy-governed sandboxes for AI agents, while Free LLM API routes requests across free provider tiers.
Orchard orchestrates Tart virtual machines across Apple silicon Macs, and Open Pencil is a programmable, local-first design editor.
Other projects include a project-management workspace, a MacBook keep-awake app, the Brutal C# game framework, and Libre Calculator.
GPT with taste and CC Stretch alter how models respond or how Claude Code replies are displayed; Desk offers a skeuomorphic Wayland desktop.
Memory supplements compacted agent context with learned soft memory, and Agent Play locally replays coding-agent sessions.

Chapters

Start	Chapter	Summary
00:00	Introduction, channel announcement, and early projects	The host introduces the weekly GitHub roundup, announces a new AI-agent channel, and covers the Claude Code Plugins Directory, a JetBrains sponsorship, scientific skills, orchestration, and search.
03:08	Agent engineering, search, CAD, and runtime security	The roundup moves through scientific agent skills, Rooflo, ECC, XERJ, Text to CAD, Agent Substrate, Open Shell, and Free LLM API.
06:46	VM orchestration, design, and productivity tools	The host presents Open Shell and Free LLM API, then introduces Orchard, Open Pencil, Zry AR Studio, and Insomnia.
10:25	Games, calculators, and agent behavior	The video covers Brutal, Libre Calculator, GPT with taste, and CC Stretch, followed by the Desk desktop environment.
13:31	Memory and session replay	The final projects are Memory, which supplements context summaries with learned memory, and Agent Play, which replays coding-agent sessions.

Quotes

Every week developers release new open-source projects on GitHub — 00:00

Each plugin can bundle {slash} commands, agent skills, and MCP servers — 01:03

Everything is programmable. — 08:50

each one explains its answer rather than just a number. — 11:27

A final answer hides the story. — 14:02

Concepts and entities

OpenPencil, Orchard, XERJ, Libre Calculator, BRUTAL, Remory, Claude Code Plugins Directory, Agent Play

Full transcript (original language)

00:00 Every week developers release new open-source projects on GitHub, and this is our weekly GitHub project update video covering the best of them. Top trending open-source GitHub projects this week, you’ll discover useful and trending developer tools from design editors to AI agent orchestration. Without [clears throat] wasting time, let’s get started. >> Before we jump into today’s project updates, here’s a quick announcement for everyone. We’ve launched a brand new YouTube channel called AI Agent Studio dedicated entirely to AI agent projects,

00:31 tutorials, and tools. So, if you’re interested in staying up-to-date with the latest AI agent open-source projects, learning how to build your own agents, or exploring cutting-edge agent frameworks, make sure to check it out. Subscribe now to get weekly videos, in-depth guides, and real-time project breakdowns. The link is right there in the description. Don’t miss it. All right, let’s get into today’s video. >> Project number one, Claude Code Plugins Directory. Anthropic’s official marketplace of Claude Code Plugins. This

01:03 is Anthropic’s official open-source directory of high-quality Claude Code Plugins. It’s split into internal plugins maintained by Anthropic, like front-end design, code review, code modernization, security, and language server integrations, and external plugins from partners and the community, such as GitHub, Linear, Playwright, Firebase, and Terraform. Each plugin can bundle {slash} commands, agent skills, and MCP servers, and you install any of them from Claude Code with {slash} plugin install name at Claude plugins

01:35 official. You should trust a plugin before installing it. Browse it and extend Claude Code. >> Before we move to the next project, let’s introduce something for the engineers and developers. This part is sponsored. JetBrains just launched a new IDE plugin. It is called JetBrains AI in IDEs. JetBrains builds the tools a lot us already use. Air in IDEs is their agentic workspace inside those IDEs. You bring the coding agents you already use,

02:07 Codex, Copilot, Claude, Cursor, Juni, or other ACP-compatible agents, and run them from one place. Keep several projects open. Run sessions in parallel. See where something needs your attention. When an agent finishes, review the diff with the IDE tools you already trust. Navigation, refactoring, tests, debugging. You stay in control. If you want to try it without burning your own subscription, JetBrains is

02:38 offering Juni light free for a limited time. That is their efficient baseline agent for normal tasks, not their strongest model. It is enough to test the workflow. You need a JetBrains account for that. Cloud runs still need a JetBrains AI subscription. So, try this plugin right now. Okay, let’s move to the next project. >> Project number two, Jan scientific agent skills. Jan 63 science skills for your coding agent. Scientific agent skills is

03:08 an open-source library of 163 skills that turn a coding agent into a research assistant across biology, chemistry, medicine, and drug discovery. Each skill is a markdown file that teaches the agent how to query a specific resource, connecting to over 100 databases and tools like PubMed, UniProt, and the PDB. It works with Claude Code, Codex, and Cursor, and you install just the skills you need. Install it and run your science. Project number three, Rooflo,

03:38 multi-agent swarm orchestration for Claude Code. Rooflo is an open-source multi-agent orchestration harness for Claude Code. It lets you deploy swarms of specialized agents across machines, teams, and trust boundaries, layering self-learning memory, federated communication, vector rag, and enterprise policy controls. Hooks automatically route tasks, spawn agents, and learn from what works. So, you use Claude Code normally. A CLI manages swarms, agents, and memory, and a policy layer caps spend and concurrency, gates

04:10 sensitive actions, and audits every decision. Install it and orchestrate a swarm. Project number four, NECC, performance optimization system for AI coding agents. ECC is an open-source system for making coding agents better engineers, working across Claude Code, Codex, Open Code, Cursor, and more. It layers on skills, memory, per-stack rules, security, and a research-first workflow. So, the agent plans before it builds, verifies changes with tests, reviews its own work from a fresh

04:42 context, and remembers what matters. It ships commands like review pair, learn, and consult, plus a security layer, Agent Shield. Install it as a plugin or via setup. Level up your agent. Project number five, NIM XERJ, a search engine for AI agents, Elasticsearch compatible. XERJ is an open-source search engine for AI agents. Pointed at a folder, one command indexes code, docs, logs, and PDFs. So, an agent asks questions instead of reading files into context.

05:14 Auto Index sniffs each file and makes an index per data set. Code with tree sitter symbols and line numbers, plus CSV, JSON, SQLite, DOCX, and mail. It speaks the Elasticsearch API, so clients work, and XERJ knit wires it into Claude Code and Cursor. Install it and let agents search. Project number six, Text to CAD, agent skills that give your agent CAD powers. Text to CAD is an open-source library of agent skills that give your agent CAD superpowers. Ask it

05:45 to model a part, and it writes and edits parametric CAD in Python. Build 123D on Open Cascade, exporting step, STL, 3MF, GLB, and DXF. A browser viewer previews the result, plus robot files and G-code, and stable at CAD references let you request precise edits. Other skills cover robot descriptions, inverse kinematics, and implicit CAD. Install it into Claude code or Codex, and model from text. Project number seven, Agent

06:16 Substrate. Run agent workloads at scale on Kubernetes. Agent Substrate is an open-source system built on Kubernetes that runs agent-like workloads at higher density and lower latency. It maps idle actors onto a pool of worker pods, suspending and resuming them with state intact for multiplexing. It keeps the Kubernetes control plane off the request path, isolates workloads with Gvisor, and stays framework agnostic across ADK, LangChain, Claude code, and MCP. It runs

06:46 on any cluster through a kubectl plugin, and it’s early. Deploy it and scale your agents. Project number eight, Mines Open Shell. Secure, policy-governed sandbox runtime for AI agents. Open Shell is Nvidia’s open-source, secure-by-design runtime for autonomous AI agents. Agents like Claude code, Codex, and Open Claw run unmodified inside kernel-level sandboxes governed by declarative YAML policy. You declare what each agent can touch, and Open Shell enforces it.

07:17 Agents never see credentials. It injects them only into requests bound for approved endpoints, blocking exfiltration. Policy changes are formally verified, so risky access waits for review. It runs on prem in Docker or Kubernetes with SDKs. Deploy it and sandbox your agents. Project number nine, Free LM AP. Stack free LLM tiers behind one endpoint. Free LM AP is an open-source OpenAI compatible proxy that stacks the free tiers of 34 LLM

07:48 providers, 635 endpoints, billions of tokens monthly behind one flash V1 endpoint plus any custom OpenAI compatible endpoint. It routes and fails over automatically and a signed catalog syncs new models and quotas. Provider keys are AES-256 GCM encrypted in SQLite and your app’s C1 unified token. Launchers keep credentials out of Claude code and Codex configs. It’s local first for personal use. Install it and point your app at it. Project number 10,

08:19 Orchard. Orchestrate Tart VMs across Apple silicon Macs. Orchard is OpenAI’s open-source orchestrator for running Tart virtual machines across a cluster of Apple silicon Macs. A controller and workers let you create, run, and manage a fleet of macOS VMs through a CLI or a built-in REST API. A local dev mode starts a controller and worker. It now runs Linux workers through V2, so one cluster can mix architectures and operating systems. It’s written in Go and installs with Homebrew. Set it up

08:50 and orchestrate your VMs. Project number 11, Nush Open Pencil. AI-native open-source Figma alternative you can program. Open Pencil is an open-source AI-native design editor, a local-first MIT licensed Figma alternative. It reads and writes native.fig files and its own.pen format. So, you copy and paste nodes between it and Figma, and there’s a built-in AI assistant. Everything is programmable. A headless CLI inspects, queries, lints, and exports to PNG, SVG,

09:21 PDF, HTML, and more. An MCP server exposes it to Claude code, Codex, and Gemini, and a view SDK builds custom editors. Install it and design locally. Project number 12, Zeri AR Studio. A calm open-source project workspace. Zry AR Studio is an open-source calm project management workspace. It gives you a home dashboard, an inbox, a my tasks view, and projects you can see as a board, list, table, calendar, timeline, or files. Plus members, teams, activity,

09:54 and settings. It’s built with plain JavaScript ES modules and CSS bundled by Vite, with no UI framework and no runtime dependencies. It’s a polished front end ready to wire up to REST and PostgreSQL. Deploy it and run your projects. Project number 13, Insomnia. Keep a MacBook awake, lid closed, for agents. Insomnia is an open-source macOS menu bar app, an eye icon, that safely keeps your MacBook awake with the lid closed for a timed agent session. It turns off the display and keyboard

10:25 backlight, saving their brightness. And if Wi-Fi drops, it can join your iPhone’s hotspot. It’s careful with permissions, a narrow sudoers rule, owner-only files, and sign releases. It needs a recent Apple Silicon Mac and is experimental. Use a ventilated surface, not a closed bag. Install it and run overnight. Project number 14, Brutal Framework. Open-source C# framework for games and engines. Brutal is a free open-source C# framework for making games or building your own engine on

10:56 top. It’s a framework, not a full engine. A custom interop layer exposes native APIs, Vulkan, and low-level C++ libraries, STL, GL ave, Jolt, and Box2D physics, FMOD audio, ImGui, glTF to C# with low allocations and minimal overhead. From Ahu and Rocketworks, it already powers Kitten Space Agency and RimWorld’s Waylith Engine. It’s free for commercial games, no royalties. Clone it and build. Project number 15, Libre

11:27 Calculator. Free private calculators for everything countable. Libre Calculator is a free, open-source collection of calculators for everything countable, the universe in numbers. It gathers 72 calculators across math, geometry, unit conversion, finance, cooking, health, construction, physics, dates, and statistics, and each one explains its answer rather than just a number. It’s fast and private with no sign-up and no ads. Use it in a browser at librecalculator.com or run the desktop app on Mac, Windows,

11:57 or Linux with a quick panel and key board shortcut. Open it and calculate. Project number 16, GPT with taste, better judgment and taste for GPT and Codex. GPT with taste is an open-source behavioral recipe that gives GPT and Codex better judgment and taste with less ceremony. From one recipe, it compiles system instructions plus per message steering through hooks. The prompt sets the behavior, and a reminder follows each of your messages. Instead of hedging and self-justifying, the model is pushed to choose sensible

12:29 defaults, preserve supported claims, synthesize useful results, and finish work with care. It’s backed by research on defensive writing. Install it and give GPT taste. Project number 17, CC Stretch, short replies that expand phrase-by-phrase on click. CC Stretch is an open-source Claude Code plugin that turns replies into stretch text, short by default with each phrase expanding in place when you click it. You read the skim version, then open just the parts you want more on. So, a long answer

12:59 stays scannable. A full mode opens everything. It works in Claude Code’s full-screen TUI and everywhere else every phrase shows open, so nothing is ever hidden. Install it from its marketplace and read less, expand on demand. Project number 18, Desk, a skeuomorphic Wayland desktop that’s literally a desk. Desk is an open-source skeuomorphic Wayland desktop for Linux where the desktop is a literal desk. Your windows are sheets on a walnut desk. The dock is a drawer. Your apps are binders on a bookshelf, and

13:31 notifications arrive in a post box. Nothing is a symbol. Take a sheet and the app opens on it. The room is ray traced, lit by one desk lamp. It’s written in C and an early beta. Log in and work at your desk. Project number 19, memory. Learned memory that survives context compaction. Memory is an open source project, learning residual memory for context compaction from Food on Fusion Lab. When an agent compacts its context into a summary, detail is lost. Memory supplements that summary with

14:02 learned soft memory from its history. A memory network reads the model’s hidden states and stores residual memory in a local SQLite file, keeping more of what mattered. It runs alongside Codex compaction, ships Qwen and GLM checkpoints, and needs two 80 GB GPUs. Clone it and compact with memory. Project number 20, agent play. Replay coding agent sessions as a map and timeline. Agent play is a free open source tool that replays your coding agent sessions as an interactive map and a timeline. A final answer hides the

14:34 story. Failed tests, approaches tried, errors fixed along the way. So, Agent play reads your Claude code, Codex cursor, and Copilot sessions, and shows what the agent did, where it stalled, and how it got there. It runs locally with no tracing setup and no runtime dependencies, and nothing leaves your machine. Run it with UVX and replay a session. Thanks for watching. See you in the next update.