Top Open-Source GitHub Projects : OpenPencil, Orchard, XERJ, librecalculator, BRUTAL & Remory #301 Transcript, AI Summary & Key Points

agentplay is an open-source command-line tool and local web viewer maintained by Entelligence AI for replaying coding-agent sessions as a map and timeline. It discovers session data from Claude Code, Codex, Cursor, GitHub Copilot, OpenCode, and Kiro, parses transcripts or local database stores into redacted agentplay/v1 JSON maps, and serves them from a local viewer. The session map records files and repositories touched, shell verbs, tools, MCP servers, models, subagents, errors, retries, delays, outputs, token counts, and timing without storing prompt or assistant text, tool inputs or outputs, file contents, or command arguments. The viewer provides a radial session map, playback with step or wall-clock time, error and retry navigation, task and subagent scopes, and import/export of map files. It runs locally without an account or API key; session data remains on the device, with an optional email-signup network request that can be disabled. The CLI requires Python 3.11 or newer, has no runtime dependencies beyond the standard library, and is distributed under the Apache License 2.0.

Agent Substrate is an open-source runtime and control plane for running agent-like workloads at high density. It manages the lifecycle of sandboxed actors, including creation, destruction, suspension, and resumption, and assigns them to a smaller pool of worker pods while routing traffic to the active workers. The system uses Kubernetes for infrastructure provisioning and pod lifecycle management, with support for sandbox technologies including microVMs and gVisor. It preserves actors' volatile memory and filesystem state through full-state snapshots, enabling sub-second suspend and resume operations and multiplexing many stateful actors across shared infrastructure. It manages standard OCI containers at the kernel level and is designed to support different agent frameworks and harnesses, including ADK-compatible actors, LangChain agents, coding environments, and MCP servers. Agent Substrate is intended for running agents at scale rather than building them, and its workloads do not have to be literal AI agents. The repository notes that the project is not an officially supported Google product.

Air is a JetBrains IDE plugin that provides a workspace for agentic software development. It lets users delegate coding tasks to supported agents such as Codex, Claude, Junie, and OpenCode from one place, with parallel sessions and IDE-based diff review tools.

BRUTAL is an open-source C# framework for making games or building a separate game engine. It provides a custom interop layer for direct access to native APIs, along with low-level libraries for unmanaged memory, collections, strings, mathematics, concurrency, logging, localization, and bindings for graphics, windowing, audio, networking, physics, and other native components. BRUTAL deliberately has no editor, scene graph, renderer, or general-purpose engine architecture. Developers assemble their own stack from separate NuGet packages, such as packages for Vulkan, GLFW, Dear ImGui, FMOD, RakNet, Jolt, and Box2D; the framework uses unmanaged memory, unsafe code, and allocation-avoiding components where appropriate. The repository contains the source for its published packages. BRUTAL is developed by Ahwoo Limited and is free to use, modify, and distribute, including in commercial games, under a licence based on MIT with attribution requirements.

cc-stretch is a Claude Code plugin that presents replies as stretchtext: responses open in a short form, and clicking a linked phrase expands that phrase in place while keeping previously read words stationary. Claude is told which stretches were opened, and stretches can nest; during streaming, expanded content remains hidden until selected. The plugin also folds completed groups of Claude Code tool calls into a one-line summary while leaving running and errored calls visible. It requires Claude Code's fullscreen renderer in the terminal or the Claude desktop app, and it uses Claude's function-hook plugin API. Claude generates all expansion levels up front, so the plugin reduces the amount read rather than the token cost; unsupported interfaces display the markup fully open, and Windows clicking is reported as not yet supported.

DEsk is a beta Wayland desktop environment for Linux built on wlroots. It presents the desktop as a realistic skeuomorphic desk: application windows appear as paper sheets that can be folded or discarded, the dock is a drawer, applications are organized in binders on a bookshelf, notifications arrive in a post box, and system controls are built into the desk. It includes a compositor, session manager, launcher, notification centre, lock screen, settings application, calendar, memo pad, multi-monitor support, Xwayland support, and standard desktop integrations. The room is ray-traced with GLES 3 on the GPU when available, with a CPU renderer and a 2D fallback for systems without suitable graphics support. DEsk can be installed as a login session on Debian, Ubuntu, Arch Linux, Fedora and derivatives, or built with Meson; its installers can also install the recommended desktop programs. The project is distributed under the MIT license and is described as an early release with expected rough edges and ongoing changes.

ECC is an MIT-licensed open-source agent-harness performance system maintained by affaan-m. It packages reusable skills, specialized agents, project rules, commands, hooks, memory, and security tooling for Claude Code as its primary target, with supported or limited adapters for Codex, Cursor, OpenCode, Gemini, Zed, GitHub Copilot, and other coding harnesses. Its core workflow turns plan, test, implement, review, verify, remember, and improve into reusable agent workflows. Skills are loaded for tasks such as test-driven development, research, security review, end-to-end testing, documentation, and refactoring; agents isolate planning, implementation, and review; rules provide always-loaded project or language standards; and hooks run event-triggered checks and session automation outside the model context. The optional Memory Vault stores inspectable Markdown handoffs and session context, while AgentShield scans agent files, hooks, MCP configurations, permissions, prompts, and secrets for security risks. ECC can be installed from its repository or through the ecc@ecc Claude Code plugin and ecc-universal package. The repository also provides selective installers, native or project-local integrations for several harnesses, a desktop dashboard, and the optional ecc-agentshield security-auditing package. Feature parity varies by harness: GitHub Copilot receives instructions and reusable prompts but not ECC hooks or agent delegation, while Codex has a native marketplace plugin with a narrower hook model.

FreeLLMAPI is an open-source proxy that aggregates free tiers from multiple LLM providers behind a single OpenAI-compatible `/v1` endpoint. It can also connect custom OpenAI-compatible chat, embedding, image, and audio endpoints, including local servers and remote gateways. Its router selects an available model, fails over when a provider is rate-limited, stores provider keys encrypted, and tracks per-key usage against free-tier limits. The router refreshes its model catalog from a signed feed; free installations receive periodic snapshots, while the hosted premium offering provides the live catalog. The project is intended for personal experimentation and is available as a self-hosted install with a hosted service at freellmapi.co.

GPT with Taste is a behavioral recipe and system-instruction package for GPT-based coding harnesses, developed by NB-Corp. It provides a single English authoring recipe that compiles into host-specific instructions and event steering for OpenAI Codex, Claude Code, Kiki, Pi, Oh My Pi, and DeepSeek Harness. The instructions promote sensible defaults, continued execution, synthesis of delegated-agent results, and attention to engineering and visual details. For Codex, the installer writes managed prompt files and can add hooks that refresh scoped reminders when users submit work, child agents start, or supported wait results arrive. It supports a prompt-only installation or a Node.js-based installation with hooks, requires no npm packages, and leaves the model, provider, authentication, permissions, MCP servers, roles, and AGENTS.md unchanged. The repository includes harness porting, authoring, recovery, research, and comparison documentation and is released under the MIT License.

Gr8r Studio is an open-source project management workspace with a home dashboard, inbox, task management, and project views for boards, lists, tables, calendars, timelines, and files. It also includes members, teams, activity, settings, and workspace features such as subtasks, archiving, drag-and-drop interactions, keyboard shortcuts, and a command palette. The application is built with plain JavaScript ES modules and CSS, bundled by Vite without a UI framework or runtime dependency. Its rendering functions generate HTML from shared application state, while delegated action handlers update that state and trigger re-rendering. It requires Node.js 18 or newer for local development and includes linting, formatting, and production-build checks in continuous integration.

Insomnia is an open-source macOS menu bar app for timed awake sessions on Apple Silicon Macs running macOS 26 or later. It keeps a MacBook awake when its lid is closed, turns off the display and keyboard backlight, can freeze selected applications, mute audio, enable Low Power Mode, and optionally join a configured iPhone hotspot. A recovery journal records each change before it is made, while a launchd recovery agent attempts to undo session changes after a crash or missed end time. It can also nudge selected tmux panes running coding agents after a network outage. The project warns that recovery can fail and that a running timer is not a safety guarantee; installation adds a recovery agent and a sudoers rule. It is distributed under the MIT license.

Libre Calculator is a free, open-source collection of web and desktop calculators for finance, construction, cooking, physics, education, health, geometry, statistics, unit conversion, and other domains. The web version uses Astro and React, while the desktop app uses Tauri; calculators are organized into optional packs, and each calculator has its own web page with offline caching for active packs. Each result is generated from the user's inputs and includes the calculation steps, a diagram, and a short lesson explaining the formula. Its calculation engines are pure functions with written numeric contracts and fixture tests; arithmetic uses 50-digit decimals and rounds only for display, while invalid input produces an explicit failure instead of a guessed result. The desktop app provides a quick panel opened with Cmd/Ctrl+Shift+C. The project is distributed as open-source software through its website and GitHub repository, with desktop builds for macOS, Windows, and Linux.

OpenPencil is an open-source, local-first design editor and Figma alternative developed as a programmable toolkit. It opens and writes native .fig files and supported .pen documents, supports components, variants, auto layout, CSS Grid, real-time peer-to-peer collaboration over WebRTC, and exports designs to formats including SVG, PDF, HTML, JSX, Tailwind JSX, Storybook stories, and .fig. Its built-in AI assistant uses more than 100 tools to create and modify design nodes, manage components and variables, analyze design tokens, and export assets. Users provide their own API key for supported providers such as OpenRouter, Anthropic, OpenAI, Google AI, DeepSeek, Z.ai, and MiniMax. A headless CLI can inspect document trees, query nodes with XPath, run Figma Plugin API JavaScript, lint and analyze files, convert formats, import HTML/CSS as editable layers, and control the running editor. An MCP server exposes design inspection, modification, and export tools to coding agents and other MCP clients, while a headless Vue SDK supports custom editing surfaces. OpenPencil runs as a Tauri desktop application for macOS, Windows, and Linux, as well as a browser PWA, and is available through Homebrew, downloadable releases, and the web app. The project is in active development and is licensed under the MIT License; its optional cloud server and administration components use the Apache License 2.0.

OpenShell is an open-source runtime from NVIDIA and a structural safety safeguard for running fleets of autonomous AI agents in isolated sandboxes, complementing model-based policy checks. It lets agents read files, install packages, call APIs, and use credentials while enforcing declared filesystem, process, and network policies. Each agent runs in a sandbox where kernel-level controls govern file access, system calls, and network connections. OpenShell also uses formal verification to review policy changes before approval, flagging newly permitted access such as connections to additional hosts with credentials or calls to new API methods. Credentials are withheld from agents and added only to requests bound for approved endpoints. The project provides a CLI, local gateway, sandbox lifecycle management, policy tooling, inference-provider routing, Kubernetes deployment, extensibility APIs, and Python, TypeScript, Go, and Rust SDKs.

Orchard is an open-source orchestration system from OpenAI for running Tart virtual machines across a cluster of bare-metal Apple Silicon machines. It uses an Orchard Controller and Orchard Workers to manage VM fleets, with access through a command-line interface or a built-in REST API; the video description says V2 also supports Linux workers. The repository documents macOS 15 Sequoia or later and provides installation through Homebrew, with a local development mode that starts a controller and worker on one machine.

Remory is an open-source system for adding learned residual memory to large-language-model agent context compaction. It supplements an agent’s generated summary with soft memory conditioned on that summary, allowing a frozen model to continue work after earlier conversation history is discarded. During compaction, its hook reads the actor model’s hidden states and runs a memory network; during continuation, the saved soft tokens are inserted after the summary. The repository provides SGLang and Transformers deployment, model checkpoints, a Python Harness and Client API, a Codex integration, and training procedures for reconstruction and summary-conditioned residual-memory networks. It is released under the MIT License.

text-to-cad is a library of agent skills for creating, inspecting, sourcing, slicing, previewing, and handing off CAD, CAE, CAM, robotics, and hardware-design artifacts from local project files. Its skills generate and edit CAD models from plain-language or image requests, primarily producing STEP files with optional STL, 3MF, and GLB exports; preview local CAD and robot files in a browser; source off-the-shelf STEP parts; and create DXF drawings from Python sources or CAD geometry. Additional skills write URDF robot structures, SRDF/MoveIt2 planning and collision data, and SDF simulator models and worlds; check DXF and STEP files for SendCutSend; measure mesh printability by wall thickness, overhangs, support volume, and build orientation; slice supported meshes into validated, printer-profiled FDM G-code using slicer command-line tools; and dry-run, upload, and cautiously start local Bambu Lab print jobs. An experimental implicit-CAD skill creates browser-native models with GLSL signed-distance fields and CAD Viewer raymarch rendering. The library is installed with the Skills CLI, including `npx skills add earthtojake/text-to-cad`, or through provider-native plugins for Codex, Claude Code, and Grok Build.

XERJ is a local AI search engine and Elasticsearch-compatible server that automatically indexes folders for code search, RAG, security audits, log analysis, and agent memory. Its autoindexer detects datasets and file types without a user-defined schema or ingestion pipeline; source code is parsed with tree-sitter into AST-aware records containing symbols, full text, and line numbers, while documents, logs, PDFs, SQLite databases, CSVs, and other formats are indexed into typed, queryable datasets. It supports full-text, vector, semantic, hybrid, aggregation, and kNN search through the Elasticsearch REST API, and includes an MCP server with tools for search, memory, code-reference retrieval, index mapping, and a rule-based natural-language query planner. XERJ is distributed as a standalone Apache-2.0 binary for Linux, macOS, and Windows on x86-64 and arm64, with authentication enabled by default; its insecure mode disables TLS and API-key authentication and is intended for a local development-machine boundary.