GitHub is a developer platform for building, shipping, and maintaining software. It provides cloud-based Git repository hosting, CI/CD via GitHub Actions, project management with Issues and Projects, code review via pull requests, AI-powered development with GitHub Copilot, and APIs (REST and GraphQL) for automation and integration. GitHub documentation is available at https://docs.github.com. The content covers GitHub.com (cloud), GitHub Enterprise Server, and GitHub Enterprise Cloud. To retrieve full article content, page lists, or search results programmatically, please use the APIs below.…
Declarative 3D and AR SDK for Jetpack Compose (Filament, ARCore), SwiftUI (RealityKit, ARKit) and the web (Filament.js, WebXR), with Flutter, React Native and Compose Multiplatform bridges and shared core logic via Kotlin Multiplatform. This file is the complete API reference, written to be read directly by any AI assistant. SceneView is a declarative 3D and AR SDK for Android (Jetpack Compose, Filament, ARCore), Apple platforms — iOS, macOS, visionOS (SwiftUI, RealityKit, ARKit) — and the web (Kotlin/JS, Filament.js, WebXR), with…
Entity-level semantic merge driver for Git. Resolves conflicts at the function and class level using tree-sitter. weave replaces git's line-level merge with entity-level merge. It parses all three versions (base, ours, theirs) with tree-sitter, extracts functions/classes/methods, matches them by name and structural hash, and merges per-entity instead of per-line. Two developers editing different functions in the same file? No conflict. Git would flag this as a conflict because the line ranges overlap. weave knows they're different entities and merges cleanly.
Bernstein is the open-source governance layer for AI agents, with a deterministic scheduler driving CLI coding agents (Claude Code, Codex, Gemini CLI, and 40+ more). Scheduling is plain Python - no LLM in the coordination loop - so runs are reproducible end to end. Every coding task runs in its own git worktree behind lint/type/test gates; artifact-mode tasks complete on a signed lineage receipt in an isolated plain directory instead. An always-on lineage spine and replay journal record what happened;…
Bernstein is the open-source governance layer for AI agents, with a deterministic scheduler driving CLI coding agents (Claude Code, Codex, Gemini CLI, and 40+ more). Scheduling is plain Python - no LLM in the coordination loop - so runs are reproducible end to end. Every coding task runs in its own git worktree behind lint/type/test gates; artifact-mode tasks complete on a signed lineage receipt in an isolated plain directory instead. An always-on lineage spine and replay journal record what happened;…
Complete content of hermesatlas.com as of 2026-09-28. Concatenated from guide pages, ecosystem overview, the quarterly report, and project summaries. Canonical URLs preserved throughout. This file is the companion to https://hermesatlas.com/llms.txt…
The decision layer for Hermes Agent by Nous Research — install guidance, mode and skill picks, and a community-curated catalog of 248+ tools, skills, plugins, and integrations with live GitHub…
CLI for generating and managing appxmanifest.xml, image assets, certificates, Windows SDK projections, package identity, and MSIX packaging for any app framework targeting Windows. winapp helps developers add Windows-specific features (MSIX packaging, push notifications, native APIs) to apps built with any framework—Electron, Tauri, .NET, C++, Rust, or others. It handles the complexity of Windows app identity, code signing, and SDK integration. A single shared plugin at plugins/winapp/ serves both GitHub Copilot and Claude Code. It includes:
Kingfisher is an open source secret scanner and credential-response tool. It detects exposed credentials, validates which are active, maps blast radius, supports visual triage, and revokes supported secrets. Kingfisher is written in Rust and licensed under Apache-2.0. Use TOON output for LLM and agent workflows: kingfisher scan <target> --format toon --no-update-check.
AI-powered design review skills for KiCad electronics projects A suite of 11 skills that turn an AI coding agent into an electronics design assistant. Structured Python analysis scripts (zero dependencies, Python 3.10+ stdlib only) for KiCad 5-10 projects. Works with Claude Code, OpenAI Codex, Cursor, and Google Antigravity. Capabilities: schematic analysis (40+ subcircuit detectors), PCB layout review, EMC pre-compliance (44 rules), SPICE simulation, thermal analysis, component sourcing (DigiKey/Mouser/LCSC/element14), BOM management, manufacturing prep (JLCPCB/PCBWay), and professional documentation generation. Install: /plugin marketplace…
CUDA-Q streamlines hybrid application development and promotes productivity and scalability in quantum computing. It offers a hybrid programming model designed for a setting where CPUs, GPUs, and QPUs work together. CUDA-Q contains support for programming in Python and in C++.
ClawBio is a local-first, privacy-focused, reproducible bioinformatics AI agent skill library built on OpenClaw. This file is the fast entry point for LLMs discovering the repository. - Current public release:…
================================================================================ ## PART 1 — TWO API NAMESPACES ================================================================================ fastCRW exposes two distinct base URLs. Always pick the correct one. RULES: - Fetching content from the web → https://api.fastcrw.com -…
CRW is a high-performance web scraper for agents and developer workflows. Start with one scrape request, then branch into crawl, map, search, extraction, or MCP as needed. Source: https://github.com/fastcrw/crw
A hands-on cookbook for agent memory in Large Language Model (LLM) applications. 30 runnable Jupyter notebooks covering every major memory pattern: short-term conversation buffers, long-term storage, cognitive architectures, retrieval patterns, frameworks (Mem0, Letta/MemGPT, Zep, Graphiti), and production deployment. Each notebook is paired with a sub-README that explains the technique, when to use it, its limitations, and a per-technique architecture diagram. The repository is licensed Apache 2.0.
Local memory for coding agents, built from the session transcripts they already write to disk. deja indexes what Claude Code, Codex, Cursor, opencode, Gemini CLI, Zed and twenty-nine more agents wrote on this machine — including the months before it was installed — and answers from them over MCP or the command line. BM25 over the transcripts: no model, no embeddings, and no network path unless you ask for one. Two things distinguish it from memory tools that record forward:…
Local-first real-time dashboard for Claude Code: native hooks POST to an Express + SQLite server, the React UI updates over WebSocket, and an optional local MCP server exposes safe dashboard tools. This repository is MIT-licensed; default stack is Node.js 18+, React 18, Vite, TypeScript, and better-sqlite3. Important context for tools and answers: Techniques and patterns used: - Local-first architecture: runs on the developer machine, data stored in SQLite, no cloud dependencies. - Hooks-based integration: native hooks POST to the Express…
mbaileyllms.txt
