md-mode is an Emacs major mode that provides Org-inspired structural editing for Markdown files with live font-lock styling in the edit view and a read-only rendered view in the same buffer. It requires only Emacs 29.1 or newer and no external Markdown processor for its core in-buffer rendering.
- Tables remain valid Markdown source while being rendered responsively with width-aware column layout, debounced resize relayout, and per-buffer measurement caching
- Optional local integrations render LaTeX math, Mermaid, PlantUML, and Graphviz diagrams asynchronously with no content sent to remote services
- The renderer was adapted from agent-shell-markdown.el by Alvaro Ramirez
- Tables remain valid Markdown source while being rendered responsively with width-aware column layout, debounced resize relayout, and per-buffer measurement caching
- Optional local integrations render LaTeX math, Mermaid, PlantUML, and Graphviz diagrams asynchronously with no content sent to remote services
- The renderer was adapted from agent-shell-markdown.el by Alvaro Ramirez
Ayush Pande writes about how his Proxmox server became more useful after he stopped treating LXCs as Docker containers. Coming from a Docker-only background, he initially tried to manage LXCs as ephemeral, single-app environments, but realized they are fundamentally system containers that run a full userland (systemd, SSH, cron) and require managing the underlying OS just like a lightweight VM. Once he shifted his approach, his home lab's utility improved significantly.
- LXCs are system containers running a full userland, unlike Docker's single-process application containers
- Proxmox developers do not recommend Docker-in-LXC; live migration can break nested container environments
- VMs are the preferred Docker hosts from a security standpoint
- On low-spec hardware (e.g., a decade-old laptop), Docker-in-LXC can still make the box usable for experimental services
- LXCs are system containers running a full userland, unlike Docker's single-process application containers
- Proxmox developers do not recommend Docker-in-LXC; live migration can break nested container environments
- VMs are the preferred Docker hosts from a security standpoint
- On low-spec hardware (e.g., a decade-old laptop), Docker-in-LXC can still make the box usable for experimental services
Guillaume Meyer writes about watermarks-remover, a privacy-first open-source tool (MIT, Python stdlib) that strips multi-vendor machine-learning provenance marks from text and files the user owns. It operates across three layers: a deterministic Unicode and metadata scrub (Layer A), a best-effort LLM rewrite for statistical token-sampling watermarks (Layer B), and file-format-specific metadata stripping for C2PA, EXIF, XMP, and document properties across dozens of formats including images, video, audio, PDF, DOCX, EPUB, and more.
- 20.9k GitHub stars; formerly named "remove-claude-marks"
- Ships as a Claude Code plugin with a deterministic PostToolUse hook that auto-cleans files the agent writes without requiring model cooperation
- Includes a black-box watermark-stealing module (stealer/) and pre-commit hooks for CI gating
- The README carries an explicit disclaimer: Layer B rewriting degrades copy quality, and no tool can certify that a vendor detector will fail
- Optional external backends: CtrlRegen (ICLR 2025 pixel regeneration), MarkDiffusion, MarkLLM, and a model-free keyed-Gumbel (Aaronson EXP) detector
- Google retired its SynthID text watermarking API in August 2026
- 20.9k GitHub stars; formerly named "remove-claude-marks"
- Ships as a Claude Code plugin with a deterministic PostToolUse hook that auto-cleans files the agent writes without requiring model cooperation
- Includes a black-box watermark-stealing module (stealer/) and pre-commit hooks for CI gating
- The README carries an explicit disclaimer: Layer B rewriting degrades copy quality, and no tool can certify that a vendor detector will fail
- Optional external backends: CtrlRegen (ICLR 2025 pixel regeneration), MarkDiffusion, MarkLLM, and a model-free keyed-Gumbel (Aaronson EXP) detector
- Google retired its SynthID text watermarking API in August 2026
Cobus Greyling provides a practical pattern library, starter templates, and CLI tools for loop engineering using AI coding agents. This repository aims to help developers design systems that orchestrate agents to discover work, execute tasks, verify results, and persist state—moving beyond simple prompting toward automated agentic workflows.
- Includes the `@cobusgreyling/loop` unified CLI with commands like `init`, `doctor`, `status`, `audit`, and `cost`.
- Offers various patterns such as Daily Triage, PR Babysitter, CI Sweeper, and Dependency Sweeper.
- Features a tiered rollout strategy: L1 (report) $rightarrow$ L2 (assisted) $rightarrow$ L3 (unattended).
- Includes tools for observability like `loop-cost` to estimate token spend and ROI.
- Includes the `@cobusgreyling/loop` unified CLI with commands like `init`, `doctor`, `status`, `audit`, and `cost`.
- Offers various patterns such as Daily Triage, PR Babysitter, CI Sweeper, and Dependency Sweeper.
- Features a tiered rollout strategy: L1 (report) $rightarrow$ L2 (assisted) $rightarrow$ L3 (unattended).
- Includes tools for observability like `loop-cost` to estimate token spend and ROI.
This repository contains a highly customized, Zelda-inspired Oh My Zsh theme titled "Hero of Legend." Designed by knerd to gamify the command-line experience, it transforms the standard terminal into an interactive adventure featuring a 16-bit Heads-Up Display (HUD), a persistent Rupee economy, and various mini-games. Users can interact with their shell using gamepad-inspired mapping for Git commands, directory navigation, and file management tasks.
- Features a dynamic HUD that tracks "health" via Git repository status and time via a Majora's Mask inspired countdown.
- Includes an archery mini-game (`a!`) in the Downloads folder to earn Rupees by purging files accurately.
- Implements "Spells" for common tasks, such as `git add` (Magic Hammer) or `git commit` (Magic Scroll).
- Employs context-sensitive companion advice from characters like Navi and Princess Zelda based on terminal environment triggers.
- Features a dynamic HUD that tracks "health" via Git repository status and time via a Majora's Mask inspired countdown.
- Includes an archery mini-game (`a!`) in the Downloads folder to earn Rupees by purging files accurately.
- Implements "Spells" for common tasks, such as `git add` (Magic Hammer) or `git commit` (Magic Scroll).
- Employs context-sensitive companion advice from characters like Navi and Princess Zelda based on terminal environment triggers.
Anthropic provides a public repository of skills designed to enhance Claude's performance on specialized, repeatable tasks by dynamically loading instructions and scripts. These skills allow the model to master complex workflows such as branding adherence, data analysis, document creation, and technical development through self-contained folders containing markdown metadata.
- Skills are implemented using `SKILL.md` files with YAML frontmatter for name and description.
- The repository includes source-available (not open source) skills used in production for PDF, DOCX, PPTX, and XLSX document creation.
- Users can install these skills via Claude Code as plugins or use them through the Claude API and web interface.
- A separate "Agent Skills" specification is available at agentskills.io to standardize agent capabilities.
- Skills are implemented using `SKILL.md` files with YAML frontmatter for name and description.
- The repository includes source-available (not open source) skills used in production for PDF, DOCX, PPTX, and XLSX document creation.
- Users can install these skills via Claude Code as plugins or use them through the Claude API and web interface.
- A separate "Agent Skills" specification is available at agentskills.io to standardize agent capabilities.
Pushpak Chhajed writes about the evolution of project rule systems for AI coding agents, explaining why Laravel Boost moved away from complex semantic search layers in favor of a simple markdown-based approach. To prevent instruction files like `CLAUDE.md` from becoming bloated and consuming excessive context, the team implemented a system using `.ai/rules` containing specific Markdown files linked by a generated two-column index. This "progressive disclosure" method allows agents to efficiently locate relevant project conventions without overwhelming their prompt window or requiring complex vector databases for small rule sets.
- The system uses an automatically updated `index.md` file to help agents map current file paths to specific rule files.
- Agents are encouraged to use a combination of index matching and `grep -rin` to find rules that span multiple directories.
- This approach aligns with advice from the Anthropic Claude Code team regarding progressive disclosure in agentic workflows.
- The solution avoids "staleness" risks associated with maintaining separate vector embeddings for small collections of files.
- The system uses an automatically updated `index.md` file to help agents map current file paths to specific rule files.
- Agents are encouraged to use a combination of index matching and `grep -rin` to find rules that span multiple directories.
- This approach aligns with advice from the Anthropic Claude Code team regarding progressive disclosure in agentic workflows.
- The solution avoids "staleness" risks associated with maintaining separate vector embeddings for small collections of files.
This repository provides an open-source face recognition software development kit (SDK) for Windows and Linux systems, developed by Faceplugin. It uaes deep learning models to offer on-premise processing of facial data, ensuring privacy as no information leaves the user's device. The toolkit supports various functions including face detection, landmark detection, feature embedding generation, and similarity comparison via Python APIs.
- Supports JPG, PNG, BMP, and TIFF image formats
- Compatible with both CPU and GPU acceleration
- Requires Python 3.9 or higher and Anaconda is recommended for setup
- Includes capabilities for bounding box extraction and facial landmark detection
- Supports JPG, PNG, BMP, and TIFF image formats
- Compatible with both CPU and GPU acceleration
- Requires Python 3.9 or higher and Anaconda is recommended for setup
- Includes capabilities for bounding box extraction and facial landmark detection
@githubprojects writes about Quivr-core, a Python package extracted from Quivr.com's production retrieval-augmented generation pipeline that lets developers get a working system in five lines of code. It centers on a `Brain` class that ingests files and answers questions, with a YAML-configurable workflow (filter history → rewrite → retrieve → generate) that keeps the pipeline inspectable rather than a black box. It supports OpenAI, Anthropic, Mistral, and local Ollama models, and handles PDFs, Markdown, and TXT files out of the box.
- Integrates with Megaparse for more sophisticated document ingestion without switching frameworks.
- The opinionated philosophy is the core differentiator: sensible defaults over an infinite configuration surface.
- Integrates with Megaparse for more sophisticated document ingestion without switching frameworks.
- The opinionated philosophy is the core differentiator: sensible defaults over an infinite configuration surface.
rohitg00 writes agentmemory, a persistent memory solution for AI coding agents designed to eliminate the need for repetitive context re-explanation between sessions. By silently capturing tool usage and session details through various hooks (including native plugins for Claude Code, Cursor, and Codex), it compresses observations into searchable structured memories that are injected back into subsequent conversations. The system utilizes a hybrid retrieval approach combining BM25 keyword matching, vector embeddings, and knowledge graph traversal to ensure high-quality context injection with significant token savings compared to standard long-context prompting.
- Supports multiple agents including Claude Code, Cursor, GitHub Copilot CLI, Devin, Gemini CLI, OpenCode, Hermes, and more via MCP or native plugins.
- Employs a 4-tier memory consolidation model: Working (raw observations), Episodic (session summaries), Semantic (extracted facts), and Procedural (workflow patterns).
- Offers high retrieval accuracy; real-world benchmarks show up to 95.2% R@5 on the LongMemEval-S dataset.
- Reduces LLM token costs significantly, claiming ~170K tokens per year compared to millions when pasting full context.
- Includes a real-time visualizer (on port 3113) and an observability console for monitoring memory writes, traces, and graph structures.
- Supports multiple agents including Claude Code, Cursor, GitHub Copilot CLI, Devin, Gemini CLI, OpenCode, Hermes, and more via MCP or native plugins.
- Employs a 4-tier memory consolidation model: Working (raw observations), Episodic (session summaries), Semantic (extracted facts), and Procedural (workflow patterns).
- Offers high retrieval accuracy; real-world benchmarks show up to 95.2% R@5 on the LongMemEval-S dataset.
- Reduces LLM token costs significantly, claiming ~170K tokens per year compared to millions when pasting full context.
- Includes a real-time visualizer (on port 3113) and an observability console for monitoring memory writes, traces, and graph structures.
