Gleb Shalimov presents esp_ble_finder, a BLE scanning tool designed for the Waveshare ESP32-S3-Touch-AMOLED-1.8 hardware. The application helps users locate nearby devices by monitoring RSSI (Received Signal Strength Indicator) through a visual dotted UI and auditory feedback that mimics parking sensors.
- Uses an AMOLED display to show signal strength with dots and a filling line indicator.
- Features "parking-sensor clicks" where audio speed increases as the user gets closer to the target device.
- Allows users to hunt for specific devices by editing the `TARGET_NAME` in the source code.
- Includes a mute function that silences speaker clicks while maintaining the scan and visual updates.
- Uses an AMOLED display to show signal strength with dots and a filling line indicator.
- Features "parking-sensor clicks" where audio speed increases as the user gets closer to the target device.
- Allows users to hunt for specific devices by editing the `TARGET_NAME` in the source code.
- Includes a mute function that silences speaker clicks while maintaining the scan and visual updates.
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.
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.
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
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.
This repository provides optimized serving configurations for the Qwen3.8-27B model running on a single 24 GB consumer GPU (RTX 3090). It achieves high throughput of approximately 1,000 tok/s at 64 concurrent users in batch mode and up to ~133 tok/s for single-user scenarios using speculative decoding techniques like MTP or DFlash2. The project includes custom patches, requantization scripts (such as int8 tensor-core GEMMs), and Docker support to enable extended context windows of 150k to 262k tokens on a single consumer card.
- Offers two distinct serving profiles: `batch` for high throughput/API backends and `single-user` for low-latency chat experiences.
- Implements advanced speculative decoding modes including MTP (Multi-Token Prediction) and DFlash2 block drafting.
- Supports extreme context lengths up to 262k tokens through KVarN, which utilizes a lossy 4/2-bit KV cache.
- Includes specialized optimizations like int8 activations, quantized lm_head, and split-KV verify attention to maximize VRAM efficiency.
- Offers two distinct serving profiles: `batch` for high throughput/API backends and `single-user` for low-latency chat experiences.
- Implements advanced speculative decoding modes including MTP (Multi-Token Prediction) and DFlash2 block drafting.
- Supports extreme context lengths up to 262k tokens through KVarN, which utilizes a lossy 4/2-bit KV cache.
- Includes specialized optimizations like int8 activations, quantized lm_head, and split-KV verify attention to maximize VRAM efficiency.
Imran Hassanali presents a comprehensive benchmark comparing "Code Mode"—where an LLM generates complete code to execute tools—against traditional function calling for tool interactions. The results demonstrate that Code Mode is significantly more efficient, achieving 60% faster execution, 68% fewer tokens used, and an 87.5% reduction in API round trips while maintaining equal accuracy compared to regular agents.
- Evaluated using eight realistic business scenarios, including multi-client invoicing and expense tracking.
- Code Mode advantage scales with task complexity; high-complexity tasks saw up to a 79.2% speedup.
- The benchmark tested both Claude 3 Haiku (showing major efficiency gains) and Gemini 2.0 Flash Experimental.
- Secure code execution is implemented via RestrictedPython, preventing filesystem and network access during the sandbox phase.
- Evaluated using eight realistic business scenarios, including multi-client invoicing and expense tracking.
- Code Mode advantage scales with task complexity; high-complexity tasks saw up to a 79.2% speedup.
- The benchmark tested both Claude 3 Haiku (showing major efficiency gains) and Gemini 2.0 Flash Experimental.
- Secure code execution is implemented via RestrictedPython, preventing filesystem and network access during the sandbox phase.
Rohit Edathil writes about Dagic, a minimal workflow Directed Acyclic Graph (DAG) definition language and asynchronous execution engine implemented in Python designed for LLM agents. It provides a middle ground between standard tool calling and full code execution by allowing models to describe workflows through assignments and function calls that are parsed, type-checked, and executed concurrently without the security risks of arbitrary code execution.
- Performs ~7x more efficiently than per-call tools in math benchmarks regarding token usage
- Executes independent branches of a workflow concurrently using Python's asyncio
- Provides static type checking for tool arguments to prevent mid-run failures
- Avoids the need for sandboxing arbitrary model-generated code by restricting execution to host-registered functions
- Performs ~7x more efficiently than per-call tools in math benchmarks regarding token usage
- Executes independent branches of a workflow concurrently using Python's asyncio
- Provides static type checking for tool arguments to prevent mid-run failures
- Avoids the need for sandboxing arbitrary model-generated code by restricting execution to host-registered functions
Yiwei Ho writes about open-slide, a slide framework built for coding agents where you describe your deck in natural language and the agent writes React components rendered on a fixed 1920×1080 canvas. It handles navigation, hot reload, and present mode so the agent can focus on content rather than boilerplate.
- Works with any coding agent (Claude Code, Codex, Cursor, etc.)
- In-browser inspector: click any element to attach a comment, then run `/apply-comments` to have the agent apply all pending edits
- Integrated svgl catalogue for searching and dropping in brand logo SVGs
- Exports to self-contained static HTML or print-ready PDF with one command
- Presenter mode includes speaker notes, timer, and current/next slide preview
- Works with any coding agent (Claude Code, Codex, Cursor, etc.)
- In-browser inspector: click any element to attach a comment, then run `/apply-comments` to have the agent apply all pending edits
- Integrated svgl catalogue for searching and dropping in brand logo SVGs
- Exports to self-contained static HTML or print-ready PDF with one command
- Presenter mode includes speaker notes, timer, and current/next slide preview
