TokenWatt is a transparent, OpenAI-compatible proxy designed to measure the actual electricity cost of running local Large Language Model (LLM) inference on Apple Silicon hardware. By sitting in front of local inference servers and utilizing Apple's IOReport via SoC rail energy measurements, it provides real-time pricing for requests based on user-defined utility rates without requiring sudo privileges. The tool allows users to compare the cost-efficiency of local execution versus cloud API providers, particularly highlighting the economic advantages of running high-context agentic loops locally where context re-processing is essentially free (limited only by power).
- Uses Apple's IOReport for sudoless energy measurement on macOS/Apple Silicon.
- Provides an OpenAI-compatible interface that forwards requests byte-for-byte to backends like LM Studio or MLX.
- Supports dynamic model discovery so routing updates automatically when models are loaded into memory.
- Offers a calibration feature to replace estimates (±15–30%) with highly accurate measurements via smart plugs.
- Uses Apple's IOReport for sudoless energy measurement on macOS/Apple Silicon.
- Provides an OpenAI-compatible interface that forwards requests byte-for-byte to backends like LM Studio or MLX.
- Supports dynamic model discovery so routing updates automatically when models are loaded into memory.
- Offers a calibration feature to replace estimates (±15–30%) with highly accurate measurements via smart plugs.
Alvaro Bartolome provides a Rust-based implementation of the System One compatible API, designed specifically for open decision models such as Laya. The project features dynamic token-based batching and supports hardware acceleration via CPU, CUDA, and Metal (MPS). It is built using modern asynchronous frameworks like tokio and axum to provide high performance for model queries.
- Achieves approximately 14ms latency per query on an NVIDIA RTX Pro 6000.
- Includes support for ModernBert with custom decision heads for Laya models.
- Utilizes the Candle machine learning framework by Hugging Face.
- Supports multiple installation features via cargo, including specific flags for metal or cuda.
- Achieves approximately 14ms latency per query on an NVIDIA RTX Pro 6000.
- Includes support for ModernBert with custom decision heads for Laya models.
- Utilizes the Candle machine learning framework by Hugging Face.
- Supports multiple installation features via cargo, including specific flags for metal or cuda.
OpenProse is a declarative language for standing AI work, where users write Markdown contracts to describe a desired world state and a deterministic reconciler keeps reality matching it. The project applies classical declarative paradigms (SQL, Terraform, Kubernetes, React) to agent-based systems, using "Responsibilities" as the core unit — standing goals with sections for what they maintain, what they require from upstream, and what wakes them. It ships as a skill installable into any Prose-Complete agent host and runs without a separate binary.
- Tagline: "Stop scripting agents. Declare them."
- Forme, the wiring layer, automatically matches subscriptions between contracts so the dependency graph assembles itself with no manual wiring
- The old LLM-based judge loop was retired entirely in the v2 overhaul; a render fires only when a content-addressed fingerprint moves, with no model in the wake/commit decision
- The reference harness "Reactor" was extracted to its own repo and is labelled experimental (alpha)
- Tagline: "Stop scripting agents. Declare them."
- Forme, the wiring layer, automatically matches subscriptions between contracts so the dependency graph assembles itself with no manual wiring
- The old LLM-based judge loop was retired entirely in the v2 overhaul; a render fires only when a content-addressed fingerprint moves, with no model in the wake/commit decision
- The reference harness "Reactor" was extracted to its own repo and is labelled experimental (alpha)
Paul Sawers writes that Zed has launched Delta, a collaborative development platform now in public beta that replaces pull requests with shared threads preserving the full conversation between developers and coding agents. The move responds to both volume pressure on GitHub — monthly commits jumped from roughly 1 billion in 2025 to 2.9 billion by August 2026 — and a structural mismatch: when much of the reasoning behind a change happens inside an agent conversation, a bare diff gives reviewers little context. Zed has already disabled pull requests on Delta's own repository, where 33 developers have landed 570 changes to main through threads, and co-founder Nathan Sobo expects the company to fully leave GitHub within a few months.
- DeltaDB, the version control layer beneath Delta, records individual edits and conversation events between Git commits, a finer granularity than Git's commit-based model; Zed calls these individual records "deltas."
- Sobo predicts the thread will replace the commit or branch as the fundamental unit of software development, with commits remaining only as checkpoints.
- Competitors share the thesis: SpaceX-owned Cursor launched Origin in August 2026, and GitLab has Project Switch in private beta.
- Delta works with existing Git repositories, so contributors who don't adopt it can still submit conventional pull requests; the platform is free during public beta with paid plans to follow.
- Zed raised $32 million from Sequoia Capital in August 2025, a round that also teased DeltaDB.
- DeltaDB, the version control layer beneath Delta, records individual edits and conversation events between Git commits, a finer granularity than Git's commit-based model; Zed calls these individual records "deltas."
- Sobo predicts the thread will replace the commit or branch as the fundamental unit of software development, with commits remaining only as checkpoints.
- Competitors share the thesis: SpaceX-owned Cursor launched Origin in August 2026, and GitLab has Project Switch in private beta.
- Delta works with existing Git repositories, so contributors who don't adopt it can still submit conventional pull requests; the platform is free during public beta with paid plans to follow.
- Zed raised $32 million from Sequoia Capital in August 2025, a round that also teased DeltaDB.
mogenson wrote a Rust application that lets a Flipper Zero write to a Waveshare e-Paper Tag over NFC, effectively turning the passive paper tag into a programmable display.
i12bp8 writes about TagTinker, a Flipper Zero app for exploring infrared electronic shelf-label (ESL) protocols, enabling users to transmit custom images and text to supported e-ink graphics tags. The project bundles a browser-based image preparer with dithering and colour quantisation, NFC tag scanning for auto-identifying ESL targets, and optional WiFi plugins via an ESP32-S2 bridge that render live designs (crypto prices, weather, GitHub profiles) through a Cloudflare Worker without reflashing the Flipper.
- Security relies entirely on protocol obscurity; the Flipper team noted the IR signal is "same that you use in TV remotes"
- Tags store firmware in volatile RAM, so removing the battery permanently bricks them
- A sub-$5 ESP32 + IR LED setup replicates the functionality without a Flipper Zero
- The web preparer uses Oklab 3-colour quantisation with Floyd-Steinberg, Atkinson, or Bayer dithering
- Supports monochrome and accent-colour (red/yellow) tags including SmartTAG Color 2.6 (type 1626)
- Security relies entirely on protocol obscurity; the Flipper team noted the IR signal is "same that you use in TV remotes"
- Tags store firmware in volatile RAM, so removing the battery permanently bricks them
- A sub-$5 ESP32 + IR LED setup replicates the functionality without a Flipper Zero
- The web preparer uses Oklab 3-colour quantisation with Floyd-Steinberg, Atkinson, or Bayer dithering
- Supports monochrome and accent-colour (red/yellow) tags including SmartTAG Color 2.6 (type 1626)
Becquerel is a Python package for analyzing nuclear spectroscopic measurements, offering tools to read/write spectrum files, fit spectral features, perform detector calibrations, and interpret results. It relies on numpy, scipy, matplotlib, and pandas for data analysis and visualization. The package is designed for both educational and research use, supporting a wide range of users from undergraduates to advanced researchers.
- Developed by Lawrence Berkeley National Laboratory
- Supports spectrum file formats like N42, CHN, and CSV
- Includes tools for radiation spectrum plotting and nuclear data access
- Developed by Lawrence Berkeley National Laboratory
- Supports spectrum file formats like N42, CHN, and CSV
- Includes tools for radiation spectrum plotting and nuclear data access
This GitHub repository features ReadAny, a local-first AI e-book reader designed for desktop and mobile platforms. The application facilitates an intelligent reading workflow through semantic search, RAG (Retrieval-Augmented Generation) chat, highlights, text-to-speech, and WebDAV synchronization to build private knowledge bases from personal libraries.
- Supports multiple formats including EPUB, PDF, MOBI, AZW3, FB2, CBZ, and TXT.
- Features a "Skills System" for built-in or custom AI tasks like summarization or character tracking.
- Offers cross-device synchronization via WebDAV to keep notes and highlights in sync.
- Built with a modern tech stack including Tauri (Rust), React 19, TypeScript, and Tailwind CSS.
- Supports multiple formats including EPUB, PDF, MOBI, AZW3, FB2, CBZ, and TXT.
- Features a "Skills System" for built-in or custom AI tasks like summarization or character tracking.
- Offers cross-device synchronization via WebDAV to keep notes and highlights in sync.
- Built with a modern tech stack including Tauri (Rust), React 19, TypeScript, and Tailwind CSS.
The `check-if-email-exists` repository provides a Rust-based tool designed to verify the existence and deliverability of email addresses without actually sending an email. The project includes multiple ways to interact with it, including a CLI binary, a programmatic library for Rust projects, and a Dockerized HTTP backend that offers various verification features such as syntax validation, MX record checking, and SMTP server verification.
- Offers several modes: via CLI, through a Rust crate dependency, or using an HTTP/Docker backend.
- Verifies multiple properties including reachability status, disposable email detection, role account identification, and Gravatar URLs.
- Includes checks for "Have I Been Pwned?" to see if an email has been compromised in data breaches.
- Offers several modes: via CLI, through a Rust crate dependency, or using an HTTP/Docker backend.
- Verifies multiple properties including reachability status, disposable email detection, role account identification, and Gravatar URLs.
- Includes checks for "Have I Been Pwned?" to see if an email has been compromised in data breaches.
OpenHuman is an open-source agent harness designed as a personal AI super intelligence, featuring local-first memory through Markdown trees in SQLite and orchestration capabilities via checkpointed graphs. It functions as a brain that builds persistent context from various data sources like email and calendars, acting as both an orchestrator for multi-agent workflows and a deep researcher with built-in web search and media generation tools.
- Features "Memory Trees" stored locally in Markdown format to create a Karpathy-style Obsidian wiki.
- Provides end-to-end encrypted agent-to-agent messaging using the Signal protocol.
- Supports visual, trigger-driven workflows that can be proposed by an AI and reviewed on a canvas.
- Includes a "Privacy Mode" which ensures no inference data leaves the user's machine when toggled.
- Features "Memory Trees" stored locally in Markdown format to create a Karpathy-style Obsidian wiki.
- Provides end-to-end encrypted agent-to-agent messaging using the Signal protocol.
- Supports visual, trigger-driven workflows that can be proposed by an AI and reviewed on a canvas.
- Includes a "Privacy Mode" which ensures no inference data leaves the user's machine when toggled.
