A developer released Fitter, an open-source scraping engine that converts any website or API into structured JSON using declarative YAML/JSON configs instead of code, enabling LLMs like Claude Code to…
A developer released a local, extensible web viewer for coding-agent session archives that supports Pi and Codex, normalizing both formats into a searchable timeline while preserving raw JSON. The vie…
PenguinHarness, an open-source agent framework from Prism Shadow, claims to build agents at 100× the speed of LangChain with a zero-code CLI and Web UI connected to 1000+ models, achieving best accura…
Canonry has released an open-source, self-hosted AI engine optimization (AEO) operating platform that tracks citations across Gemini, ChatGPT, Claude, Perplexity, and local LLMs, and includes tools fo…
A GitHub repository released the compressed weights for the Conscious Field Transformer, a neural network with 14.88 trillion parameters stored in a 358 MB NPZ file, free and open source for any use. …
Poolside's Laguna S 2.1, a 118B MoE coding model, runs on a single RTX 5090 (32 GB) at ~19 tok/s decode and ~60 tok/s prefill using auto-fit layer placement. A developer achieved this by packing full …
A new curated list of Model Context Protocol (MCP) servers enforces a strict open-source, self-hostable, no-lock-in policy, excluding any tool that requires a paid proprietary backend or vendor cloud …
NotchAgent, a native macOS notch control surface for AI coding agents running under herdr, is now available. The app provides a color-coded status line below the MacBook notch, allowing users to monit…
A new open-source tool called serve-avd lets developers stream Android emulators to a browser window for use with AI agent tools like Codex, Cursor, or Claude Desktop, capturing the emulator's screen …
A developer released a conceptual blueprint for a Pre-Transformer Packet Rectifier that interlocks with the Fluidic_Network_Grid (FNG) V3 distributed data bus pipeline to mitigate computational bottle…
Forgesynapse Ltd. released ClawLite, a local-first personal AI assistant that runs on Telegram entirely on the user's machine with no subscription or cloud dependency, using Ollama for local LLM infer…
Netmon, a self-hosted local network monitor that runs hourly speed tests and LAN scans, sends sarcastic AI-generated reports to Telegram every four hours. The open-source Python tool, created by devel…
A developer has created agent_cli, a cross-agent command-line tool that unifies five AI coding agents—Claude, Codex, Cursor, Copilot, and Grok—behind a single interface. The script supports both read-…
Harbinger, a non-human identity (NHI) and agentic security platform, provides cryptographic identity (mTLS) and policy-based request checking for AI agents, bots, and service accounts without requirin…
A developer has released Readmer, a compiler that builds README.md files from Liquid or Jinja2 templates, aiming to reduce repetitive work for maintainers of multi-package projects. The tool stores te…
A developer released Millwright, an open-source, self-hosted LLM router built in Rust, designed to sit between coding agents and GenAI workloads for cost savings and transparency. The tool supports pr…
Rabbitty, a native Mac terminal for running AI coding agents in parallel, released Beta 0.1.0-beta.53 with faster integration panels, background prefetching for pull requests and Jira, and a fix for a…
Szr, a Go-native CLI proxy developed by devr-tools, reduces noisy terminal output before it reaches an LLM context, preserving exit codes and saving tokens on logs, diffs, and test output. It wraps co…
Cactus released Gemma 4 E2B Hybrid, a small on-device model that outputs a confidence score (0-1) for each answer, allowing developers to route low-confidence queries to a larger model. The model matc…
A free, open-source Chrome extension called Usage Bar for Claude displays Claude plan usage limits, a live token counter for the context window, and a prompt-cache countdown directly on claude.ai. The…