CtxRay, a local-first observability and control layer for OpenAI Codex, launched with benchmark results showing a 73.3% reduction in estimated model-visible prompt and a 29.1% reduction in exact aggre…
SynapsCLI, an open-source agent runtime written in Rust, launches on Hacker News, enabling users to control an agent swarm while optimizing LLM costs and resource use. The project, started four months…
Celerp, a self-hosted accounting and ERP system created by a developer with 20 years of experience building ERP systems for factories, wholesalers, and gemstone & jewelry businesses, launches as a des…
Rafaelpta released litepipe, an open-source macOS app that captures everything a user sees, says, and hears on their computer into a local SQLite database with full-text search, making zero network ca…
CodeSlimmer v2.2, a new open-source tool by developer akasula09, converts local codebases or public GitHub repositories into a single LLM-ready text file with token estimation and directory mapping, c…
A developer released Context Base, a skill that helps AI agents understand a project before making changes by reading the repository, separating facts from guesses, and asking users only for context t…
Qubitz, a local-first AI agent for GGUF models on llama.cpp, aims to make 7B–35B MCP/tool-capable LLMs more predictable and useful through a specialized harness and Agent Behavioral Contracts. It oper…
Wardline, an open-source Go proxy released by developer Kabir Narang, automatically blocks compromised AI agents in real time by enforcing identity, policy, budget, and audit with statistical anomaly …
Beacon, a self-hosted error tracking and LLM observability tool from developer Tboworst, ingests errors from any service, groups them by root cause, and displays them in a live terminal dashboard or b…
An open-source Verilog implementation of a Tensor Processing Unit (TPU) with a 32x32 systolic array was designed, but due to excessive area (1,749,468.03 units) preventing place-and-route, the design …
Intel has released LLM Scaler, a GenAI solution for text, image, and video generation optimized for Intel Arc Pro B60 and B70 GPUs, with the latest version intel/llm-scaler-vllm:0.21.0-b2 adding Multi…
A new open-source showcase from ProtoLink places autonomous agents in a fictional liability tribunal to make agent-to-agent communication observable, with replayable opinion changes after every public…
Sufleur, a solo project by an unnamed developer, launched as an npm-style prompt registry with a CLI that generates typed code for Mustache-based prompts, featuring semver versioning, immutable versio…
A new open-source tool called us-vs-them provides line-level provenance for text under agentic editing, determining whether each line was written by a human or an AI agent based on a text's version hi…
Hermes plugin developer released an adversarial LLM reversal tool, hermes-agent, that catches large language models sandbagging in real time by forking two disposable clones every seventh turn to inte…
ParallelClusterMaker, an open-source CLI toolkit co-written with Anthropic's Claude Code, automates the creation and destruction of AWS ParallelCluster v3 stacks, enabling researchers and engineers to…
A new open-source web tool, remote-mcp-server-tester (also available as mcp-tester), lets developers inspect any Model Context Protocol (MCP) server by browsing its tools, resources, and prompts, meas…
A developer has created an output style for Claude Code that enforces ASD-STE100 Simplified Technical English, a controlled language originally developed for the aerospace industry. The style rules li…
A developer has compiled a definitive deny-list of AI writing tells for OpenTrawl's landing-page copy, aiming to produce copy that reads like a sharp human wrote it. The list includes classic AI vocab…
Wieland Hoffmann and Cloud released K3I-Core, an open-source hardware-level Linux kernel isolation system that claims to solve the AI value alignment problem by anchoring machine ethics in physical ha…