An audit of a NIST AI RMF-aligned prompt-governance rubric found documentation/implementation drift where only two of four specified rules for the 'fair_bias_managed' dimension are implemented, and a …
Kimi has launched 'Kimi Everywhere', a kit that lets developers run any coding harness—including Claude Code, Codex, OpenCode, Cline, and Aider—on a single flat-fee Kimi Code subscription ($19+/mo). T…
A developer created a tool called Agent Instruction Minto Refactor that refactors AGENTS.md, CLAUDE.md, and agent instruction files into action-oriented, Minto/MECE/runtime-sequenced documents while p…
Pedro Shakour released Grok-iOS, an open-source iOS client that lets users remotely control Grok Build from an iPhone over ACP via WebSocket. The app acts as a pager UI while the agent runs on a Mac u…
A developer is using large language models to automatically extract architectural parameters from the RISC-V specification, aiming to replace slow and error-prone manual reading. The approach involves…
A developer introduced graphwiki, a variant of Karpathy's LLM Wiki pattern that stores the maintained knowledge layer as a property graph in Neo4j instead of markdown pages. The design uses typed rela…
A developer created an AI agent skill for writing tests in the Nushell repository, emphasizing the use of modern `nu_test_support` infrastructure over older subprocess-style testing. The skill provide…
OpenAI has reduced the context size of its Codex model from 372,000 to 272,000 tokens, according to a developer note. The change affects the model's ability to process longer code sequences in a singl…
A new open-source project demonstrates how multimodal vector search works under the hood, using OpenAI CLIP (ViT-B/32) to embed text and images into a 512-dimensional vector space and Qdrant (HNSW ind…
A draft specification v0.9 for the Autonomous Company Interface (ACI) has been released as an open standard for describing organizations to autonomous agents through structured, machine-readable contr…
A curated list of tools and resources for 'vibecoding'—building software through AI prompts and iteration—has been published, featuring web-based builders like Bolt.new and Lovable, editors like Curso…
Agentty, an open-source Agentic Development Environment (ADE) built with Rust and Ratatui, launches as a terminal-based multi-agent orchestrator for AI-assisted software development, supporting Codex,…
Synapse, a local codebase indexer and MCP server for Claude Code, now lets developers give Claude instant knowledge of their project without uploading code to the cloud. The tool watches project folde…
Flightwake, an ultra-lightweight work-recording framework for strong AI coding agents such as Claude Fable 5, has been released as an open-source tool that creates Markdown-based flight records stored…
EnviousWispr, a free open-source AI dictation app for macOS, runs entirely on-device using Whisper and Parakeet speech-to-text models on Apple Silicon, with no cloud, account, or subscription required…
SafeAI, an open-source static analysis tool for AI agent source code, scans for security risks, capability exposure, and governance gaps without executing agents or calling LLMs, integrating into CI/C…
ADA, an open-source automated data analyst tool, enables users to upload CSV or Excel files and receive an interactive Plotly dashboard, anomaly detection, baseline forecasts, and plain-English questi…
A developer who built a long-running pipeline harness for coding agents found that frontier models (Fable 5, GPT-5.6 class) and platform vendors made the pipeline itself unnecessary. The surviving val…
Waylou ACE CLI, an open-source AI coding assistant forked from Google Gemini CLI, adds multi-provider support for Gemini, OpenAI, Anthropic, Ollama, and DeepSeek models through a single terminal inter…
Rcarmo released Memento, a cross-agent memory system that stores shared facts for multiple AI agents on the same network, using Markdown files with Git versioning and optional local semantic ranking v…