Gemma Translator
Google's Gemma Translator, built with Google Antigravity, enables fully offline, on-device voice translation using the Gemma 4 large language model and LiteRT-LM, with text-to-speech powered by Moonsh…
Google's Gemma Translator, built with Google Antigravity, enables fully offline, on-device voice translation using the Gemma 4 large language model and LiteRT-LM, with text-to-speech powered by Moonsh…
NextBlock CMS, an open-source, AI-native CMS for Next.js 16 and Supabase, launched on Hacker News, claiming 100% Lighthouse performance and native AI-readiness. The open-core product is free under AGP…
Nathan Cord's Superlawyers prompt library provides 65 production-tested Claude prompts across 12 practice areas, each following a CONTEXT → TASK → FORMAT → CONSTRAINTS structure. The library includes …
Anthropic's Claude Code v2.1.212 on macOS in IntelliJ IDEA terminal sent a user's real email address as the User-Agent string in a curl command without explicit confirmation, according to GitHub issue…
Hindcast, a new Mac app by developer Karan B, indexes, searches, and replays every Claude Code session locally, reading transcripts from ~/.claude/projects/ without sending data off-device. As of Augu…
Dbctx, a new open-source tool, compiles a PostgreSQL database into a compact, queryable context file (.dtx) that helps LLMs generate accurate SQL queries by including expected value sets and JSONB pat…
Jan Bogaerts released md², an Electron desktop app that organizes AI coding work around Markdown feature cards and Git worktrees, with a signed Windows x64 installer available and macOS/Linux runnable…
Dbward, an open-core project, has launched approval workflows and audit logs for production databases, featuring multi-step approvals, tamper-evident audit trails, and AI agent guardrails. The core co…
Martin Krasserm released agent-exchange, an open-source tool that lets terminal-based agents such as Claude Code and Codex exchange messages via the asn command-line interface, supporting local, remot…
An open-source, local-first video editor built for coding agents has been released after nearly 3 years of development. The browser-based editor uses WebCodecs for encoding and decoding, offers an inf…
Ts-profanity-filter, a TypeScript library for context-aware profanity filtering, now offers a streaming batch runner with a CLI, PII detection, and optional AI checks, supporting English and German ou…
A developer's Browser Agent harness outperforms Browser Code on the BU Bench v1 benchmark, achieving an 88% success rate at $5.37 and 32,694 seconds, compared to Browser Code's 78% success rate at $8.…
Porcupine, a terminal AI agent built for safe autonomy, has been released as an open-source tool on GitHub, requiring Node.js 22.19+ and installable via npm. It offers Ask, Normal, and Auto modes to l…
Shalom Borohov released Claude Fleet, a Windows widget that tracks multiple Claude Code sessions in an always-on-top strip, sorting them by urgency so users can see which session is waiting on them. T…
A new CUDA benchmark compares three knowledge-distillation loss implementations—Full Dense KL, Forward-Chunked Loss, and Full Chunked KL—showing that the Full Chunked KL method fuses the output projec…
Mutaz Abubaker released a research preview of DeepSeek V4 Flash, a 78.62 GiB GGUF model with 284.33B logical parameters, that runs on a Linux laptop with only 7.7 GiB of physical RAM and no GPU using …
Frags, an advanced AI/LLM agent framework for executing complex workflows of data retrieval, transformation, extraction, and aggregation, is now available as a CLI tool and a Golang library. The syste…
A developer has built a WhatsApp-to-Discord message forwarder that integrates with the go-whatsapp-web-multidevice (GOWA) REST API. The tool filters messages from a specific WhatsApp chat, resolves se…
A developer has outlined a workflow that automates AI-powered security analysis on GitHub pull requests, posting summarized reports as comments. The process fetches changed files, scans for vulnerabil…
Anansi, an open-source, self-hostable memory API for LLM applications, was released on GitHub under the MIT license, with a commercial enterprise layer. It provides two API calls, /v1/ingest and /v1/c…