Freerange, a static analysis tool built on the official TypeScript API, lets developers find potential NaN, Infinity, division by zero, and out-of-bounds array indexes in TypeScript code at compile ti…
AIBuildAI Agent 2.5 achieved #1 on OpenAI's MLE-Bench with a score of 70.7%, substantially outperforming the agents ranked 2nd through 5th. The AI agent, which automatically builds AI models, also ran…
A developer released Telegram AI Secretary, a self-hosted notification filter that uses an LLM to analyze Telegram messages and forward only important alerts to a phone via ntfy, enabling users to kee…
A developer built a chess game that runs inside the Claude Code CLI, where Claude suggests three possible moves for the player to choose from. The game supports local play against a bot or remote play…
Relay, a self-hosted LLM gateway and model router released as a single static Go binary under Apache-2.0, supports OpenAI and Anthropic API dialects inbound and routes across any provider outbound wit…
A developer created a /council skill for Claude Code that convenes a five-advisor council to pressure-test decisions, plans, or ideas. Based on Andrej Karpathy's LLM Council, the skill uses five subag…
LLMrPro, a new self-hosted LLM router, pools users' own machines as inference workers with automatic per-tier cloud fallback, exposing a single OpenAI-compatible API. The open-source project, released…
D-FINE-seg, a framework for real-time object detection, instance segmentation, and semantic segmentation, achieves higher F1 scores than YOLO26 and RF-DETR on Cityscapes detection and instance segment…
An unofficial open-source project lets users control the Codex Micro feature of the Codex desktop app on Mac from a phone over private Wi-Fi or Tailscale. The project, hosted on GitHub by maxxspotter,…
Unsloth announced AMD GPU support for local LLM training and inference, enabling 500+ models to run up to 2× faster with 70% less VRAM on AMD Radeon, Instinct, Ryzen, and data center GPUs. The release…
A developer released a production-shaped LangGraph multi-agent template that wires five critical production features—structured routing, parallel-branch reducers, per-node retry policies, hard budget …
A bug report on Anthropic's Claude Code GitHub repository states that the github-actions bot is labeling issues as duplicates without referencing the original issue, citing issue #79240 as an example.…
A new open-source tool called chrome-agent, built in Rust, provides an LLM-native browser automation tool that reduces page representation to ~50 tokens using the accessibility tree, compared to ~2,00…
A developer shared a setup combining the Pi coding agent with the Ghostty terminal emulator, featuring the tokyo-night-storm-improved theme, a custom statusline, tps meter, and startup header. The con…
An anonymous billboard on Aztec v5 mainnet allows users to deposit ETH on L1, post anonymous messages on L2, and withdraw ETH back to L1, with no sender address in public call data. The system include…
A developer created a Cache Break Notifier plugin for GitHub Copilot CLI that warns users when the AI assistant's context cache drops significantly between turns, helping to identify costly cache miss…
Newsline, a new open-source tool by developer itdar, lets users display rotating one-line news headlines in their terminal status line, designed to be used while waiting for AI agents like Claude Code…
GoCD MCP Server is a production-grade Model Context Protocol server that exposes GoCD pipelines over Streamable HTTP with per-user authentication via GoCD Personal Access Tokens, enabling MCP-capable …
A developer has built a pipeline using Claude Code and Higgsfield's CLI to produce 10-minute AI movies for about $200 each, with Seedance 2.0 for video, Nano Banana Pro for images, Sonilo for music, E…
A developer shared global CLI aliases that launch coding agents (agy, codex, claude, opencode) inside timestamped tmux sessions, bypassing permission prompts for faster iteration.…