HydraFusion’s research preview now draws from Claude Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, and GPT-6 Luna, tailors reasoning effort per stage, and upgrades Cascade with a judge/repair step and Critique with parallel tool-using critics. New HydraFusion Max targets harder tasks; both options stay in preview on Copilot Pro through Enterprise in VS Code, the Copilot app, and CLI.
Show HN launch: Graphicle indexes a repo into a tree sitter code graph plus docs, decisions, and past agent sessions in one local SQLite store, then returns cited file/line excerpts over a single MCP server with no API key or telemetry. Install with brew install graphicle ai/tap/graphicle and run graphicle setup to wire Claude Code, Codex, Cursor, and other MCP clients…
Open source coding agent jcode 0.98.1 (Oct 15) reduces idle CPU and disk reads in repos with many untracked files, shares model catalog processing across equivalent clients, and lets Desktop capable clients receive Markdown through a new user response tool…
Radar's new MCP server lets ChatGPT, Claude, and other MCP clients query its location data in plain English, for example to trace suspicious signups across shared devices, networks, and addresses, then export the user IDs as a CSV. Access is rolling out to enterprise customers first…
Precisely opened an MCP Server for Precisely Automate that exposes Automate Studio scripts and Evolve workflows as tools for Claude, ChatGPT, Copilot, and other MCP clients, plus native OData support for SAP Clean Core. One config works across assistants without rebuilding SAP integrations per LLM…
In an Oct 14 OpenAI case study, Amp CEO Quinn Slack says OpenAI models make up the majority of tokens used in Amp. He adds that some users burn 10B tokens a week, and that Calling Puck, built on GPT Live 1, lets you talk in real time, even from a watch, to the Amp assistant that launches and coordinates your other agents…
Spotted something we missed? Start a thread.
