A Nov 2 email to users says one combined view will let you go from talking through an idea to having ChatGPT build a site, make a deck or act on the web with your files and plugins, starting with a small test group before a wider rollout. OpenAI's Thibault Sottiaux said on X it's "not rolling out just yet," and no date has been given (The Verge).
Shown on HN Nov 2 under GPL 3.0, the MCP server reads the journal, units, processes and disks from a strictly confined snap where AppArmor blocks writes and internet sockets, and the model can only propose typed plans like restarting one failed service, which you apply with maatctl and a polkit prompt into a hash chained audit trail. It's a developer preview tested only on Ubuntu 24.04 arm64, and the author's first local model runs ( gpt oss:20b found the root cause 28 of 30 times) cover ten admittedly easy scenarios (Show HN)…
Shown on HN Nov 2, the local Go CLI wraps agenttm run codex "task" , logs events to SQLite with before and after workspace snapshots, and serves a UI at 127.0.0.1:7331 to browse historical files, compare diffs and fork any checkpoint into .agenttm/worktrees/ without touching your tree, index or HEAD. v0.1 only captures non interactive Codex runs it launches, file snapshots aren't redacted, and only Windows end to end use is reported as tested…
Shown on HN Nov 2 with an Apache 2.0 core, it sits between agents and databases, applies rules to each tool call, compares the real change with the agent's report (its demo catches an agent claiming 1 row while a trigger changed 301), signs each result as an offline checkable record and can undo the changed rows. npx y deedglass protect guards Claude Code, Cursor and other coding agents locally with no account, and ee/ features are under FSL 1.1…
Shown on HN Nov 2 under Apache 2.0, claude mcp add knock uvx knock mcp serve repo . toolset map gives the agent map , open and remember tools that return a skeleton of relevant code with line ranges plus saved findings flagged fresh or stale, all locally with no API key. The author's median of three runs on Saleor cut cost from $0.49 to $0.25, but says gains vanished on a small repo and quick edits cost slightly more (benchmark)…
Shown on HN Nov 2 under Apache 2.0, it starts each run with a roughly 1,250 token prefill of nine core tools, lets the model switch on web, memory and MCP tools only when needed, and holds a reply once if the model claims a file it never wrote, while an honest "I couldn't" always passes. It runs on Ollama, LM Studio, llama server or any OpenAI compatible endpoint, inside editors via ACP or its own web UI, and the authors say their 4B model test samples are small and early (Show HN)…
Spotted something we missed? Start a thread.
