The always-on agent, now in beta on Pro and Enterprise plans, reads merged diffs, repeated support questions, and flagged Slack threads, drafts the doc change, and opens a pull request that a teammate must merge, learning your team's tone from each review. It costs 250 credits per PR it opens or updates (runs that find nothing are free), and Pro plans can only connect GitHub and Slack.
Double tap Control, rest the cursor on the broken UI element, and talk; the free, open source macOS app queues your transcript (speech to text runs on device, no account) with a cropped screenshot that Claude Code, Codex, or Cursor can pick up over MCP, fix, and mark done. It launched on Product Hunt on Oct 19 and needs Apple silicon…
The open source terminal agent's Oct 19 release lets a hosted parent launch snapshot isolated children that can read a frozen copy of the workspace without editing files or running commands, and adds Kubernetes workspaces that keep files across sessions, SSH and native macOS runtimes, and in session switching between default, auto edit, and yolo modes. No breaking changes are listed; update with npm install g @qwen code/qwen code@latest…
Scope (MIT) runs the same task through agents like GitHub Copilot and Claude Code over repeated runs, scores each against a dependency graph of criteria with an LLM judge, and keeps tool calls, logs, and workspace snapshots so you can trace where an agent got stuck. There's no hosted version: you run it locally with Docker Compose or on Kubernetes via Helm, and the default worker needs a Copilot entitlement (GitHub)…
The MIT repo, built from the setup behind Votito, bundles a sandboxed Claude Code container, a bash command regulator that auto approves or denies with guidance, a lint on edit PostToolUse hook, and a generator that turns a plan into multi agent workflow scripts with test gates. Its author says moving that orchestration out of the LLM cut token spend by about 80% versus a bare Claude workflow (Show HN)…
Fine tuned from Qwen3.8 27B on 127 real engineering sessions, it ties its base at 133/150 on BenchLocal while generating 25% fewer tokens, and its multi token prediction draft head roughly doubles code generation on an RTX 4090 (49 to 96 tokens/sec). Apache 2.0 BF16 and GGUF weights are on Hugging Face, and the benchmarks are Continuity Research's own runs…
Spotted something we missed? Start a thread.