Shared on HN Oct 31, the zero-dependency agent reads and edits files, runs shell and git with checkpoints and undo, speaks MCP, loads SKILL.md skills and works with any model in the models.dev catalog, using about 1.7 MB of memory on Windows. Only Windows is fully tested (Linux builds and runs, macOS is source-only), and its source-available license bans commercial use and public forks.
Shown on HN Oct 31, adding @khalilgharbaoui/opencode claude code plugin to your OpenCode 1.x or 2.x config drives your logged in claude CLI as a subprocess, so you get Claude's own tools, MCP servers and skills (which OpenCode 2.2.3's built in Claude Agent provider skips) while OpenCode still runs Bash, Edit and Write behind its own permission prompts. It never touches your OAuth token and bills however your CLI does, but it's a brand new one person project (Show HN)…
Posted Oct 30, each runtime session gets an authenticated URL that forwards HTTP, SSE and WebSocket traffic to 1–5 allowlisted ports (8000–12000) and stops working when the session ends. It's microVM runtimes only, with public HTTPS and no PrivateLink for inbound connections…
Released Nov 1 under Nace.AI Open RAIL M, Drex Max returns a probability for every option in one forward pass instead of generating text, so routing, triage and guardrail checks can run locally: a 4 bit build fits 24 GB Apple Silicon Macs, with a Q8 0 GGUF and llama.cpp and Ollama forks for 48 GB machines or CPU. Its 67.52 on Decision Index 0.4 is self reported, and local Mac and CPU paths are text only for now…
Launched Oct 30, claude mcp add transport http scope user deployhq https://mcp.deployhq.com/mcp (or codex mcp add deployhq url ... ) signs you in through the browser, with no package or API key, and six tools answer questions about your projects, servers and recent deployments. It can't deploy, roll back, read logs or see secrets yet, needs a plan with API access, and admins can switch it off account wide…
Released Nov 1 with no listed breaking changes, /autofix pr now hands a check that's still failing after three fix pushes to a human and comments on the PR when it's blocked, while the PR watch skill gains in place to work in your own checkout. Generated UI cards are on by default, and an experimental Helm chart deploys the Managed Agent in one command…
Spotted something we missed? Start a thread.