OpenRouter Armor: plain-English classifier for agent tool calls
At a glance
Beta plugin sits between the model and your app: write hard-deny/soft-deny/allow rules in prose; Armor evaluates every tool call (powered by a decision model) and blocks policy violations before bash/git/exfil runs—Claude Code auto mode works via Ori on any OpenRouter model. This workflow is listed under safety, tool-calls, guardrails, coding-agents, learnable-paradigm.
Agents / tools
OpenRouter Armor, Jev, Claude Code, Ori, MCP tools
AWS Labs open-source (5k+★): one harness-neutral core turns Claude Code/Codex/Cursor/Copilot/Kiro/opencode into structured, verifiable delivery workflows via `aidlc config --harness` + doctor—install script, not a new agent.
SuperCompress v2 compresses context against the query (keeps answer-critical lines verbatim): ~64% mean cut on their B5 coding-agent suite with 24/24 evidence-retention passes; MCP/plugin for Cursor/Claude Code/Codex plus hosted API and open weights.
Oct 15 Every deep dive (Shipper + six OpenAI interviews): Cloud flop → Rust local agent → no-editor desktop app → ChatGPT merge; learnable arc on form-factor bets, separate model lines, and agent-native UX.
Anthropic’s Claude Code team documents a layered review stack—pre-PR verify, AI review + security block, risk-tiered human approvals, merge queue/flags, and fast rollback—so most agent PRs merge with ≤1 human while revert rate fell >40% as volume doubled.