MIT Python package signs every policy-gated tool call into a hash-chained .tkb file verifiable offline (Python+TS); works across Claude Code, OpenAI Agents, LangChain/LangGraph, MCP and more—agents can edit their own logs but not hide edits when the signer is out of reach.
Local-first Apache-2.0 CLI for Claude Code/Codex/Cursor: mcp-xray ranks bloated tool schemas, sync compresses CLAUDE.md↔AGENTS.md↔Cursor rules, and shield fails CI on leaked keys/prompt-injection/Trojan Unicode—claims large cuts in model-visible prompt size without API calls.
Thesys’s OpenUI hit 1.0 (Oct 15): models stream OpenUI Lang into your registered React components (cards/forms/charts); Lang 1.0 adds defineAction/defineFunction, library.extend, and stored messages; CLI scaffolds apps and setup-agent writes AGENTS.md for Claude Code/Codex/Cursor—vendor tiktoken bench claims ~53% fewer tokens vs JSON-render formats.
Octopus Cloud ships a built-in HTTP MCP at /mcp so coding agents can list spaces/projects, check PR deployment status, create/promote releases, run runbooks, search task logs and audit events—no per-machine local MCP to install; Server gets it in 2026.3.
Open-source MIT guardrail tracks audience×trust labels across tool calls (algebra, not LLM-as-judge), returns remedy plans (sanitize/authority/subagent) so agents keep ~90% task completion with 0% exfil on their benches—plugs via pre/post tool hooks; docs also as MCP.