agent tooling

A semantic diff tool for Sigil code that highlights contract, effect, signature, and test-impact changes for reviewers and agents.

A persistent memory layer for AI agents, built as a standard MCP server with local setup, dashboard, and benchmark claims against other memory tools.

A blog post describing ptc_runner’s MCP server and code-mode approach, where agents run short-lived untrusted programs inside a small Lisp REPL instead of Python or JavaScript.

A drop-in memory plugin for Hermes Agent that uses a pull-model episodic memory approach with real deletes and audit traces. It supports synchronous writes, trace logging, and Claude-backed summarization for on-demand recall.