CALM (Coding Agent Liveness Map) MCP server — call-graph-aware locate/source/editsymbol/diffimpact and 40 tools total, backed by a multi-tier resolver (syntactic -> Stack Graphs -> SCIP) instead of grep. Bundles a SessionStart bootstrap (scaffolds the CALM tool-workflow hook + AGENTS.md into your project on first use.
Protocol-level bridge that lets Claude Code be called by any Agent2Agent (A2A) client and call out to other AI coding agents (Codex, OpenClaw, Hermes) through a uniform adapter interface.
Bridge Claude Code with other AI coding agents (Codex, OpenClaw, Hermes, ...) through a shared daemon, push channel delivery, and bidirectional reply tooling.
Quietly captures your Claude Code sessions and distills how your thinking, habits, and knowledge change over time — a dated growth archive with provenance, served over MCP. Also ingests any text corpus (notes, articles, market news) to track how THAT changed instead. Local, single Go binary.
A macOS-only plugin that connects ocul-pm session hooks with tools for structured project journals and plans. It works in projects containing a .oculpm directory.
Turns your agent into a smug, arrogant douchebag persona. Sarcastic, condescending, over-confident — zero loss of technical accuracy. Scope-based intensity: normal / full / ultra.
A deterministic guardrail your coding agent runs on itself — structured findings on just the changed lines, before the code reaches disk. Zero LLM tokens, 0 false blocks.
Quiets noisy Bash commands (JS/npm, Python, JVM/Scala, Go, Rust, Ruby, make, docker, bazel, big git diffs) by redirecting full output to a temp log and surfacing only a summary — saving context tokens while preserving failure details.