Detect stale references and context rot in AGENTS.md files. Keep your AI coding agents accurate and cost-efficient.

Diagnose context rot before your coding agent reads it.

Local-first MCP server for search isolation, memory ledger, context rot detection, and cost governance

Enforce rules on AI coding agents — guardrails that run outside the context window, so they survive context rot, compaction, and agent amnesia.

Context Rot Detection & Healing MCP Service — gives AI agents self-awareness about their cognitive state. Supports 15+ curated models and auto-resolves any HuggingFace model.

Machine-checkable fitness-to-build gate — denies starting a high-risk P4 build in a degraded (context-rot) session unless an audited override is recorded (C13).

Command a bot army for your codebase: an Opus Mission Control delegates whole-project goals to specialist squads and ships behind a human merge gate. Five AI CLIs, zero context rot.

Eliminate context rot in Claude Code with intelligent memory, auto-learning hooks, and specialized subagents

Oswald the Analytical Octopus — a runtime-agnostic, MCP-native, context-rot-resistant workflow layer for analytical-engineering AI agents.

Production-ready MCP server for Dart AI task management with batch operations, SQL-like selectors, CSV import, and zero context rot

ADD (AI-Driven Development) 2.0. The agent is the hands; ADD is the memory, judgment, and conscience — a minimal, state-tracked skill: one freeze per feature, trust from passing tests, state on disk so context rot never survives a new session.

Context Rot Detection & Healing MCP Service — gives AI agents self-awareness about their cognitive state. Supports 15+ curated models and auto-resolves any HuggingFace model.

Find out where your coding agent starts degrading. Personal context-rot analytics from your own agent sessions. (npm wrapper around the Python CLI — always runs the latest PyPI release via uv.)

Static checking for broken internal links

Context rot indicator for Pi — shows token usage with research-backed degradation warnings

Context-rot smoke test — scores how hard each file is for an AI to edit correctly. Placeholder release; the real tool lands soon.

A lightweight registry of LLM model information, like name and context sizes, for building AI-powered apps.

MWA — Memory Working Agent. A turnkey TS agent runtime built on AWM as an always-on cognitive substrate, so a cheap model conducts, resumes, builds on prior reasoning, and runs long without re-onboarding or context rot.

Lightweight plan management plugin for Claude Code with context-aware handoffs to prevent context rot during multi-phase implementations

DeepSeek adapter for rot-balance AI engine