"How to improve memory or retention like GPT models" matching MCP servers:

Enables searching, comparing, and inspecting AI models by pricing, context window, and capabilities via the models.dev catalog.

Enables AI agents to query OpenRouter model information including prices, ELO rankings, context, and perform comparisons.

Captures user corrections and improvements during interactions, logs them, finds recurring patterns, and prescribes preventive fixes like CLAUDE.md rules, skills, scripts, or MCP tools to avoid repeating mistakes.

Classifies development task complexity (LIGHT/MEDIUM/HEAVY) and recommends the most cost-efficient AI model per provider, enabling optimized model selection for coding tasks.

MCP server that lists available GitHub Models and compares responses from multiple models for the same prompt.

An MCP server that wraps the @apitomy/data-models library for querying, validating, and editing OpenAPI and AsyncAPI documents.

Enables Codex chat to use the Claude Code harness for repository consultation and editing, routing through GPT models via a local proxy.

Enables Claude and other MCP-compatible tools to communicate with OpenAI's GPT models (GPT-5, GPT-5-mini, o3) with conversation history and session management. Features advanced controls like reasoning effort settings, token tracking, and parallel conversation sessions for efficient AI workflows.

An MCP server that helps interact with and compare different GitHub Models, enabling listing, filtering, and comparing model responses.

MCP sidecar for Hermes Agent exposing operator tools (cron, skills, config, workspace) with tiered read-only/operator/owner modes and dry-run by default for safe local development.

Enables AI clients to control local Windows development tools by exposing project files, code search, file editing, test execution, Git operations, and resource viewing through a secure MCP interface with permission controls.

Auto-captured, auto-recalled, path-scoped memory for AI coding agents and teams.

Enables ChatGPT Desktop to securely access and search local filesystem files through ngrok tunneling with whitelist-based directory protection and read-only operations.

Exposes an authenticated local runtime over OpenAI Tunnel so ChatGPT can inspect authorized Windows workspaces, read bounded Git status and diffs, submit and cancel Codex CLI tasks, and use workspace Skills. It also brokers connections to optional loopback stdio or HTTP MCP services, such as Stata and Zotero, with explicit tool allowlists and loopback-only access.

Converts AI Skills (following Claude Skills format) into MCP server resources, enabling LLM applications to discover, access, and utilize self-contained skill directories through the Model Context Protocol. Provides tools to list available skills, retrieve skill details and content, and read supporting files with security protections.

MCP server for managing project memory in AGENTS.md. Allows agents to record and remove durable facts using save/forget tools.

A different approach from typical persistent-memory MCPs. Instead of a local SQLite + embeddings store, the memory lives as plain files in a .ai-memory/ directory you commit to your repo (facts.jsonl, decisions/\*.md, gotchas.md). Git is the sync layer — what one Claude/Cursor/Cline learns about a repo, the next session (or a teammate's agent) picks up automatically. 5 MCP tools: get_rep

MCP server for AI agents to send notifications, copy to clipboard, request confirmations, and collect text input from users across their devices.

Routes one brief to the right image model across 60+ (gpt-image-1.5, Ideogram 3, Recraft V4, Flux), validates the output, and fans out to iOS/Android/PWA/favicon/visionOS/Flutter bundles. Works without an API key via Pollinations, HF Inference, Stable Horde, or host-LLM inline SVG.

Failure Memory provides AI coding agents with a shared local memory of failures, enabling them to record, recall, and learn from mistakes across sessions.