"Persistent" matching MCP servers:

Creates and maintains a semantic knowledge graph of code that allows maintaining context across sessions with Claude, providing advanced search capabilities without requiring the entire codebase in the context window.

Enables interaction with the ACL2 theorem prover through 15 tools for theorem proving, expression evaluation, persistent session management, and proof debugging.

Enables proof-backed code audit via MCP tools for AST-based code maps, symbol lookup, callers, audit commands, and persistent verdict memory.

Provides AI coding agents with token-budgeted, context-aware code retrieval from a persistent code graph, enabling efficient question answering without loading the entire repository.

Provides AI coding assistants with code search, impact analysis, task chaining, and persistent memory to turn AI demos into deliverable code.

Provides persistent memory for coding agents and grounds their claims by verifying against the actual codebase, preventing hallucinated responses.

Analyzes codebases to produce a persistent code knowledge graph and an MCP server with 9 tools for AI coding agents.

An MCP server that provides CLI coding agents with persistent decision memory, codebase dependency-graph awareness, plan validation against architectural constraints, and a self-bootstrapping constraints.md file.

Bridges the Model Context Protocol with Language Server Protocol to provide AI agents with persistent access to code intelligence features including navigation, diagnostics, refactoring, and completion across 7+ programming languages.

Multi-language code intelligence MCP server providing structured code analysis including symbol search, references, hierarchies, and change impact. Supports 25 languages with persistent indexing and LSP integration.

Persistent memory for AI coding agents that knows when it has gone stale.

A self-hosted persistent memory platform for AI agents and humans offering tools for memory storage, search, beliefs, work management, and code intelligence via MCP.

A stateful Model Context Protocol server for interactive Agda proof development, enabling persistent sessions with goal-aware proof actions.

Self-hosted AI Agent Memory + Code Intelligence Platform providing persistent memory, AST-aware code search, and quality enforcement via a single MCP endpoint.

Provides AI coding agents with persistent architectural memory of codebases, enabling impact analysis, test generation, and code generation with reduced token usage.

Provides coding agents with persistent repository context, including code maps, specs, timeline, team memory, and past session history, through MCP tools.

Validates Mermaid diagram syntax using a persistent browser for fast, reliable checks.

MCP server that uses Recursive Language Models to analyze codebases hierarchically, creating a persistent, queryable knowledge map to overcome context window limits and prevent context rot in RooCode.

Provides persistent codebase memory and semantic context for AI agents via AST-aware chunking and symbol graph indexing.

coldstart gives coding agents durable memory of a specific codebase, with no embeddings, no vector store, and no API key. Agents write notes after real tasks — what a file is for, how a flow spans files, which invariants hold — and those notes are surfaced automatically to a later session whose task matches, so nothing gets rediscovered from scratch. Every note is anchored to real files by content