Cap'n Proto

Protocol Buffers (Protobuf) is Google's language-neutral, platform-neutral format and interface definition system for serializing structured data across programming languages. Developers define messages and service interfaces in `.proto` files; the `protoc` compiler generates language-specific code, which works with a Protobuf runtime for serialization and deserialization. The project is distributed as a C++ protocol compiler and language-specific runtimes, with prebuilt compiler binaries available for released versions.

Paritok is an open-source compression gateway for AI coding agents. It runs as a drop-in proxy between an agent and an upstream LLM API, stripping irrelevant tool schemas, compressing tool results and file reads, and summarizing stale conversation history before forwarding requests. Compressed content remains recoverable on demand through the gateway, while responses pass back to the agent unchanged. It supports agents such as Claude Code, Cursor, Codex, and OpenHands, as well as agents that support BASE_URL configuration, and is powered by an open-source code-focused 4B compression model.

Toolport is a free, open-source local MCP gateway that allows multiple AI agents to share a single server for accessing tools and managing credentials. It integrates with agents and clients such as Claude, Cursor, VS Code, and Codex, and the project claims it can reduce tool tokens and secrets stored in the OS keychain by up to 91%.

FlatBuffers is a cross-platform serialization library and interface definition system developed by Google. It uses schemas written in `.fbs` files and the `flatc` compiler to generate language-specific code, which constructs and accesses serialized buffers directly without first parsing or unpacking them. The shared buffer layout supports reading data across languages and schema versions, and is designed for memory-efficient transmission, storage, and access. The project provides code-generation and runtime support for languages including C, C++, C#, Dart, Go, Java, JavaScript, Kotlin, Lua, PHP, Python, Rust, Swift, TypeScript, and others. It runs on Windows, macOS, Linux, Android, and other systems with a recent C++ compiler, and is licensed under the Apache License 2.0.

codebase-memory-mcp is an MCP server from DeusData that indexes a codebase into a persistent local knowledge graph for AI coding agents. It parses source with tree-sitter AST grammars and uses Hybrid LSP semantic type resolution for selected languages to model functions, classes, call chains, HTTP routes, and cross-service links. Its MCP tools support code search, structural and Cypher-style queries, call tracing, architecture overviews, impact analysis, dead-code detection, and graph visualization. The project is distributed as native executables for macOS, Linux, and Windows, with no language runtime, hosted service, or API key required. Processing is local; the repository describes a RAM-first pipeline using compressed data, in-memory SQLite, and fused Aho-Corasick pattern matching, and reports sub-millisecond structural queries. A local visualization interface is available at localhost:9749.