Releases

Transport layer (stdio, SSE, WebSocket) for FastMCP

MCP client implementation for FastMCP

MCP protocol types and JSON-RPC implementation

Rich console output for FastMCP servers

Procedural macros for FastMCP (#[tool], #[resource], #[prompt])

Core types and context for FastMCP

AMQP protocol support for MockForge

Shared logic for MockForge - routing, validation, latency, proxy

A Rust-based terminal coding agent with modular architecture supporting multiple LLM providers

ACP bridge and client implementation for VT Code

Core library for VT Code - a Rust-based terminal coding agent

Model Context Protocol (MCP) client, connection pooling, and tool discovery for VT Code

LLM provider abstraction, client implementations, and streaming for VT Code

Unified UI crate for VT Code: design system, theme registry, and TUI framework

Agent Plugins loader for VT Code: portable plugin manifests, skill discovery, and MCP configuration.

Skill types, discovery, loading, and validation for VT Code

Authenticated WebMCP bridge and workspace adapter for VT Code

Command safety detection, execution policies, and sandboxing for VT Code

Config loader components shared across VT Code and downstream adopters

Algorithmic audio generator for Bevy.

Rust bindings for Barretenberg, a C++ cryptographic library for zero-knowledge proofs

API bindings for the Nominal platform

CLI for the Harn programming language — run, test, REPL, format, and lint

A LangChain-inspired framework for building LLM applications in Rust. Supports OpenAI, Agents, Tools, Memory, Chains, RAG, BM25, Hybrid Retrieval, LangGraph, HyDE, Reranking, MultiQuery, and native Function Calling.

Reusable discovery, scheduling, execution, and receipt contracts for Harn tests

Shared outbound workflow server core for Harn adapters

Host capability exposing the harn-rules declarative rule engine to Harn (`rules.search` / `rules.report` / `rules.apply`).

c ffi bindings for tailscale-rs

Language Server Protocol implementation for Harn

Linter for the Harn programming language