Packages

Harness Floating Terminal: a persistent F7 shell for unwrapped AI CLIs

Validate a structured agent workflow, project its state, and scaffold one to start.

Registry of LLM agent tools: callable + schema + side-effects + defaults

Per-category p50/p90 token budget forecasting from agent history

A Rust implementation of the Microsoft Agent Framework: build AI agents and multi-agent workflows. Meta-crate re-exporting core and providers.

Agent2Agent (A2A) protocol client: talk to remote A2A agents as local agents

Anthropic (Claude) chat client for agent-framework-rs

Azure OpenAI chat client (Entra ID + api-key auth)

Azure AI Search context provider

AWS Bedrock (Converse API) chat client for agent-framework-rs

Microsoft Copilot Studio agent client

Core abstractions for agent-framework-rs: messages, chat clients, agents, tools, threads, middleware, memory, and workflows

Azure Cosmos DB NoSQL chat-message store

Declarative agents and workflows loaded from YAML/JSON specs

Azure AI Foundry (Responses API) chat client and Prompt Agents for agent-framework-rs

Microsoft Foundry Local chat client for agent-framework-rs

Google Gemini chat client for agent-framework-rs

GitHub Copilot chat client for agent-framework-rs

Host agents over HTTP: OpenAI-compatible, A2A, and DevUI-style APIs

Model Context Protocol (MCP) client: stdio and streamable HTTP transports

Mem0 context provider for long-term agent memory

Mistral chat client for agent-framework-rs

Ollama chat client for agent-framework-rs

OpenAI (and OpenAI-compatible) chat client for agent-framework-rs

Microsoft Purview compliance middleware

Redis-backed chat message store and context provider

Ahp public package coordinate scaffold

A git wrapper that tracks cloned repos and prevents duplicate clones

Public Preview — Rust SDK for the Agent Governance Toolkit (policy, trust, audit, identity)

Public Preview — MCP governance and security primitives for the Agent Governance Toolkit

Agent graph library

Base interfaces for agent-graph checkpoint savers

Conformance test suite for agent-graph checkpointer implementations

Postgres implementation of an agent-graph checkpoint saver

SQLite implementation of an agent-graph checkpoint saver

CLI for interacting with agent-graph

Procedural macros for agent-graph

Run 9 agents at once — MCP server for graph-orchestrated LLM workflows with parallel fan-out (up to 16 nodes), checkpoint/resume, HITL approvals, HMAC receipts

Linux control plane for AI agent security — trait surface and receipt types for BPF LSM, cgroup v2, Landlock, and seccomp sandboxing

Broker-owned Git push: resolve, authorize and execute the exact outbound transaction

agent-guard command-line interface (approval workflow)

Core types, policy engine and audit for agent-guard

Sandbox execution layer for agent-guard

High-level SDK for agent-guard policy enforcement

Bash and path validators for agent-guard

agent-harmonic-field

Drive LLM coding agents — Claude Code, OpenAI Codex, and local Ollama / OpenAI-compatible models — from Rust behind one trait, with a normalized streaming event vocabulary. Bring your own agent too.

Agent loop harness with local and sandbox tool runtimes, context management, and MCP support

Health status tracker for LLM agent components

Periodic heartbeat recorder and stall detector for AI agents