Agent frameworks

Nine official open-source SDKs for integrating applications with Melaya's APIs, covering authentication, agents, pipelines, device control, evaluations, and other public platform surfaces.

Microsoft's framework for building AI agents and workflows, combining capabilities from AutoGen and Semantic Kernel.

MySpec ships Claude Code plugins that connect an MCP server to spec-driven development and a manager plugin that plans task waves, dispatches worker sessions, verifies their pull requests, and gates merges.

A runtime library and config generator for OpenCode agent workspaces, with provider abstraction, A2A task delegation, persistent memory, and MCP servers.

Nexus-Agent is an autonomous software-engineering agent with a self-healing execution loop, AST pre-validation, persistent rollback, and terminal and web interfaces.

A Rust CLI-first AI agent runtime that uses model providers and MCP tools to work with files, code, and shell, with interactive, piped, daemon, WebSocket, and ACP modes.

An agent-to-agent marketplace protocol for capability discovery, reverse auctions, task verification, and USDC escrow payments.

Okto-Nexus is a local-first MCP coordination hub for multi-agent teams, with durable messaging, atomic handoffs, governance controls, and human approval.

Okto-Pulse is a local-first SDLC workbench for AI coding teams, with structured project artifacts, governance gates, validation rules, and MCP tools.

OpenAgents is an open-source workspace where AI agents connect and collaborate, with an agent launcher, shared workspace, and support for agent protocols and SDKs.

OpenAI's framework for building agent workflows with tools, handoffs, guardrails, sessions, and tracing.

A self-hosted coding agent that takes labeled GitHub issues through planning and implementation, opens pull requests, checks changes against acceptance criteria, and merges when configured gates pass.

A CLI runtime for running and coordinating teams of AI agents on parallel tasks with shared state and review workflows.

Praison AI is a low-code, centralized framework leveraging AutoGen and CrewAI to simplify creating and orchestrating multi-agent systems for LLM applications, emphasizing customization and ease of human-agent interaction

A Python framework for building and running AI agents with integrated tools, controllable reasoning, memory, security, governance, and observability.

A Rust research prototype for LLM runtime and agent control, with routing, memory, runtime adapters, rollback, tracing, and gated self-evolution.

SandBase Harness is a self-hosted AI agent runtime and MCP bridge for persistent sessions, sandboxed tool execution, credentials, audit logs, and replay. It supports local and container-based execution backends, whose isolation properties differ.

Sayna is a self-hosted real-time voice server that provides speech-to-text and text-to-speech through WebSocket and REST APIs, with provider integrations, LiveKit streaming, and SIP telephony.