38 repos
Standardized interfaces and protocols for distributed agent interaction and cross-service tracing.
Explore 38 awesome GitHub repositories matching artificial intelligence & ml · Agent-to-Agent Communication. Refine with filters or upvote what's useful.
LangChain is an orchestration framework designed for building, managing, and deploying applications powered by large language models. It provides a unified integration layer that normalizes disparate model provider APIs into a consistent set of primitives, enabling developers to build complex, multi-step AI workflows that manage state, memory, and tool execution. The project distinguishes itself through a durable execution runtime that maintains persistent state across long-running processes by checkpointing progress to external storage. It models agent workflows as directed graphs, allowing
Provides standardized messaging interfaces to facilitate distributed interaction and cross-service observability between agents.
This project provides a modular framework for building and orchestrating autonomous AI agents. It functions as an agentic workflow engine that manages the full lifecycle of task execution, including model reasoning, tool invocation, and the integration of results. By utilizing a centralized orchestration platform, the system enables the creation of multi-agent teams that collaborate on complex objectives through structured communication and shared task graphs. The framework distinguishes itself through its focus on persistent, stateful operations and multi-agent coordination. It employs file-
Uses file-based inboxes to decouple agent memory, allowing teammates to operate independently while reporting results.
Agentscope is a comprehensive toolkit for developing and orchestrating autonomous multi-agent systems. It provides a unified framework for building agents that can reason, execute tools, and manage memory, enabling the creation of complex, collaborative workflows where multiple specialized agents interact to solve multi-step objectives. The platform distinguishes itself through a robust orchestration engine that supports both sequential and concurrent agent pipelines. It utilizes a centralized event bus for real-time telemetry, allowing developers to track agent reasoning, tool usage, and sys
Exchanges messages and tasks between different systems using standard communication protocols to ensure interoperability with external agents.
Deepagents is an LLM agent orchestration platform and stateful application server designed for deploying and managing AI agents built with computational graphs. It provides a containerized runtime environment that handles agent execution, state persistence, and the versioning of AI assistants. The platform distinguishes itself through deep integration with the Model Context Protocol, allowing agents to function as servers that expose tools and capabilities to external clients. It features a sophisticated observability suite for capturing execution traces, performing LLM-based evaluations agai
Facilitates direct interaction and data exchange between multiple agents via standardized protocols.
Nanoclaw is an LLM agent orchestrator and multi-platform chat gateway designed to deploy and manage isolated AI agents. It provides a containerized runtime that executes agents within sandboxed Linux containers, ensuring filesystem and state isolation through dedicated workspaces and host bind-mounts. The project distinguishes itself through a unified routing pipeline that connects agents to diverse messaging platforms, including WhatsApp, Discord, Slack, Telegram, Signal, and iMessage. It integrates the Model Context Protocol to extend agent capabilities via managed external data and functio
Enables communication between agents through a queued inbox and outbox pipeline for collaborative task delegation.
This project is a Python framework for building autonomous, event-driven agent systems. It provides a unified runtime for orchestrating multi-agent workflows, managing persistent conversation state, and executing code within secure, isolated sandbox environments. The framework is designed to handle complex task delegation, allowing agents to invoke other agents as tools while maintaining context across multi-turn interactions. The framework distinguishes itself through its deep integration with the Model Context Protocol, enabling agents to connect to external data sources and remote services
Provides standardized interfaces for transferring tasks between specialized agents during live sessions.
Mastra is an orchestration framework designed for building, deploying, and managing autonomous AI agents and multi-agent systems. It provides a comprehensive suite of primitives for creating resilient AI applications, including durable workflow orchestration, event-driven agent loops, and semantic memory management. By integrating these core components, the platform enables developers to build complex, multi-step processes that can reason about goals and execute tasks without manual intervention. The framework distinguishes itself through its focus on observability and secure, isolated execut
Passes task ownership between agents to allow specialized agents to continue interactions directly.
LangChain.js is a framework for building, executing, and monitoring stateful agentic applications. It provides an orchestration engine that models workflows as directed graphs, allowing developers to connect language models, data sources, and external tools into modular, multi-step processes. The platform distinguishes itself through its focus on stateful execution and human-in-the-loop control. It manages agent lifecycles by persisting execution state across threads, enabling fault tolerance and the ability to pause workflows at designated breakpoints for manual review or modification. This
Facilitates direct data exchange between independent agents using standardized communication protocols.
This project is a comprehensive framework for building and managing autonomous agent systems. It provides a unified architecture for orchestrating multi-agent societies, where specialized agents collaborate through roleplay to decompose and solve complex tasks. The system integrates language models with external environments, enabling agents to perform real-world actions through a standardized tool-calling abstraction layer. The framework distinguishes itself through its focus on iterative reasoning and data reliability. It employs automated feedback loops to refine agent outputs and self-eva
Provides standardized message structures to ensure consistent communication across diverse agent workflows.
Semgrep is a static analysis security testing tool designed to identify vulnerabilities and logic errors by matching source code against declarative patterns. It functions as an automated scanner that integrates into development workflows to detect insecure code patterns and enforce coding standards before deployment. The engine utilizes a language-agnostic intermediate representation and a modular parser architecture to normalize diverse programming languages into a unified format. This allows for consistent rule execution across different codebases, enabling users to perform custom structur
Exposes code analysis and security findings through standardized communication protocols to ensure consistent data exchange between systems.
Pipecat is a framework and software development kit for building real-time multimodal AI agents and speech-to-speech systems. It utilizes a frame-based data pipeline to route audio, video, and text through a modular sequence of processors, enabling the orchestration of low-latency conversational AI. The project is distinguished by its ability to coordinate complex multimodal services, including speech-to-text, language models, and text-to-speech, within a single pipeline. It features semantic voice activity detection for natural turn-taking, state-machine conversation flows for dialogue manag
Coordinates multiple specialized agents using a shared message bus and priority queues for inter-agent communication.
This project is an LLM coding agent orchestrator and AI software engineering platform designed to manage fleets of agents that autonomously solve issues, handle pull requests, and fix CI failures. It functions as an agentic CI/CD automator and parallel workflow manager, coordinating the end-to-end development lifecycle from initial ticket tracking to final code merging. The system is distinguished by its modular plugin framework and isolated worktree management, which allow multiple agents to work on separate coding tasks simultaneously without file system conflicts. It utilizes role-based mo
Implements a messaging system to send files and text to agents while ensuring they are idle before delivery.
Gastown is an LLM agent orchestration platform designed to coordinate multiple AI agents with persistent state and context recovery across coding tasks. It provides a coordination layer that manages agent lifecycles, monitors health through a real-time dashboard, and ensures continuity during task executions. The system distinguishes itself through a federated agent network that links separate orchestration instances to distribute work and track agent reputation. It employs a git-backed work state manager that uses version control worktrees to store progress as structured data and a bisecting
Implements a shared communication layer for linking separate orchestration instances to distribute work and track agent reputation.
PraisonAI is an autonomous AI agent platform that coordinates multiple LLM-powered agents for research, planning, and execution of complex workflows. It functions as a multi-agent orchestration framework, a workflow builder, and a Model Context Protocol server, while also providing retrieval-augmented generation through vector knowledge bases. Agents can interact via CLI, web, or standardized protocols with sandboxed code execution. The platform distinguishes itself with a rich set of agent communication protocols, including A2A, REST, WebSocket, voice and telephony integration, and MCP, allo
Implements a dedicated protocol for direct message exchange between agents for coordinated task execution.
AOS Community Edition is a runtime platform for AI agents such as Claude, Codex and Grok. It connects them to local tools and services through plugins and a standard tool-protocol interface. A broker and per-agent host bridges make sure each agent sees only the local tools it is permitted to use. Each capability runs as a capsule, an isolated WebAssembly module that holds only the permissions it was explicitly granted. Capsules talk to each other through typed contracts over a shared event bus, so larger tools, connectors, services and agent harnesses are built by combining smaller pieces. An
Links existing agents to locally hosted tools and services through host plugins and a standard tool-protocol interface.
Uses the transport-agnostic agent launcher directly to serve agents via gRPC, WebSocket, or other protocols.
Reef is a platform that lets AI agents keep improving from real usage. It serves live agent traffic through OpenAI- and Anthropic-style endpoints, records each interaction, and turns the resulting user feedback into better versions of the agent. Those versions are tested, versioned, and shipped again and again, without manual retraining cycles. Reef can improve an agent in two ways. It can evolve the agent's harness, meaning its prompts, rules, and skills, stored as a plain text-file tree. Candidate edits are tested on real tasks and the best-scoring ones are published as snapshots that clien
Handles incoming agent requests and records each interaction so later feedback can be matched to what the agent did.
This project is a local bridge that lets a ChatGPT web subscription handle planning and review for coding tasks while the Codex agent only executes them. The aim is to keep heavy reasoning on the chat subscription rather than paid API quota, without needing API keys or reverse proxies. A local server exposes a read-only view of the workspace to the chat app over the Model Context Protocol, and tasks move through plan, execute, review, and done stages by exchanging small structured messages instead of pasting full diffs or logs. Access is tightly scoped. Each token is bound to a single workspa
Moves a task through plan, execute, review, and done stages by exchanging small structured messages between planner and executor sessions.
n2n is a peer-to-peer VPN that creates an encrypted mesh network by establishing layer 2 overlay networks. It uses UDP tunneling to connect remote computers into a shared virtual local area network, allowing devices to communicate as if they were on the same physical Ethernet switch. The system utilizes a centralized signaling registry and federated coordination nodes to facilitate peer discovery and node registration. It implements NAT traversal through UDP hole punching and UPnP port mapping, while using supernode relay routing to ensure connectivity when symmetric NATs prevent direct peer-
Distributes workload across multiple coordinating nodes to provide fail-over and increased network resilience.
Swarms is a multi-agent orchestration framework and autonomous agent toolkit designed to coordinate large language model agents. It serves as a workflow engine for managing agent relationships, providing the infrastructure to build autonomous agents with integrated memory, tool-calling capabilities, and reasoning loops. The framework is distinguished by its multi-agent consensus systems, which utilize voting, adversarial debates, and judge agents to synthesize high-quality responses. It supports a variety of collaboration patterns, including director-worker hierarchies, expert synthesis, and
Utilizes a council of agents to provide reasoning and a separate judge agent to deliver a final verdict.