distributed-agents

A distributed framework for LLM agents

Durable execution framework for AI agents in Go. Keeps agent state, tool calls, and execution loops resilient across process crashes.

Peer-to-peer communication for AI coding agents. 8 MCP tools, full CLI, Python client. Part of the Qualixar research initiative by Varun Pratap Bhardwaj.

A framework for building multi-agent AI systems. Enables LLMs to collaborate through hierarchical organization, parallel task execution, and extensible tools.

Composable primitives for goal-directed coordination in Go. Synchronization, resource allocation, and collective intelligence that adapt through multiple strategies. Built with capacity for systems with 1000+ independent agents.

Multi-agent systems framework for the BEAM platform - build distributed autonomous agents with OTP supervision and fault tolerance

Distributed Multi-Agent AI Orchestration with Ollama - Advanced collaborative workflow with AST quality voting, TrustCall validation, and adaptive strategy selection

A minimal protocol for task exchange between autonomous AI agents (TASK → RESULT | ERROR).

Experimental Hermes power-user Kanban labs: remote Docker workers, distributed execution, and sharded-model worker backends ahead of upstream stabilization.

Open-source TypeScript framework for persistent human-agent collaboration, with shared artifacts, human approvals and controlled execution on your infrastructure.

흩어진 컴퓨터와 브라우저를 하나의 AI 팀으로 — Agent Skills + MCP + 플러그인 (Claude Code · Codex · Gemini CLI · Cursor)

Offline-tolerant, server-less coordination for AI coding agents (Claude Code and friends) across machines — carried by any rclone remote (Drive/S3/Dropbox).

Decentralized multi-agent coordination for Codex CLI using isolated Git worktrees, shared intent-aware ledgers, cooperative conflict resolution, and serialized staging integration.

LangGraph agents that coordinate across machines with durable execution, retries, and human approval.

Coordinate distributed Codex workers to solve, review, and submit patches for approved open-source projects.

Run Claude Code across multiple PCs and Claude accounts: one lead Claude hands tasks to worker Claudes on your friends' computers, and every Claude sees what the crew is doing.

Distributed execution for agents — gateway/worker architecture for running agent fleets in isolated Docker runtimes. Part of the nano series.

Horizontally scaled coding agents + behaviour analytics (FastAPI, Redis workers, eval harness)

Self-hosted collaboration hub for long-running AI agents, shared sessions, and multi-agent dispatch.

LangGraph coordinates agents in one process. AXME coordinates them across machines - with durable state and automatic recovery.