multi-agent — independent software & tools
-
Agent-Worlds
-
parley
Provable consensus for AI agents of rival owners: deterministic red lines, max-min consensus over masked verdicts, and a verifiable non-betrayal transcript. Multilateral, non-crypto, self-hosted.
-
hypertaks-agent
Hypertaks = "A founder who owns a library of more than 1,400 books, knows exactly which book to consult for this issue, and has a strict SOP: intake → formulation → implementation → integration → documentation."
-
AlfredOS
An open-source, self-hostable, multi-user, multi-persona, security-hardened agentic OS.
-
repomon
Run a fleet of AI coding agents (Claude Code, Codex, Aider) across many repos — Rust TUI, tmux-backed.
-
AladdinAI
AladdinAI: open-source BYOI (Bring Your Own Infrastructure) AI Agent platform. Connect your own VMs, NVIDIA NIM, OpenAI, Anthropic, Ollama — build and manage AI agents visually.
-
ai-badger
Source-of-truth marketplace + project scaffolder for custom Claude/agent skills, personas, and instructions. Organized as {stack|common}/{feature}; welcome-ai-badger scaffolds a repo, feed-badger contributes back.
-
partyline
One wire, every agent — a shared telephone line for Claude Code agents. (It's a JSONL file.)
-
b3rys-team-os
내 맥에 상주하는 AI 팀. 텔레그램·슬랙에서 일을 맡기면 누가 담당인지 정하고, 진행이 대시보드에 남습니다.
-
akashic-aurora
Memory for AI agents that learns what actually helped: lessons injected at the moment of action, credited by outcome, challenged by counter-evidence. Local-first, multi-agent, test-gated.
-
ai-jury
Stdlib-only Python CLI that runs native coding-agent CLIs (Claude Code, Codex, Antigravity) + a free local model as one review jury — review a diff/PR/issue, debate, verify, synthesize one verdict (chair or panel vote). Local-first, secure by default.
-
daedalus
Daedalus is a standalone terminal-based AI coding assistant that runs on your machine. It connects to local LLM servers (LM Studio, Ollama, llama.cpp, vLLM) or remote providers (OpenAI, Groq, OpenRouter, Anthropic), routes requests intelligently, and gives your AI agent access to your file system, terminal, git, web search, and codebase indexing
-
lilith-cli
Lilith — Norse-themed terminal IDE and AI agent interface (Textual TUI, agent orchestration, vector memory)
-
graftty
Worktree-centric libghostty-based terminal for macOS & iOS
-
omadia
Self-hostable agentic OS. Build, run & audit multi-agent AI teams from signed plugins. Bring your own LLM key, own all your data, EU/GDPR-ready.
-
alloy
Multi-provider coding agent harness built on Pi.
-
proofpress
Proofpress is the artifact provenance and handoff layer for multiplayer AI. It makes what was accepted, rejected, changed, and why travel with the artifact itself—so handoffs preserve context and trust.
-
forge-harness
Forge your Claude Code projects — pass them through, they come out faster.
-
Hermes-House
🤖 Self-Evolving Multi-Agent AI System | 116+ Skills | TrendRadar · Reviewer | Learn, Build & Evolve
-
claude-grep
Search your Claude Code conversation history by content (not just titles), then resume any session. grep + fzf, no index.
-
cyborg
Open-source collaborative AI agent platform. Humans and AI agents on different machines work together in shared workspaces — agents run locally on your own daemon, self-hosted, no cloud execution of your code.
-
klypix-mcp
Shared project brain and coordination layer for multi-agent coding — versioned decisions, evidence, active work, handoffs, and overlap awareness.
-
loom
Orchestrate a fleet of real Claude Code agents on your Claude subscription, not per-token API bills - local-first.
-
Arctus.ai
An autonomous ultra-massive context agent orchestration framework designed to coordinate hundreds of LLMs across a 10-million token context window. This framework scales multi-agent workflows to an unprecedented enterprise tier. Local first support by all llm openrouter Omniroute olama.
-
work-harness
A multi-agent delivery harness for Claude Code: decompose a backlog into PR-sized units, dispatch one autonomous lead per unit across local/SSH/cloud hosts, and drive every PR to merged through a persistent shepherd.
-
owledge
Markdown-first persistent memory and project planning for AI agents, existing knowledgebases, and multi-agent workflows.
-
AIsland
A local-first multi-agent status island for Windows
-
star-owner
星⭐收藏家：Bilibili 收藏视频 Markdown 多 Agent 本地编排工作台
-
openclaw-n8n-stack
Deploy an OpenClaw and n8n Docker stack for AI agents, MCP, and workflow automation in one setup
-
llm-task-tree
Local-first visual task graph that keeps humans and AI agents aligned on goals, progress, reasoning, and the next action.
-
Wakeflow
Dual-host Wakeflow plugins for Codex and Claude Code: controller state roots, task packages, direct-thread/session delivery, evidence review, and local-first runtime.
-
Cheers
A Slack-style hub for humans and AI agents — real-time channels, external agent bots, file-aware chat, and channel memory. Open-source & self-hostable & MacOS & IOS.
-
hara
A coding agent CLI that runs like an engineering org — role routing, plan DAGs, approvals, memory, and a 10-platform chat gateway. Apache-2.0.
-
codexconclave
Build and orchestrate autonomous AI agent teams with a Python framework for structured workflows, observability, and control
-
a2acast
Zero-infrastructure A2A messaging between AI agents on different machines — Claude, ChatGPT/Codex, Copilot, any harness; ntfy relay transport, no ports, no server
-
potion
🧪 The magic potion for Claude Code — a lean project framework: plans are prompts, disk is memory, evidence or it didn't happen. Brewed itself to v1.0.0.
-
cys-terminal
AI agent fleet orchestration terminal — bidirectional socket IPC, resource governance, mission-control dashboard. macOS · Windows. Built largely by AI agents under human direction.
-
subfloor
Forkable shell substrate for a single code repository — DB-backed identity, memory, roadmap, content; harness-agnostic boot. We build the data layer, we rent the harness.
-
Teamwork
Evidence-first skills for Codex, Cursor, and Claude Code: research, debugging, planning, execution, review, and goal loops.
-
cmux-tips
Field-tested tips for running multiple Claude Code sessions in cmux (native macOS terminal) — workspace groups, tmux mirroring, hooks, session addressing. By CMDSPACE.
-
hermes-agent-desktop
Automate tasks on your local machine using an AI agent client for Claude, Grok, and Gemini models on Windows, macOS, and Linux.
-
share-sharvis
Orchestrate multiple Claude Code sessions from a single control panel across different machines.
-
cc-harness-skills
Package portable CC coding-agent skills for Claude Code, Codex, and OpenClaw with reusable prompts, helper scripts, and installable SKILL.md bundles
-
wait-agent
Agent mux terminal.
-
lmctl
A provider-agnostic control plane for teams of AI coding agents — across providers, with independent review and durable memory. Homepage + docs source for lmctl.com.
-
H
-
StrategyForge
Coral — a native macOS app to design and run multi-agent AI teams on your own AI subscriptions (Claude Code, Codex, Gemini), locally. No API keys, no backend.
-
evolab
A² · Agentic AI × Anything：多 agent 编排方法论与治理 skill 合集（旗舰 cto-orchestration）
-
qodex
Desktop-first multi-model AI agent platform with Context Engine, Skill Runtime, MCP Runtime and Multi-Agent orchestration.
-
chorus
A local-first desktop workspace where you and several coding agents share one conversation. Drives your own claude and codex CLIs; every command and edit goes through visible approval.
-
agent-fleet
Run many Claude Code sessions in parallel against one shared task queue — concurrency derived from the work and from what your machine can actually spare. 100 tasks never means 100 browser tabs.
-
llminbox
A per-agent inbox over the markdown coordination logs your AI agent fleet already writes
-
cantos-plugin
The full Cantos system as a one-command Claude Code plugin: a self-improving, multi-agent assistant orchestrator that routes each request to a specialist assistant.
-
AI-Arena-Adversarial-LLM-Lab
Local adversarial LLM multi-agent lab where various models battle against each-other.
-
myAIspecials
ais
-
ai-coder-symphony
Multi-Agent AI Coding Assistant 2026 - Open Source DeepSeek/GM5
-
openamer
The self-improving, self-learning open-source AI agent. Background Computer-Use, A2A Swarm, Vector Memory, Plugin System, Voice, Smart Approvals, Autonomous Web Agent - 100/100 Score. 99+ tools, 124+ skills. Windows-native.
-
limen
MCP-accessible multi-agent task orchestration: cross-repo task intake, universal dispatch schema, self-healing fleet-scale coordination over the Model Context Protocol.
-
pi-ralph-beret-brigade
Hat-Based Multi-Agent Orchestration Loops for Pi Coding Agent 2026 – AI Workflow Revolution
-
corralai
One directive → a herd of AI agents that plan, build, verify, and re-plan across any model (local 7B to frontier) — human-gated, jail→repo, with shared memory + skills. Every mission recorded and replayable.