OpenWork brings connected write tools to workflows and artifacts
Live artifacts, scheduled automations and on-demand workflows gain connected actions; desktop work reports back to Slack, with explicit self-hosting caveats.
Open Orchestrators
Open multi-agent orchestration platforms directory and news.
Track the projects shaping multi-agent orchestration, then compare the builders, workspaces, company OSes, coordination protocols, and visual systems in one place. Closed products that matter to the community are separated from the open directory.
Latest news
News
Paperclip adds PR review bots and queued approvals, with full-auto execution defaults
Scheduled GitHub reviews and queued responses expand agent workflows, while new execution defaults and the Composio retirement require an upgrade review.
Agno 3.1 adds AgentOS RBAC, followed by observable knowledge sync
AgentOS gains authorization and user-partitioned files; 3.1.1 adds sync progress and cancellation, with a manual filesystem migration for existing users.
Directory
Multi-agent orchestration platforms.
Open-source or publicly documented systems where orchestration is central to the product, sorted by GitHub stars when available.
Open-source personal AI assistant software built around chat interfaces, persistent context, skills, and execution.
Directory note
Represents the assistant-shaped end of the orchestration space.
An MIT-licensed autonomous agent from Nous Research with persistent memory, self-created skills, scheduled automations, subagents, and messaging gateways.
Directory note
Centers orchestration on a persistent personal agent that learns across sessions, delegates parallel work, runs scheduled tasks, and reaches operators through CLI and chat platforms.
An agentic workflow builder combining workflows, chatflows, apps, and knowledge systems in one product surface.
Directory note
Combines orchestration features with app-building and knowledge tools.
Open-source orchestration for zero-human companies, framed around AI employees, goals, and jobs across business functions.
Directory note
Frames orchestration at the company and business-function level instead of only task flow.
A worktree-based IDE for AI coding agents that runs Claude Code, Codex, OpenCode, and other agents side by side across isolated git branches.
Directory note
Centers orchestration on parallel coding agents, worktree isolation, and in-app review flow inside a desktop IDE.
Rf
An MIT-licensed coding-agent meta-harness, formerly Claude Flow, for coordinated Claude Code and Codex swarms, with team topologies, per-agent Git worktrees, and swarm lifecycle tools.
Directory note
Lite plugins and full CLI initialization differ materially. Full init writes workspace configuration and hooks and registers MCP; the swarm plugin requires ruflo-core with CLI v3.6 major/minor compatibility, and its live pane uses early-access Claude function hooks. Capability and performance claims are not independently runtime-tested here.
Organizes work as crews of specialized agents with a role-based model for delegation, collaboration, and task structure.
Directory note
Makes the team metaphor central to the orchestration model.
An open-source system for building AI agents visually, with emphasis on agent flows and orchestration through a builder interface.
Directory note
Presents orchestration through a visual builder rather than a code-first framework.
An open-source managed agents platform where coding agents act like teammates, take assigned issues, execute autonomously, and reuse shared skills over time.
Directory note
Centers orchestration on issue boards, runtime daemons, and reusable skills for human-plus-agent teams.
LG
An MIT-licensed low-level orchestration framework for long-running, stateful agents, with durable execution, memory, and human-in-the-loop controls; developers can compose custom multi-agent workflows as graphs.
Directory note
Not an out-of-box coding-team runner: developers implement multi-agent composition, and the core also supports single-agent workflows. Optional LangSmith observability and deployment services are separate from the MIT-licensed LangGraph core.
An open-source runtime for building, running, governing, and monitoring agents, teams, workflows, and AgentOS services in production.
Directory note
Centers orchestration on production agent runtimes, teams, workflows, memory, guardrails, and AgentOS operations.
OH
A GPL-3.0 personal AI agent harness with a desktop-first UI, local memory tree, Obsidian-style wiki, integrations, model routing, voice, and optional local AI.
Directory note
Centers orchestration on a personal agent that can connect to everyday tools, auto-fetch context, compress it into local memory, expose typed tools, and operate through a simple desktop experience rather than a config-first terminal workflow.
A workflow layer for OpenAI Codex CLI that adds stronger default sessions, reusable skills, native hooks, HUD/status surfaces, project guidance, and team-style execution commands.
Directory note
Centers orchestration on making Codex a repeatable agent runtime: `$deep-interview` for clarification, `$ralplan` for planning, `$team` for coordinated parallel execution, and `$ralph` for persistent completion loops.
An MIT-licensed personal AI assistant that runs Claude agents in isolated containers, connects to chat channels, keeps memory, schedules work, and uses skills as git branches.
Directory note
Centers orchestration on a small, understandable OpenClaw alternative with OS-level container isolation and multi-channel personal-agent operation.
An open-source AI agent platform for building agents with integrations, workflows, knowledge bases, tables, and docs.
Directory note
Leans toward a workspace-style product rather than a narrow framework.
An open-source TypeScript framework for building agents, graph-based workflows, MCP servers, evals, observability, and production AI applications.
Directory note
Centers orchestration on TypeScript agents, explicit workflows, human-in-the-loop suspension, MCP, evals, and observability.
An open-source Kanban workspace for planning, running, reviewing, and shipping parallel coding-agent work.
Directory note
Centers orchestration on issue planning, coding-agent workspaces, branches, terminals, dev servers, diff review, browser preview, inline feedback, PR creation, and merge flow.
A local-first agent workspace and host layer for teams, with desktop and CLI runtimes, shareable setups, browser control, scheduled tasks, and remote operation.
Directory note
Centers orchestration on shareable agent setups: local or remote hosts, permissions, browser automation, scheduled prompts, and opencode-powered execution.
GT
A multi-agent workspace manager for Claude Code, GitHub Copilot, Codex, Gemini, and other coding agents with persistent work tracking.
Directory note
Centers orchestration on git-backed work state, handoffs, and workspace-level coordination for coding agents.
A local code editor and control plane for running many CLI coding agents in parallel across isolated git worktrees.
Directory note
Centers orchestration on parallel coding-agent execution, worktree isolation, monitoring, review, and editor handoff.
An MIT-licensed Python and .NET developer framework for graph-based multi-agent workflows, including sequential, concurrent, handoff, and group-collaboration patterns with streaming, checkpointing, and human-in-the-loop steps.
Directory note
A framework for building applications, not a ready-made parallel coding-agent workspace. Developers must implement the application, configure provider credentials, test behavior, and supply responsible-AI mitigations; third-party services and their costs remain the user's responsibility.
A TypeScript library and CLI for orchestrating AI coding agents in isolated sandbox environments with branch strategies, hooks, logs, templates, and merge-back workflows.
Directory note
Centers orchestration on programmatic sandboxed coding-agent runs: invoke an agent with `sandcastle.run()`, run it in Docker, Podman, Vercel, Daytona, or a custom provider, and bring the resulting commits back through a branch strategy.
OR
An Apache-2.0 local coordination system where YAML RigSpecs define coding-agent teams, their communication edges, and continuity, with a daemon, CLI, TUI, and MCP server managing native agents in tmux.
Directory note
Requires Node.js 22 or 24 and tmux on macOS/Linux; native Windows is unsupported and WSL2 untested. Setup and startup can write provider hooks and trust/workspace settings; back up configuration because dry-run does not preview every later effect.
Rv
An Apache-2.0 host agent that plans complex tasks as DAGs and orchestrates built-in research, coding, design, and on-call agents plus third-party agents such as Claude Code, Codex, OpenClaw, and Hermes Agent over ACP, CLI, or OpenAI-compatible APIs.
Directory note
Centers orchestration on one host agent that generates a DAG for a complex task, coordinates specialized agents, manages task dependencies and parallel execution, and turns multi-step collaboration into reusable workflows.
Sq
An open-source GitHub Copilot-based agent team system where specialists live in the repo, keep memory, route work, and run in parallel.
Directory note
Alpha software; centers orchestration on repo-native team files, coordinator routing, persistent memory, parallel execution, watch mode, and CLI/SDK workflows.
An AI-first knowledge base where files live on disk and a team of AI agents help with execution.
Directory note
Combines files, knowledge, and agent execution in one operating surface.
A free desktop app for coordinating autonomous AI agent teams across major coding agents and model providers from a Kanban and review workflow.
Directory note
Centers orchestration on high-level commands, autonomous task execution, agent-to-agent messaging, Kanban task management, cross-team communication, and built-in review surfaces.
An MIT-licensed, local-first multi-agent desktop application where a Commander coordinates specialist agents across research, coding, data, documents, and media.
Directory note
Centers orchestration on one desktop conversation, shared plans, parallel or sequential dispatch, visibility-scoped context, local storage, and per-agent memory and skill evolution.
Sc
An Apache-2.0 orchestration platform for teams of Claude Code, Gemini CLI, Codex, and OpenCode agents running as independent processes with delegation, messaging, and parallel execution.
Directory note
Pre-1.0 infrastructure and a collaboration testbed, not an officially supported Google product. APIs and configuration evolve; team behavior depends on the instructions and templates you supply.
AO
An Apache-2.0 local-first agent operation environment that builds portable agent and team packages and runs them across supported coding hosts.
Directory note
Centers orchestration on portable package contracts, explicit roles, host-owned runtime selection, governed memory and policy boundaries, MCP/A2A interoperability, and verification receipts.
An Apache-2.0 local-first IDE and workbench for orchestrating Claude Code, Codex, and other coding agents across worktrees.
Directory note
Centers orchestration on planning, running, reviewing, testing, merging, and shipping multi-agent software work locally instead of handing the source tree to a hosted vendor.
An open-source, multi-node agent orchestrator where a planning agent turns a plain-language task into a PROMPT.md plan, then runs plan, review, execute, and review gates for each task in an isolated git worktree, controllable from desktop, web, mobile, or the fn CLI.
Directory note
Centers orchestration on a kanban board with per-task worktrees, workflow approval gates, hierarchical missions, and any local or cloud model across a synced multi-node mesh.
RQ
An Apache-2.0 real-time human-in-the-loop task manager where AI agents and operators share tasks, replies, approvals, and workspace state through MCP.
Directory note
Centers orchestration on the live agent-human control loop: agents create or claim tasks, request decisions, receive operator replies, and keep multiple agent workspaces moving without losing context.
An open-source desktop workspace for dispatching, monitoring, reviewing, and merging parallel coding-agent work across isolated git worktrees.
Directory note
Centers orchestration on local parallel coding-agent sessions, automatic branch and worktree isolation, real embedded terminals, diff review, and merge flow.
An MIT-licensed lead/worker orchestration framework where a lead agent receives tasks from Slack, GitHub, GitLab, Linear, Jira, email, WhatsApp, or the API and delegates to worker agents running in isolated Docker environments with persistent memory and identity.
Directory note
Centers orchestration on a lead/worker swarm with persistent SOUL/IDENTITY identity, vector-searchable compounding memory, DAG workflows with human-in-the-loop gates, scheduled tasks, MCP servers, skills, and harness-agnostic execution across Claude Code, OpenAI Codex, pi-mono, Devin, Claude Managed Agents, and opencode.
An MIT-licensed local mission-control center for launching, monitoring, and coordinating multiple AI agents in parallel.
Directory note
Centers orchestration on a visual canvas dashboard, parallel agent sessions, unified human-in-the-loop approvals, reusable prompt/templates, tools, skills, views, git worktree isolation, diff review, and local control.
FR
An Apache-2.0 CLI and terminal UI for hierarchical loops of coding agents, with recursive delegation across separate git worktrees.
Directory note
Centers orchestration on recursive agent trees, per-node worktrees, multiple coding-agent backends, and hard caps on iterations, depth, children, cost, and time.
A self-hosted multi-agent AI runtime and control plane for autonomous agents, delegated work, schedules, provider management, MCP support, and chat-platform connectors.
Directory note
Centers orchestration on a self-hosted runtime where agents can delegate work, manage providers, use connectors, run scheduled tasks, and operate OpenClaw and Hermes Agent swarms.
PR
An open-source local and cloud agent IDE for running coding agents across isolated workspaces, shared sessions, and subagents.
Directory note
Centers orchestration on parallel workspaces, multi-agent collaboration, plugins, MCP bindings, and review flow across local and cloud environments.
Cx
A local-first control plane that runs existing coding agents through one interface, with parallel best-of-N candidates, cross-model review, and inspectable results.
Directory note
Coordinates Claude Code, Codex, Cursor, OpenCode, Antigravity, and API-backed runs while keeping account profiles, quota facts, and run artifacts explicit.
A self-hosted issue-to-release runner: label a GitHub Issue ai-ready, and one agent session implements it on a branch while a separate review session checks the pull request against the Issue's acceptance criteria before the reviewed head is merged and tagged.
Directory note
Centers orchestration on GitHub Issues as the work queue: implementer and reviewer run as separate sessions, and only the commit the reviewer approved is merged and released.
Or
An Apache-2.0 terminal CLI and TUI that turns one goal into an ordered, editable plan of coding-agent tasks, each pinned to its own runner, model, mode, and effort, where a task counts as done only when its own completion marker appears in that runner's output.
Directory note
Centers orchestration on a dependency graph of named tasks: independent nodes run concurrently on whichever harness the operator assigns, the plan stays editable while tasks are in flight, and every completion verdict is read from the runner's own output rather than from a summary written by an agent.
Tm
An Apache-2.0 Tauri-based ADE (Agentic Development Environment) that runs CLI coding agents with 64% fewer tokens via an embedded xterm.js terminal.
Directory note
Centers orchestration on token intelligence, isolated DB branches per session, and multi-agent session management inside a native desktop environment.
LT
A local GUI orchestrator for repository-scale coding tickets that separates multi-model planning, atomic task execution in isolated OpenCode worktrees, and human review gates.
Directory note
Centers orchestration on phased ticket lifecycles: multi-LLM councils deliberate on specifications, tasks decompose into atomic units, and agents execute in isolated worktrees with fresh-context recovery loops.
cc
An MIT-licensed Rust coding-agent workflow engine built around Sangha: Claude Code and Codex run plan, quorum assessment, implementation, review, and fix stages, with parallel workers and recorded run events.
Directory note
Acceptance counts successful approval markers rather than resolving dissent or proving checks; execute required checks separately. Codex readonly review requests currently use workspace-write, Copilot code generation is unsupported, replay re-executes, and undo only reports commits.
An Apache-2.0 office suite where AI agents collaborate with humans on docs, databases, slides, and flowcharts through MCP and comments.
Directory note
Centers orchestration on shared office artifacts: agents can be mentioned, receive contextual tasks, edit content, leave traceable changes, and work through MCP without replacing the user's existing agent.
Gc
A native macOS workspace that arranges coding-agent sessions into a graph, where every node is a live terminal and edges fire hand-offs, messages, and spawns without a person present.
Directory note
Centers orchestration on the graph itself rather than a board or a queue: a goal-based loop ends when its shell predicate exits 0, and that exit is what fires the outgoing edges to the next sessions.
A coordination-oriented system with a protocol, rooms, agent lifecycle docs, a CLI, and multiple agent clients.
Directory note
Structured around agent coordination, communication, and lifecycle management.
NN
An open-source AI agent team workspace by NetMind.AI whose agents remember, collaborate, and use tools from day one.
Directory note
Centers orchestration on ready-to-run agent teams: memory-aware agents with persistent context, multi-agent collaboration between PM, developer, deployment, research, and custom agents, composable capabilities, and Matrix-based communication.
Ag
An autonomous research system that coordinates scientist, coder, and auditor loops from topic to idea, proposal, experiment, and paper.
Directory note
Centers orchestration on compact prompt loops, zero-code dispatch, independent critique, and human checkpoints for long-running scientific research.
A CLI-first control plane for reviewable, repeatable, and resumable coding-agent workflows in Markdown, with explicit artifact handoffs across Claude Code, Codex, Gemini CLI, Copilot CLI, and other configured commands.
Directory note
Centers orchestration on explicit DAGs, artifact-backed handoffs, bounded review loops, and resumption from validated completed nodes while provider CLIs retain their own tools, permissions, and authentication.
Po
Open-source workspace for taking ideas from conversation to coordinated work with coding agents through a task system shared by agents and developers.
Directory note
A shared task system lets agents organize the effort while developers follow progress, discuss decisions, and change direction.
Not open, important
Closed products shaping the category.
These products are not open-source projects, but they are important enough to track because they influence how builders think about multi-agent orchestration.
Augment's answer to what comes after the IDE: agent orchestration, isolated workspaces, and living specs in one developer workspace.
Directory note
Not open-source; tracked as an important category signal because Intent puts coordinated agents, isolated workspaces, and living specs in one developer workspace.
Hy
A closed AI-agent platform for performance marketing where agents connect to the marketing stack, analyze data, launch campaigns, generate reports, and run scheduled workflows.
Directory note
Not open-source; tracked as an important category signal because Hyper turns marketing work into an agent operating layer with tool connections, custom agents, action controls, reporting, and MCP-aware integrations.
A closed autonomous company OS for running daily operations with a self-improving multi-agent growth team.
Directory note
Not open-source; tracked as an important category signal because Crewlet frames multi-agent orchestration as an operating layer for growth, engineering, support, and data work across existing company tools.
AG
A commercial desktop workspace for orchestrating Claude Code, Codex, and other coding agents on a persistent visual canvas.
Directory note
Not open-source; combines visible master/worker delegation, follow-up messages, session recovery, terminals, browsers, and notes in one project workspace.
Governance
Governance and enforcement layers.
Tools that sit between agent intent and execution: policy checks, approval gates, budgets, permissions, and audit trails.
MIT-licensed runtime governance toolkit for AI agents with policy enforcement, identity, sandboxing, reliability, and compliance checks.
Sits between agent frameworks and actions so tool calls, resource access, and inter-agent messages can be evaluated before execution. Microsoft documents Python, TypeScript, .NET, Rust, and Go SDKs, plus integrations for LangChain, CrewAI, AutoGen, OpenAI Agents SDK, Google ADK, Semantic Kernel, Dify, LlamaIndex, Haystack, LangGraph, and related stacks.
Open governance toolOpen-source Python SDK for pre-execution governance gates around AI agents, backed by Postgres.
Adds scope checks, budget caps, human approval tokens, loop detection, agent presence and halt handling, behavioral contracts, and HMAC-chained audit trails for actions routed through the SDK. Tracked as agent-friendly tooling, not an orchestrator runtime.
Open governance toolApache-2.0 public-fact and causal-coordination kernel for human-agent and multi-agent work.
Preserves durable Turn-owned work records, handoff facts, claim fencing, causal lineage, and pull-first recovery across agent runtimes without acting as the orchestrator itself.
Open kernelApache-2.0-licensed open-source AI gateway with provider routing, virtual-key access controls, budgets, rate limits, and MCP tool governance.
Sits between agent runtimes and model or MCP endpoints; its documented virtual keys apply per-key budgets, rate limits, allowed models, and routing rules, while MCP tool filtering can default-deny and allow-list tools. Tracked as a governance and enforcement layer, not an orchestrator runtime.
Open governance tool
Open-source authorization layer that intercepts AI agent tool calls before execution and evaluates them against policy.
Provides TypeScript and Python SDKs, YAML rules, local deterministic evaluation, optional semantic checks, human approval routing, audit logs, and integrations for OpenAI, Anthropic, LangGraph, CrewAI, MCP, browser agents, and custom tool-calling setups. The core repo is Apache-2.0; Veto Cloud adds managed commercial services.
Open governance tool
Commercial Databricks platform layer that extends Unity Catalog governance to LLM access, MCP servers, APIs, and agentic AI workflows.
Tracks LLM and MCP calls, controls which agents can access external systems with fine-grained permissions and on-behalf-of access, and adds observability, cost attribution, guardrails, fallback models, and rate limits. Included as a commercial governance layer, not an open-source toolkit.
Open governance toolCommercial MCP gateway that places agents and MCP servers behind one governed entry point.
Routes tool calls through OAuth 2.1 and SSO identity, team- and role-scoped RBAC, runtime guardrails, and audit logs. Included as a commercial governance layer, not an orchestrator.
Open governance toolTrust and policy enforcement gateway for agent-to-agent settlement, reputation, spending limits, provenance, escrow, and audit trails.
Sits between agents and an A2A Settlement Exchange so settlement requests can be governed by reputation thresholds, spend caps, provenance requirements, health checks, alerts, and cryptographic audit logs. The related A2A Settlement repo is MIT-licensed; SettleBridge's public license metadata is inconsistent across the website, README badge, and GitHub detection, so it is tracked as a trust governance layer rather than a clean OSS claim.
Open governance toolTools
Tools that make multi-agent orchestration better.
Web analytics for builders that Claude Code, Codex, Cursor, OpenClaw, Paperclip, and similar AI agents can use.
Exposes traffic, usage, sources, funnels, conversions, projects, stats, and experiments through plugin, skill, MCP, CLI/npx, and API so agents can set up tracking, verify events, brief you, find conversion leaks, and run growth experiments without a dashboard-first workflow.
Open toolReusable companies for AI agents: pre-built organizations that can be installed with a single command.
Useful when orchestration needs reusable agent-company structures instead of starting every multi-agent team from scratch.
Open tool
Observability for OpenClaw agents that shows what failed, where spend leaked, and how to improve runs.
Adds traces, trajectory dashboards, token and cost visibility, and Tracy, a doctor agent that recommends fixes from live run data.
Open toolLocal TUI observability for AI coding-agent sessions, tokens, cost, tool failures, latency, anomalies, diffs, and CI evidence.
Parses local logs from Claude Code, Codex CLI, Gemini CLI, Aider, Cursor exports, OpenClaw, and related coding agents so builders can inspect session health without sending prompts or code to a hosted tracing service.
Open toolRecords a coding-agent run beneath the harness and replays it offline from the recorded bytes, or re-runs it from a chosen step on a different model.
Captures the model traffic through a base-URL proxy plus shell, MCP, and filesystem layers, so a multi-agent run can be re-executed byte-for-byte or forked at a checkpoint to compare models on an identical prefix; the trace reconstructs which sub-agent ran and which handed off to which.
Open tool
macOS workspace for running Claude Code, Codex, Gemini CLI, and other agentic CLIs in parallel sessions.
Runs each agentic CLI as a real PTY in the user's shell, with project boards, auto-created git worktrees, session resume, git diffs, file editing, labels, dependencies, and quick commands. Tracked as a tool/session workspace, not an orchestrator runtime.
Open toolAgentic Development Environment for teams using multiple coding agents in one controlled workspace.
Runs Claude Code, Codex, Cursor, and other coding agents behind a shared workbench with containerized disk/network isolation, tasks, diffs, artifacts, unified transcripts, and review. Tracked as an ADE/workspace layer for teams standardizing agent work, not as a product analytics system.
Open ctxApache-2.0 relay for exposing existing local agents as capabilities callable by teammates and other agents over a trusted LAN.
Keeps source code, runtime dependencies, prompts, and credentials on the publishing machine while callers use a lightweight CLI with JSON output, agent identity checks, meaningful exit codes, and bounded conversations. Tracked as an agent capability-sharing and coordination-adjacent tool, not as an orchestrator runtime.
Open relayPer-user Codex skill that represents complex tasks as bounded work graphs and records revisioned local state.
Keeps graph changes, integration, reconciliation, and completion under one parent task; nodes can run inline or through optional specialists, uncertain work is reconciled before retry, and planned checks run again at closeout; this directory tracks it as Codex workflow tooling rather than a standalone orchestrator runtime.
Open toolAn MIT-licensed macOS workspace for Codex with Kanban tasks, repository browsing, subagent conversation inspection, and local code review.
Connects task planning, Codex execution, delegated-agent visibility, and review; the Apple Silicon and Intel public beta requires macOS 15+, uses the user's own supported Codex account, and is not yet notarized by Apple.
Open OrchestratorMIT MCP server that spawns parallel coding-agent fleets as independent OS processes, with peer-to-peer messaging and witnessed receipts for every handoff.
Configured the same way for Claude Code, Codex, and OpenCode via a standard stdio MCP server; quorum-based councils are part of the free core, per the project README. Install: npx -y meshfleet.
Open toolMIT-licensed local-first Rust daemon and CLI that runs Codex, Claude Code, and other coding-agent harnesses as PTY sessions inside explicit project-root boundaries.
The daemon rejects working directories that escape the project root, persists session history in SQLite, and exposes a versioned local socket API (coven.daemon.v1). Tracked as a CLI session runtime, not an orchestrator of agent teams.
Open toolApache-2.0 terminal UI that runs Claude Code, Codex, OpenCode, Gemini CLI, and other coding-agent CLIs side by side in persistent tmux sessions.
Runs on macOS and Linux (Windows via WSL2), launches each installed CLI unmodified so logins and config carry over, and adds live status, prompts sent without attaching, optional per-session Git worktrees, diff review that sends line comments back to the agent, and a built-in MCP server that lets one agent spawn, message, and wait on another session.
Open toolClosed-source, free macOS workspace for running Claude Code, Codex, and other coding-agent CLIs in parallel git worktrees.
Gives each task its own worktree, terminal, browser, and diff review, with optional Docker or Apple container, SSH-host, or cloud-sandbox isolation and Manager Agents that start and steer other agents through the dev CLI; tracked as a session workspace rather than an orchestrator runtime.
Open toolServices
Implementation services for production agent teams.
Services companies and consultants that publish practical material on deploying, hardening, and operating multi-agent systems. These are not player entries.
Malta-based AI innovation group helping organizations understand, implement, and scale AI through consulting, development, and products.
Tracked as an implementation services entry, not an orchestrator. Nomad Inno publishes services around AI strategy, responsible AI, custom LLM development, fine-tuning, RAG, system integration, process mapping, workflow automation, and practical AI implementation through Artificial Impact, Peachstone AI, and Systems Impact.
Open serviceImplementation services and practical writing for teams moving AI agents from pilots into production operations.
Tracked as an implementation services entry, not an orchestrator. Public contact details list United States and Canadian offices in New York and Montreal; no explicit worldwide coverage claim is made. Relevant because Agentix publishes production-agent guidance around OpenClaw implementation, observability, run reviews, security reviews, permissions, evals, guardrails, and operating models.
Open service