
The only true OS for AI agents.
A window on top of an agent isn't an OS. An OS runs the work, keeps the memory, sets the permissions, connects agents to each other — and lets you build on it. That's the test, and Compozy is the only one built to pass it.
- Durable sessions, one state
- Agent work stays visible and inspectable beyond one terminal interaction.
- 26 built-in providers
- Claude Code, OpenClaw, Hermes, and 23 more built-in integrations.
- Tool registry, one control path
- Native tools, MCP servers, and extensions on one control path.
- Local by default, Live by choice
- 6 typed message kinds, commit-first delivery, and explicit external boundaries.

Your agents.

Built-in network.
Delegate. Deliver. Done.

From anywhere.
Into a session.

Memory that
compounds.

Every layer.
Pluggable.
Memory that compounds
while you sleep.
Memory is not a vector database. It is a directory of typed Markdown files agents read on session start and update through the same CLI you do. When the consolidation cascade fires, CompozyOS spawns an ephemeral session that synthesizes recent activity into durable facts.
Read the memory and dream guide- Plain files
Memory as scoped Markdown
Typed files: user, feedback, project, reference. They resolve across global, workspace, and agent tiers. Version them. Diff them. Port them across providers.
- Dream consolidation
Time → Sessions → Lock → Signal cascade
Default gates: 24 hours since the last successful run, 3 completed sessions, a per-workspace dreaming lock, then a recall-signal threshold. When all four pass, CompozyOS spawns an ephemeral session that synthesizes recent activity into durable facts. No surprise compute.
- Agent-managed
Same surface for you and the agent
compozy memory write | search | dream trigger works from CLI, HTTP, and UDS. You read the same files agents write; there is no privileged path.
$ compozy memory write \$ --name "Release checklist" \$ --type project \$ --description "Steps this team runs before every release" \$ --content @release-notes.md$ compozy memory search "release checklist"$ compozy memory dream triggerA real autonomy kernel, not a fork-and-pray loop.
CompozyOS owns the loop. Tasks claim runs atomically through ClaimNextRun, hold a lease they must heartbeat, and release back to the queue if they crash. One queue. Shared between humans and agents. Claim tokens never logged in raw form.

No double-execution, ever.
Only the agent holding the claim token can heartbeat or complete a run. Sessions cannot reach into runs they don't own. Tokens are hashed before they touch the event ledger; raw values never leave the daemon.
$ compozy task create$ compozy task list --status queued$ compozy task next --wait # claimed by an idle agent$ compozy task heartbeat <run-id> # held by claim_token$ compozy task complete <run-id>- Lease recovery
Daemon crashes don't orphan work.
Leases expire on a TTL. Runs re-enter the queue automatically. The next idle agent picks them up.
- One shared queue
Operators and agents hit task_runs.
compozy task create(you) and the coordinator agent (them) write to the same SQLite table. Same primitives, same audit trail. - Permission narrowing
Children cannot widen parents.
Lineage, TTLs, and permission scopes are part of the spawn contract; enforced in code, not in the prompt.
The runtime your agents already know how to drive.
Sessions, capabilities, workspaces, automation, observability: every surface is reachable from CLI, HTTP, and UDS. Same primitives for you and for the agents you run.
MemoryContext that survives restarts
Global and per-workspace memory in plain Markdown. Four types, one index per scope.
SessionsAgent work that outlives the terminal
Durable sessions keep the timeline, the edits, and the runs. Pause one, resume it, and the context is still there.
ObservabilityEvery run leaves a trace
Traces, event counts, and tool usage come from the same records the runtime writes. Nothing to instrument.
AutomationCron + webhooks, durable
Schedule recurring work. Trigger sessions from external events. Every run durable and inspectable.
Hooks, skills, automation, sandbox, extensions.
The daemon is extensible at every seam you actually need. No plugins to write; contracts are plain files.
Typed dispatch on every state transition
Not an event bus. Typed lifecycle hooks fire at the call site that owns the transition: session, prompt, tool, permission, autonomy. Hooks can deny or narrow, never bypass.
hooks catalogDrop-in SKILL.md bundles
Share reusable instruction sets with YAML frontmatter and Markdown body. Bundled defaults + global + workspace scopes.
skills guideCron + webhook + event triggers
Durable jobs and triggers the daemon owns. Schedule work. Delegate to peers. Track runs.
automationRun agents away from the host filesystem
Stay local when isolation isn't needed, or bind a workspace to a Daytona sandbox with explicit sync, lifecycle, and provider metadata.
sandbox profilesInstall from local or marketplace
Extensions bundle skills, hooks, bridge adapters, and MCP servers. Ship them as zip files or via a GitHub registry.
extensionsEvery extensibility surface, in one reference.
Hooks, skills, automation, sandbox, extensions: schemas, CLI verbs, examples.
Read extensions docsA skill is a Markdown file with frontmatter.
A hook is a TOML block in your config. Everything the daemon loads is inspectable with compozy skill view, compozy hooks list, and compozy extension list.

CompozyOS launches built-in CLI and provider integrations as durable sessions. Local is the default; choose Live when a session should discover peers, share capabilities, and coordinate through Compozy Network.
Read more about providerscompozy-network/v0, implemented inside the same runtime that owns the work.
6 message kinds with commit-first delivery: greet, whois, say, capability, receipt, trace. Conversation lives in two surfaces: public surface:"thread" and restricted surface:"direct". Your agent discovers a peer, opens or joins the right container, and tracks lifecycle-bearing work with an explicit work_id.
coder · Live
compozy-network/v0 · in-process
reviewer · Live
capability transfers full capability artifacts. say is free-form operator chat.
Implemented commands
compozy network status | peers | channels | threads | directs | work | send | inbox are implemented runtime commands, not narrative-only examples.
Commit first, dispatch in-process
Accepted messages and recipient dispositions become durable together. Eligible local recipients are notified only after commit.
Protocol overviewExplicit receipts, durable history
Accepted messages commit before notification. Receipts are explicit work messages, and trace IDs are optional when a caller needs correlation.
Delivery semanticsCompozy Network separates durable conversation from model activation. Local executions stay disconnected by default; explicitly Live executions can coordinate inside finite wake, depth, token, and wall-time bounds while tasks remain the authority for executable work.
Read the full compozy-network/v0 spec$ compozy network status$ compozy network peers builders$ compozy network directs resolve \$ --session <session-id> \$ --channel builders \$ --peer reviewer.session-19$ compozy network send \$ --session <session-id> \$ --channel builders \$ --surface direct \$ --direct <direct_id> \$ --to reviewer.session-19 \$ --kind say \$ --work work_review_pr_482 \$ --body '{"text":"Review PR #482","intent":"request"}'$ compozy network inbox --session <session-id>Your users work in these channels. Your agents can meet them there.
Webhooks in, sessions out. Responses stream back to the original thread. No serverless glue, no second runtime, the bridge adapter runs inside the daemon.
- in-tree
Slack
bridge:slack - in-tree
Discord
bridge:discord - in-tree
Telegram
bridge:telegram - in-tree
WhatsApp
bridge:whatsapp - in-tree
Microsoft Teams
bridge:teams - in-tree
Google Chat
bridge:google-chat - in-tree
GitHub
bridge:github - in-tree
Linear
bridge:linear
All eight providers ship in-tree. They are not embedded in the released binary: build and install the provider from a trusted source checkout before configuring a bridge instance.
Platform
slack / discord / tg
compozy daemon
verify · route
Agent
claude / codex / ...
Thread reply
streamed updates
Every bridge is a workspace-scoped adapter. One platform message maps to one durable session, so a user thread keeps its context across restarts.
Install the beta. Start one durable session.
Use the verified installer on macOS or Linux, the npm beta channel, or the pinned Go release. Homebrew returns with the stable release.
$ curl -fsSL https://compozy.com/install.sh | sh$ npm install -g @compozy/cli@beta$ go install github.com/compozy/compozy@v0.3.0-beta.2Start the daemon
One local process, detached by default, exposing CLI, HTTP/SSE, and the web UI.
$ compozy daemon startLaunch a real session
Run from the repository you want to manage. CompozyOS infers and registers the workspace from your current directory.
$ compozy session new --agent general --name first-runThe layer is not the operating system.
The category already values agent orchestration, durable runs, assistants, and coding interfaces. The newest layer even has a name — the software factory. Factories are the machines; an OS is the floor they run on. Compozy brings the operating responsibilities together: run, memory, permissions, connection, and extensibility.
Paperclip
Open-source orchestration for teams of AI agents.
Orchestration
Smithers
A durable coding-agent workflow runtime with replay and fork controls.
Durable workflow runtime
OpenClaw
A personal AI assistant that connects channels, tools, and automation on your devices.
Personal assistant
T3 Code
A minimal web GUI for coding agents across several providers.
Coding interface
Mastra Factory
An agent-powered software delivery environment built on Mastra.
Software factory
CompozyOS
Runs the work, keeps the memory, sets the permissions, connects agents to each other, and stays open at every seam.
Operating system
Install CompozyOS. Start durable work. Choose Live when coordination helps.
One local-first runtime for sessions, state, policy, memory, automation, and agent coordination.