Agentlas-OS is an open-source agent runtime fabric and orchestrator developed by Agentlas AI. It is designed to standardize, coordinate, and govern interactions across heterogeneous AI coding runtimes, agents, and tooling environments via declarative contract specifications and unified communication protocols. The system operates via command-line utilities (such as the agentlas-one CLI and Hephaestus command dispatchers) and leverages a standard-library ACP (Agent Client Protocol) v1 implementation. It manages runtime registries, streams prompts, handles secretless authentication, and coordinates sessions across local runtimes and cloud backends while decoupling model identity from transport mechanisms. Agentlas-OS differentiates itself by focusing on declarative runtime governance, contract validation, and protocol standardization. It includes runtime capability grading (grades A–E, install levels L0–L3), automated runtime drift detection, and native verification for both Agent Plugins 1.0 and Model Context Protocol (MCP) configuration contracts. The project is available as open-source software on GitHub and serves as modular harness infrastructure for developers building reproducible multi-agent developer workflows.
ACP v1 Client — Native, standard-library-only client handling session initialization, secretless authentication, and structured prompt streaming. - Declarative Runtime Registry — Matrix system that categorizes runtime environments by capability grades (A–E) and install depth levels (L0–L3). - MCP & Plugin Manifest Support — Built-in contract verification and packaging for Model Context Protocol (mcp.json) and Agent Plugins 1.0 specifications. - Runtime Drift Detection — Automated scripts to detect capability diffs and configuration drift between local installations and registry definitions. - Dispatcher Command Interfaces — Unified CLI and slash-command dispatcher surfaces supporting actions like login, orchestration (orch), and updates. - Safe Lifecycle Management — The agentlas-one binary provides atomic uninstalls, timestamped backups, and structured JSON runtime status inspection.
Use cases
Use Case: Heterogeneous Agent Orchestration Standardize and manage multiple coding agent runtimes on developer workstations using a centralized runtime registry. Teams can inspect per-machine runtime support matrices and route agent workloads through uniform ACP streams.
Use Case: MCP and Agent Plugin Contract Validation Verify and enforce Model Context Protocol (mcp.json) and Agent Plugin schemas before releasing or executing agent integrations. Developers can run automated contract checks to prevent broken transport interfaces during execution.
Use Case: Runtime Capability and Drift Monitoring Monitor environment drift against upstream ACP specifications in CI/CD or local test runners. The harness identifies missing capabilities and protocol mismatches without auto-applying uncontrolled runtime changes.
Who it is for
Agentlas-OS is designed for platform engineers, tool builders, and developers orchestrating multi-runtime coding agent pipelines requiring deterministic contracts and protocol compliance. It is not intended for non-technical users looking for a plug-and-play graphical chat assistant.
Install guide
Installation Clone the repository directly from GitHub: bash git clone https://github.com/agentlas-ai/Agentlas-OS.git cd Agentlas-OS
First Run Check local runtime compatibility and authenticate against the orchestration harness: bash # Inspect the runtime support matrix in JSON format bin/agentlas-one status --runtimes --json # Authenticate the environment hephaestus auth login
Example Session Run drift detection to verify your runtime definitions, then execute orchestration tasks: bash # Check for runtime drift against registry pins python3 scripts/check-runtime-drift.py # Trigger orchestration through the dispatcher /agentlas orch
DeepAgents — DeepAgents is an open-source agentic coding framework and CLI tooling suite maintained by LangChain (langchain-ai). Designed to bring autonomous agent…
SWE-agent — SWE-agent is an open-source autonomous software engineering agent harness built and maintained by researchers from Princeton University and Stanford University.…
Agentic Engineering Framework — Agentic Engineering Framework is an open-source orchestration harness and governance layer developed by Dimitri Geelen. It is designed to constrain,…
Weaver — Weaver is an open-source agent harness and orchestration framework maintained by sean35mm on GitHub. Built on top of the Bun…
Stratless — Stratless is an open-source agent harness and execution orchestrator developed by the Stratless AI team. It provides a modular infrastructure…
Hivelore — Hivelore is an open-source agent harness and contextual memory orchestrator created by Doucs91. It provides persistent project memory, decision tracking,…