The open orchestration layer for autonomous AI agents

DeepSeek Harness lets you run, route, and observe multi-agent workflows on any infrastructure — from a laptop to a global edge network.

Read the Docs View on GitHub
12k+GitHub stars
99.98%relay uptime
<40 msmedian hop latency
MITlicense
🧩

Pluggable Agents

Bring any LLM backend — DeepSeek, GPT, Claude or local weights. One unified tool-call interface for all of them.

Edge Relays

Lightweight relay nodes keep agent sessions alive across regions with automatic failover and sub-second handoff.

🔐

Sandboxed Execution

Every agent action runs inside an isolated capability sandbox. Filesystem, shell and network scopes are policy-driven.

📈

Built-in Telemetry

Token accounting, latency traces and per-step logs streamed to your observability stack out of the box.

All systems operational · edge relay online