Agent Harnesses | NVIDIA Dynamo Documentation

Dynamo exposes v1/chat/completions, v1/responses, and v1/messages, so any agent that uses these APIs can talk to a Dynamo endpoint even if it is not listed in this guide. This guide focuses on popular agent harnesses that send stable session IDs. Dynamo normalizes these IDs for tracing and other explicitly configured consumers.

Local Setup

To locally test these out, we have a small script that runs an SGLang-backed zai-org/GLM-4.7-Flash endpoint. This script starts a TP2 instance on port 8000 and enables request tracing for replay and visualization. By default traces are saved in /tmp/dynamo-request-trace-$(date +%Y%m%d-%H%M%S)

To start it, run:

$ bash examples/backends/sglang/launch/agg_agent.sh

Codex

Codex uses the Responses API. Add a local provider in ~/.codex/config.toml:

1 [model_providers.dynamo]
2 name = "dynamo"
3 base_url = "http://localhost:8000/v1"
4 wire_api = "responses"

$ # replace -m <model> with your model
$ codex -m zai-org/GLM-4.7-Flash -c model_provider=dynamo

Codex sends a session-id header that Dynamo maps to session_id.

Claude Code

Claude Code uses Anthropic-compatible Messages API. The local launcher above starts dynamo.frontend with --enable-anthropic-api; for other deployments, pass that flag when starting the frontend. Then set:

$ export ANTHROPIC_BASE_URL=http://localhost:8000
$ export ANTHROPIC_MODEL=zai-org/GLM-4.7-Flash
$ export ANTHROPIC_SMALL_FAST_MODEL=zai-org/GLM-4.7-Flash
$ export ANTHROPIC_BASE_URL=http://localhost:8000
$ export CLAUDE_CODE_ATTRIBUTION_HEADER=0 # preserve kv cache hits!
$ export ANTHROPIC_API_KEY=
$ 
$ claude

Dynamo uses x-claude-code-session-id as the Claude Code session ID. For subagents, Dynamo uses x-claude-code-agent-id as the child session ID. Nested subagents use x-claude-code-parent-agent-id as the parent; top-level subagents fall back to the root session ID.

OpenCode

OpenCode uses a project-local JSONC provider config; setting an endpoint env var alone is not enough. Create .opencode/opencode.jsonc in the project you run OpenCode from:

1 {
2   "provider": {
3     "dynamo": {
4       "npm": "@ai-sdk/openai-compatible",
5       "name": "Dynamo",
6       "models": {
7         "zai-org/GLM-4.7-Flash": {
8           "id": "zai-org/GLM-4.7-Flash",
9           "name": "GLM 4.7 Flash"
10         }
11       },
12       "options": {
13         "baseURL": "http://localhost:8000/v1"
14       }
15     }
16   },
17   "permission": {
18     "task": "allow"
19   }
20 }

Run OpenCode with the provider/model pair:

$ opencode -m dynamo/zai-org/GLM-4.7-Flash

Dynamo maps OpenCode’s x-session-id header to session_id and x-parent-session-id to parent_session_id.

OpenClaw

OpenClaw can use Dynamo through its OpenAI-compatible Responses endpoint. Install the Dynamo provider plugin:

$ git clone https://github.com/ai-dynamo/agent-plugins.git ~/agent-plugins
$ openclaw plugins install --link ~/agent-plugins/openclaw-plugin
$ openclaw plugins enable dynamo

Add a Dynamo-backed model to ~/.openclaw/openclaw.json:

1 {
2   "models": {
3     "providers": {
4       "dynamo": {
5         "baseUrl": "http://localhost:8000/v1",
6         "apiKey": "dynamo-local",
7         "api": "openai-responses",
8         "models": [
9           {
10             "id": "zai-org/GLM-4.7-Flash",
11             "name": "Dynamo GLM 4.7 Flash",
12             "reasoning": true,
13             "contextWindow": 128000,
14             "maxTokens": 8192
15           }
16         ]
17       }
18     }
19   },
20   "agents": {
21     "defaults": {
22       "model": {
23         "primary": "dynamo/zai-org/GLM-4.7-Flash"
24       }
25     }
26   }
27 }

Run OpenClaw:

$ openclaw chat

The plugin copies OpenClaw’s current sessionId into x-dynamo-session-id on each request. Native subagents receive their own session_id and the immediate parent is recorded as parent_session_id.

Hermes Agent

Hermes uses an OpenAI-compatible custom endpoint. Configure Hermes with the served model name and Dynamo /v1 base URL:

1 model:
2   default: zai-org/GLM-4.7-Flash
3   provider: custom
4   base_url: http://localhost:8000/v1
5   api_mode: chat_completions

If your Dynamo endpoint requires auth, add api_key: <token> to the Hermes model config or set OPENAI_API_KEY.

This configuration lets you run Hermes with the hermes command. To send session IDs to Dynamo, install the plugin:

$ # clone the plugin
$ git clone https://github.com/ai-dynamo/agent-plugins.git ~/agent-plugins
$ # link it to where hermes typically looks for plugins
$ ln -sfnT ~/agent-plugins/hermes-plugin ~/.hermes/plugins/dynamo_session
$ hermes plugins enable dynamo_session
$ 
$ # run hermes
$ hermes

The plugin copies the Hermes session_id into x-dynamo-session-id on each LLM request.