Terminal
Terminal/Skill
Create a new AI agent on a live LiteLLM proxy. Asks for agent name, the underlying model, and optional MCP server access, then calls POST /v1/agents.
By LiteLLM
Works with
npx skills add berriai/litellm-skills --skill add-agentCreate a new AI agent on a live LiteLLM proxy.
Ask for these if not already known:
LITELLM_BASE_URL — e.g. https://my-proxy.example.com
LITELLM_API_KEY — proxy admin key
API reference: https://docs.litellm.ai/docs/proxy/agents
my-coding-agent)gpt-4o, claude-3-5-sonnet)server_ids this agent can usecurl -s -X POST "$BASE/v1/agents" \
-H "Authorization: Bearer $KEY" \
-H "Content-Type: application/json" \
-d '{
"agent_name": "<name>",
"litellm_params": {
"model": "<model>"
},
"agent_card_params": {
"name": "<name>",
"description": "<description>",
"version": "1.0"
}
}'
curl -s "$BASE/v1/agents" \
-H "Authorization: Bearer $KEY"
curl -s "$BASE/v1/agents/<agent_id>" \
-H "Authorization: Bearer $KEY"
curl -s -X DELETE "$BASE/v1/agents/<agent_id>" \
-H "Authorization: Bearer $KEY"
Show agent_id — needed to call or delete this agent later.