ajshedivy/agno-cookbook/agentos-api-teams

Claude Code and agent skill by ajshedivy/agno-cookbook

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

Interact with AgentOS Team API endpoints. For standard operations (listing teams, running teams, streaming), use the provided CLI script first. Only write custom Python when the script cannot handle the use case (e.g., cancellation, chaining multiple calls, custom error handling). Trigger when: running teams remotely, listing teams, creating team tests, or asking things like "what teams do I have configured?" or "run a task on my research team."

Install

npx vskill@latest install ajshedivy/agno-cookbook/agentos-api-teams

SKILL.md

The same SKILL.md was published earlier as ajshedivy/agno-cookbook/agentos-api-teams.

AgentOS Teams API

Prerequisites

Start an AgentOS server with teams configured:

bash
export ANTHROPIC_API_KEY=sk-...
uv run start_agentos.py # See agno-agentos skill

Default: Use the CLI Script

Always try the provided script first. It covers listing teams, running teams (streaming and non-streaming), and session persistence — all from the command line with no custom code needed.

The script is at: scripts/run_teams.py

List all teams
bash
uv run scripts/run_teams.py --base-url http://localhost:7777
Show full AgentOS config
bash
uv run scripts/run_teams.py --base-url http://localhost:7777 --config
Show team-specific config (members, models, tools)
bash
uv run scripts/run_teams.py --base-url http://localhost:7777 --config --team-id my-team
Run a team with a message
bash
uv run scripts/run_teams.py --base-url http://localhost:7777 \
--team-id research-team \
-m "Compare Python and Rust"
Stream a response
bash
uv run scripts/run_teams.py --base-url http://localhost:7777 \
--team-id research-team \
-m "Analyze Tesla stock" --stream
Persistent sessions
bash
uv run scripts/run_teams.py --base-url http://localhost:7777 \
--team-id research-team \
-m "Analyze NVIDIA" --session-id research-1
uv run scripts/run_teams.py --base-url http://localhost:7777 \
--team-id research-team \
-m "Now compare to AMD" --session-id research-1
Run against a remote server
bash
uv run scripts/run_teams.py --base-url http://my-server:8000 \
-m "Research AI trends"
Full CLI reference
uv run scripts/run_teams.py --help

When to Write Custom Python

Only write ad-hoc Python when the CLI script cannot handle your use case:

  • Cancel a team run mid-execution
  • Chaining multiple team calls in a single script
  • Custom error handling or retry logic
  • Programmatic inspection of team config beyond what --config shows
  • Integration tests that assert on response content
  • Authentication with custom headers (e.g., JWT tokens)

API Endpoints

MethodPathDescription
GET/teamsList all teams
GET/teams/{team_id}Get team details
POST/teams/{team_id}/runsCreate team run
POST/teams/{team_id}/cancel_runCancel team run

Custom Python Examples

Cancel Team Run
python
await client.cancel_team_run(
team_id=team_id,
run_id=run_id,
)
Authentication

When the AgentOS instance has a security key configured:

python
result = await client.run_team(
team_id=team_id,
message="Research topic",
headers={"Authorization": "Bearer your-jwt-token"},
)
Error Handling
python
from agno.client import AgentOSClient, RemoteServerUnavailableError
try:
client = AgentOSClient(base_url="http://localhost:7777")
config = await client.aget_config()
except RemoteServerUnavailableError as e:
print(f"Server unavailable: {e.message}")
print(f"URL: {e.base_url}")

Anti-Patterns

  • Don't write custom Python for basic list/run operations — use the CLI script
  • Don't forget `await` — all client methods are async
  • Don't hardcode team IDs — discover them from aget_config() or the CLI script
  • Don't confuse team and agent imports — teams use from agno.run.team import RunContentEvent
  • Don't skip discovery — always call aget_config() first to verify teams exist
  • Don't forget the server — start AgentOS before running client code

Further Reading

For advanced team API patterns, read references/api-patterns.md.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
0

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ajshedivy/agno-cookbook/agentos-api-teams/badge)](https://verified-skill.com/skills/ajshedivy/agno-cookbook/agentos-api-teams)

Something wrong with this skill or its page? Tell us.