Development
Plugin
agno
Build, run, and manage agent platforms.
Plugin Signal72/100Solid
maintained100
capable23
documented75
adopted98
Install
$ npx -y skills add agno-agi/agno --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
Stats
41,648
Stars
5,751
Forks
Active
Maintenance
Python
Language
Apache-2.0
License
22m ago
Last commit
4y ago
Created
Repo: agno-agi/agno
What's inside
Agents
1Badges
1
README
1Introduction
Agno is a framework and runtime for agent platforms. Build agents, run them as a service, manage your platform using a web UI.
- Build your agent platform using the Agno SDK.
- Run your agent platform using the AgentOS runtime.
- Manage everything using the AgentOS UI.
Agno allows you to own your agent stack. Maintain control of your data, memory, and security posture (JWT-based RBAC), and turn your agent platform into a learning loop with simulations and usage data.
Get started
Hand this prompt to your coding agent (Claude Code, Cursor, Codex):
Help me set up my agent platform.
Clone https://github.com/agno-agi/agentos-railway into a folder called
agent-platform, cd in, read the README, and follow the get started guide.
Your coding agent will set up your agent platform and run it locally using Docker, giving you a REST API for serving your agents, a Postgres database for storing your data and traces, an MCP server, and a control plane.
Deploying somewhere else? Use the same prompt but point it to a different repo. The starter templates are identical except for the deploy scripts: swap agentos-railway for agentos-docker, agentos-aws, agentos-gcp, agentos-azure, agentos-fly, agentos-render, agentos-modal, or agentos-helm.
Prefer to code by hand?
Features
- Production API. 50+ endpoints with SSE and websockets to build a product on top.
- Storage. Store sessions, memory, knowledge, and traces in your own database.
- 100+ integrations. Connect to GitHub, Slack, Postgres, and more using pre-built toolkits.
- Context Providers. Access live data from Slack, Drive, wikis, MCP, and custom sources.
- Human approval. Pause runs for user confirmation. Block tools that require admin approval.
- Observability. Monitor with OpenTelemetry tracing, run history, and audit logs.
- Security. Get JWT-based RBAC and multi-user, multi-tenant isolation out of the box.
- Interfaces. Expose your agents via Slack, Telegram, WhatsApp, Discord, AG-UI, A2A.
- Scheduling. Cron-based scheduling and background jobs with no external infrastructure.
- Deploy anywhere. Run on any cloud platform that runs containers. Docker, Railway, AWS, GCP.
Use Agno with your coding agent
Two options:
- Recommended: Add Agno docs as an MCP server. Add docs.agno.com/mcp to your favourite coding agent.
- Add Agno docs as an indexed source. In Cursor: Settings → Indexing & Docs → Add
https://docs.agno.com/llms-full.txt. Also works in VSCode, Windsurf, and similar tools.
Read the full guide here.
Community
- X: follow for releases and demos
- Newsletter: monthly updates on what's shipping
Contributing
See the contributing guide.
License
Agno is distributed under the Apache-2.0 license.
Telemetry
Agno sends a telemetry event per agent run so we know which model providers to prioritize. Prompts, messages, and outputs are never sent. Disable by setting AGNO_TELEMETRY=false.
File tree
1737agno-agi/agnoView on GitHub
.cursorrules
.editorconfig
.github/
ISSUE_TEMPLATE/
bug-report.yml
config.yml
feature-request.yml
pull_request_template.md
workflows/
claude.yml
performance.yml
pr-lint.yml
pr-triage.yml
release.yml
test_on_release.yml
test.yml
.gitignore
AGENTS.md
CLAUDE.md
CODE_OF_CONDUCT.md
CODEOWNERS
CONTRIBUTING.md
cookbook/
.gitignore
00_quickstart/
__init__.py
.gitignore
agent_search_over_knowledge.py
agent_with_guardrails.py
agent_with_learning.py
agent_with_memory.py
agent_with_state_management.py
agent_with_storage.py
agent_with_structured_output.py
agent_with_tools.py
agent_with_typed_input_output.py
config.yaml
data/
agno_overview.md
generate_requirements.sh
human_in_the_loop.py
multi_agent_team.py
README.md
requirements.in
requirements.txt
run.py
sequential_workflow.py
TEST_LOG.md
TEST_PROMPT.md
01_demo/
.gitignore
agents/
__init__.py
code_search.py
git_wiki.py
local_wiki.py
notion_wiki.py
config.yaml
db.py
evals/
__init__.py
__main__.py
assets/
sample-diagram.png
cases.py
generate_requirements.sh
README.md
requirements.in
requirements.txt
run.py
settings.py
TEST_LOG.md
02_agents/
01_quickstart/
agent_with_instructions.py
agent_with_tools.py
basic_agent.py
README.md
TEST_LOG.md
02_input_output/
expected_output.py
followup_suggestions_streaming.py
followup_suggestions.py
input_formats.py
input_schema.py
output_model.py
output_schema.py
parser_model.py
README.md
response_as_variable.py
save_to_file.py
streaming.py
TEST_LOG.md
03_context_management/
datetime_format.py
few_shot_learning.py
filter_tool_calls_from_history.py
instructions_with_state.py
instructions.py
introduction_message.py
README.md
system_message.py
TEST_LOG.md
04_tools/
01_callable_tools.py
02_session_state_tools.py
03_team_callable_members.py
04_tools_with_literal_type_param.py
README.md
TEST_LOG.md
tool_call_limit.py
tool_choice.py
05_state_and_session/
agentic_session_state.py
chat_history.py
dynamic_session_state.py
last_n_session_messages.py
persistent_session.py
README.md
search_session_history.py
session_options.py
session_state_advanced.py
session_state_basic.py
session_state_events.py
session_state_manual_update.py
session_state_multiple_users.py
session_summary.py
TEST_LOG.md
06_memory_and_learning/
learning_machine.py
memory_manager.py
README.md
TEST_LOG.md
07_knowledge/
agentic_rag_with_reasoning.py
agentic_rag_with_reranking.py
agentic_rag.py
custom_retriever.py
knowledge_filters.py
rag_custom_embeddings.py
README.md
references_format.py
TEST_LOG.md
traditional_rag.py
08_guardrails/
custom_guardrail.py
mixed_hooks.py
openai_moderation.py
output_guardrail.py
pii_detection.py
prompt_injection.py
README.md
TEST_LOG.md
09_hooks/
message_history_hooks.py
post_hook_output.py
pre_hook_input.py
README.md
session_state_hooks.py
stream_hook.py
TEST_LOG.md
tool_hooks.py
10_human_in_the_loop/
confirmation_advanced.py
confirmation_required_mcp_toolkit.py
confirmation_required.py
confirmation_toolkit.py
confirmation_with_session_state.py
external_tool_execution.py
mixed_external_and_regular_tools.py
README.md
TEST_LOG.md
user_feedback.py
user_input_required.py
user_input.py
11_approvals/
approval_async.py
approval_basic.py
approval_external_execution.py
approval_list_and_resolve.py
approval_post_hook.py
approval_team.py
approval_user_input.py
audit_approval_async.py
audit_approval_confirmation.py
audit_approval_external.py
audit_approval_overview.py
audit_approval_user_input.py
README.md
TEST_LOG.md
12_multimodal/
.gitignore
audio_input_output.py
audio_sentiment_analysis.py
audio_streaming.py
audio_to_text.py
image_to_audio.py
image_to_image.py
image_to_structured_output.py
image_to_text.py
media_input_for_tool.py
README.md
TEST_LOG.md
video_caption.py
13_reasoning/
basic_reasoning.py
README.md
reasoning_with_model.py
TEST_LOG.md
14_advanced/
01_create_cultural_knowledge.py
02_use_cultural_knowledge_in_agent.py
03_automatic_cultural_management.py
04_manually_add_culture.py
advanced_compression.py
agent_run_cancel_persistence.py
agent_serialization.py
background_execution_metrics.py
background_execution_structured.py
background_execution.py
basic_agent_events.py
cache_model_response.py
cancel_run.py
combined_metrics.py
compression_events.py
concurrent_execution.py
culture_metrics.py
custom_cancellation_manager.py
custom_logging.py
debug.py
interchange_model/
all_providers.py
claude_gemini.py
openai_chat_responses.py
openai_claude.py
openai_gemini.py
README.md
metrics.py
multi_model_metrics.py
README.md
reasoning_agent_events.py
retries.py
session_metrics.py
session_summary_metrics.py
streaming_metrics.py
TEST_LOG.md
tool_call_compression.py
tool_call_metrics.py
15_dependencies/
dependencies_in_context.py
dependencies_in_tools.py
dynamic_tools.py
README.md
TEST_LOG.md
16_skills/
basic_skills_team.py
basic_skills.py
README.md
sample_skills/
code-review/
references/
style-guide.md
scripts/
check_style.py
SKILL.md
git-workflow/
references/
commit-types.md
scripts/
commit_message.py
SKILL.md
TEST_LOG.md
17_fallback_models/
01_basic_fallback.py
02_error_specific_fallbacks.py
03_mid_run_fallback.py
04_fallback_callback.py
18_checkpointing/
01_crash_recovery.py
02_tool_error_persistence.py
03_checkpoint_endpoints.py
README.md
TEST_LOG.md
19_regenerate/
01_regenerate.py
README.md
TEST_LOG.md
20_time_travel/
01_continue_from.py
02_fork_run.py
README.md
TEST_LOG.md
21_fork_session/
01_fork_session.py
README.md
TEST_LOG.md
README.md
TEST_PROMPT.md
03_teams/
01_quickstart/
01_basic_coordination.py
02_respond_directly_router_team.py
03_delegate_to_all_members.py
04_respond_directly_with_history.py
05_team_history.py
06_history_of_members.py
07_share_member_interactions.py
08_concurrent_member_agents.py
09_caching.py
broadcast_mode.py
nested_teams.py
README.md
task_mode.py
TEST_LOG.md
02_modes/
broadcast/
01_basic.py
02_debate.py
03_research_sweep.py
04_structured_debate.py
README.md
TEST_LOG.md
coordinate/
01_basic.py
02_with_tools.py
03_structured_output.py
README.md
TEST_LOG.md
README.md
route/
01_basic.py
02_specialist_router.py
03_with_fallback.py
README.md
TEST_LOG.md
tasks/
tasks_stream.py
01_basic.py
02_parallel.py
03_dependencies.py
04_basic_task_mode.py
05_parallel_tasks.py
06_task_mode_with_tools.py
07_async_task_mode.py
08_dependency_chain.py
09_custom_tools.py
10_multi_run_session.py
11_streaming_events.py
README.md
TEST_LOG.md
TEST_LOG.md
03_tools/
async_toolkit_context.py
async_tools.py
custom_tools.py
member_information.py
member_tool_hooks.py
message_history_in_tool_hooks.py
README.md
TEST_LOG.md
tool_call_limit.py
tool_choice.py
tool_hooks.py
04_structured_input_output/
expected_output.py
input_formats.py
input_schema.py
json_schema_output.py
output_model.py
output_schema_override.py
parser_model.py
pydantic_input.py
pydantic_output.py
README.md
response_as_variable.py
structured_output_streaming.py
TEST_LOG.md
05_knowledge/
01_team_with_knowledge.py
02_team_with_knowledge_filters.py
03_team_with_agentic_knowledge_filters.py
04_team_with_custom_retriever.py
05_team_update_knowledge.py
README.md
TEST_LOG.md
06_memory/
01_team_with_memory_manager.py
02_team_with_agentic_memory.py
03_memories_in_context.py
learning_machine.py
README.md
TEST_LOG.md
07_session/
chat_history.py
custom_session_summary.py
nested_team_deep_history.py
nested_team_history_to_members.py
nested_team_history.py
persistent_session.py
README.md
... 1600 moreShowing a partial view of a very large repo.
FAQ
agno is a Claude Code plugin with 1 hand-picked skill for development work, indexed on Flowy. Install it with the command on its page. It includes haiku. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is agno?
- Build, run, and manage agent platforms.
- How do I install agno?
- Run these in Claude Code: npx -y skills add agno-agi/agno --agent claude-code. Then prompt normally.
- Does agno auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is agno free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.