Modular, event-driven AI agent SDK with trigger plugins, LLM reasoning (Amazon Bedrock), retries, and a dashboard.
Project description
🧠 Agent Skill SDK
Build modular, intelligent agents with event triggers, retry logic, memory, LLM planning (Amazon Bedrock), and a live dashboard.
🚀 Features
- ✅ Skill-based programming with
@skilldecorators - 🔁 Retry, backoff, and fallback on skill failure
- 🧠 LLM reasoning via Amazon Bedrock
- 🧩 Triggers: Timer, MQTT, HTTP, Cron, File Watcher, CoAP
- 📜 Memory tracing + export (CSV/JSON)
- ⚙️ CLI and 🧪 FastAPI-based dashboard
- 📚 Full developer documentation with MkDocs
📦 Install
pip install agent-skill-sdk
🧪 Example: Define a Skill
from agent_skill_sdk import skill
@skill(trigger="on_temp_high", retries=2, backoff="exponential")
def turn_on_fan(context):
print("Turning on fan:", context.get("location"))
⚡ Trigger from CLI
agent register examples.fan_control.turn_on_fan
agent trigger on_temp_high --data '{"location": "lab"}'
🧠 LLM Planning (Amazon Bedrock)
@skill(trigger="on_goal")
def bedrock_planner(context):
response = run_reasoning(context.get("goal"))
action = response.get("action")
context.agent.trigger(action)
Supports:
- Prompt templates
- Memory recall
- Fallback actions
🌐 Dashboard
uvicorn dashboard.app:app --reload
Visit http://localhost:8000 to:
- View registered skills
- Trigger events manually
- Inspect LLM trace logs
🔌 Trigger Plugins
| Trigger | File | Event |
|---|---|---|
| Timer | timer.py |
on_timer |
| MQTT | mqtt.py |
on_mqtt_message |
| HTTP/Webhook | http.py |
on_http |
| Cron | cron.py |
on_cron |
| File Watcher | file_watcher.py |
on_file_change |
| CoAP (IoT) | coap.py |
on_coap |
📚 Documentation
Visit your deployed docs here:
➡️ https://subhashtalluri.github.io/agent-skill-sdk/
Or build locally:
mkdocs serve
📤 Deployment
Use Docker or deploy with Uvicorn:
uvicorn dashboard.app:app --host 0.0.0.0 --port 8000
🧠 Trace Export
agent.export_trace("json")
agent.export_trace("csv")
🧩 Contributions Welcome
Build a trigger plugin, skill library, or submit a PR!
📜 License
MIT – do anything, just give credit ✨
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file agent_skill_sdk-0.1.1.tar.gz.
File metadata
- Download URL: agent_skill_sdk-0.1.1.tar.gz
- Upload date:
- Size: 11.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
685ef2b94035fb26691cf3937ed7f0dda06702a6d6c348a045b91fdff773d233
|
|
| MD5 |
f5b089e7fe4cfaba2c1e80a0d785d9cb
|
|
| BLAKE2b-256 |
c4c32b4bc61332858e88559ba83e876c25ed02e94cc25562c2d45a2de569c24b
|
File details
Details for the file agent_skill_sdk-0.1.1-py3-none-any.whl.
File metadata
- Download URL: agent_skill_sdk-0.1.1-py3-none-any.whl
- Upload date:
- Size: 14.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.0
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
56c20decc0b53ef510cffb7a8fbc6f648d15d1dbeb3b433337c412081e61a540
|
|
| MD5 |
b211d0339482ec84671e757bbe04d898
|
|
| BLAKE2b-256 |
191d68a0dfeb21ae817d71f73c815ca1250901ac39e6172858aebe2474ff65dd
|