Development
Plugin
upsonic
Build Autonomous AI Agents in Python
Plugin Signal76/100Solid
maintained73
capable61
documented100
adopted83
Install
$ npx -y skills add Upsonic/Upsonic --agent claude-code
Run the curl in your terminal, the rest in Claude Code.
What's inside
Skills
17/analyze_currentRead and understand the current baseline implementation. Extract all relevant information about the existing approach without modifying anything, and record the analysis as a structured JSON entry./benchmarkDefine the comparison metrics and extract baseline values from the current implementation. Record them as a structured JSON entry so downstream phases and final evaluation can read them directly./evaluateCompare baseline and new implementation results. Produce the machine-readable final report `result.json`, update `experiments.json`, and append a row to `comparison.json`./experiment_managementSet up and manage the experiment folder structure. This is Phase 0 — it runs before any analysis begins. All bookkeeping files are JSON (never markdown)./implementCreate a new Jupyter notebook implementing the method from the research paper, using the same data as the baseline. Record implementation details and measured metrics as a structured JSON entry./progressMaintain a **machine-readable** progress file so dashboards, CLIs, and notebooks can poll the experiment's state at any time. The file is a JSON document — never markdown, never human-prose-first.
Show all 17 skillsShow fewer
/researchRead the materialized research source and extract actionable information needed to implement the proposed method. Record the findings as a structured JSON entry./analyze_currentRead and understand the current baseline implementation. Extract all relevant information about the existing approach without modifying anything, and record the analysis as a structured JSON entry./benchmarkDefine the comparison metrics and extract baseline values from the current implementation. Record them as a structured JSON entry so downstream phases and final evaluation can read them directly./evaluateCompare baseline and new implementation results. Produce the machine-readable final report `result.json`, update `experiments.json`, and append a row to `comparison.json`./experiment_managementSet up and manage the experiment folder structure. This is Phase 0 — it runs before any analysis begins. All bookkeeping files are JSON (never markdown)./implementCreate a new Jupyter notebook implementing the method from the research paper, using the same data as the baseline. Record implementation details and measured metrics as a structured JSON entry./progressMaintain a **machine-readable** progress file so dashboards, CLIs, and notebooks can poll the experiment's state at any time. The file is a JSON document — never markdown, never human-prose-first./researchRead the materialized research source and extract actionable information needed to implement the proposed method. Record the findings as a structured JSON entry./code-reviewPerform structured code reviews with actionable feedback. Use when a user asks to review code, check code quality, find bugs, audit security, improve performance, or assess maintainability. Trigger when user says things like "review this code", "check for bugs", "is this code/data-analysisAnalyze, explore, clean, and visualize datasets with statistical rigor. Use when user asks to analyze data, find patterns, compute statistics, create visualizations, clean messy data, or explore a dataset. Trigger when user says things like "analyze this data", "what trends do/summarizationSummarize documents, articles, conversations, code, and technical content into concise, accurate summaries. Use when user asks to summarize, condense, create a TL;DR, write an executive summary, extract key points, or distill content. Trigger when user says things like
Badges
1README
1Upsonic
Build Autonomous AI Agents in Python
Documentation • Quickstart • Examples • Discord
Overview
Upsonic is a Python framework for building autonomous agents like OpenClaw and Claude Cowork, as well as more traditional agent systems.
Quick Start
Installation
uv pip install upsonic
# pip install upsonic
IDE Integration
Add Upsonic docs as a source in your coding tools:
Cursor: Settings → Indexing & Docs → Add https://docs.upsonic.ai/llms-full.txt
Also works with VSCode, Windsurf, and similar tools.
Create Autonomous Agent
Build Your Own
from upsonic import AutonomousAgent, Task
agent = AutonomousAgent(
model="anthropic/claude-sonnet-4-5",
workspace="/path/to/logs"
)
task = Task("Analyze server logs and detect anomaly patterns")
agent.print_do(task)
All file and shell operations are restricted to workspace. Path traversal and dangerous commands are blocked.
Use Our Prebuilt Ones
Prebuilt autonomous agents are ready-to-run agents built by the Upsonic community, each packaging a skill, system prompt, and first message so you can go from install to running in seconds. The collection is open to contributions, bring your agent and open a PR.
Learn more: Prebuilt Autonomous Agents
Next steps: Connect a Sandbox Provider (E2B) for isolated cloud execution environments.
Create Traditional Agent
from upsonic import Agent, Task
agent = Agent(model="anthropic/claude-sonnet-4-5", name="Stock Analyst Agent")
task = Task(description="Analyze the current market trends")
agent.print_do(task)
Add Custom Tools
from upsonic import Agent, Task
from upsonic.tools import tool
@tool
def sum_tool(a: float, b: float) -> float:
"""
Add two numbers together.
Args:
a: First number
b: Second number
Returns:
The sum of a and b
"""
return a + b
task = Task(
description="Calculate 15 + 27",
tools=[sum_tool]
)
agent = Agent(model="anthropic/claude-sonnet-4-5", name="Calculator Agent")
result = agent.print_do(task)
Next steps: Integrate MCP Tools to connect your agents to thousands of external data sources and services.
OCR and Document Processing
Upsonic provides a unified OCR interface with a layered pipeline: Layer 0 handles document preparation (PDF to image conversion, preprocessing), Layer 1 runs the OCR engine.
uv pip install "upsonic[ocr]"
from upsonic.ocr import OCR
from upsonic.ocr.layer_1.engines import EasyOCREngine
engine = EasyOCREngine(languages=["en"])
ocr = OCR(layer_1_ocr_engine=engine)
text = ocr.get_text("invoice.pdf")
print(text)
Supported engines: EasyOCR, RapidOCR, Tesseract, PaddleOCR, DeepSeek OCR, DeepSeek via Ollama.
Learn more: OCR Documentation
Check Our Videos
Documentation and Resources
- Documentation - Complete guides and API reference
- Quickstart Guide - Get started in 5 minutes
- Examples - Real-world examples and use cases
- API Reference - Detailed API documentation
Community and Support
💬 Join our Discord community! — Ask questions, share what you're building, get help from the team, and connect with other developers using Upsonic.
- Discord - Chat with the community and get real-time support
- Issue Tracker - Report bugs and request features
- Changelog - See what's new in each release
License
Upsonic is released under the MIT License. See LICENCE for details.
Contributing
We welcome contributions from the community! Please read our Contributing Guide and code of conduct before submitting pull requests.
File tree
1084Upsonic/UpsonicView on GitHub
.claude/
agents/
unittest-generator.md
.github/
ISSUE_TEMPLATE/
bug_report.md
feature_request.md
workflows/
ci.yml
claude-code-review.yml
claude.yml
release.yml
sync-dev.yml
test_publisher.yml
.gitignore
.gitmodules
.pre-commit-config.yaml
.python-version
.release-please-manifest.json
benchmarks/
__init__.py
.gitignore
Makefile
overhead_analysis/
__init__.py
benchmark.py
README.md
results/
.gitkeep
test_cases.py
QUICKSTART.md
README.md
SETUP.md
utils.py
CHANGELOG.md
CLAUDE.md
CODE_OF_CONDUCT.md
CONTRIBUTING.md
documents/
ai/
explanation/
agent/
agent.md
cache/
cache.md
canvas/
canvas.md
chat/
chat.md
cli/
cli.md
context/
context.md
culture/
culture.md
db/
db.md
embeddings/
embeddings.md
eval/
eval.md
graph/
graph.md
graphv2/
graphv2.md
integrations/
integrations.md
interfaces/
interfaces.md
knowledge_base/
knowledge_base.md
loaders/
loaders.md
memory/
memory.md
messages/
messages.md
models/
models.md
ocr/
ocr.md
prebuilt/
prebuilt.md
profiles/
profiles.md
providers/
providers.md
ralph/
ralph.md
reflection/
reflection.md
reliability_layer/
reliability_layer.md
run/
run.md
safety_engine/
safety_engine.md
schemas/
schemas.md
session/
session.md
simulation/
simulation.md
skills/
skills.md
storage/
storage.md
tasks/
tasks.md
team/
team.md
text_splitter/
text_splitter.md
tools/
tools.md
uel/
uel.md
utils/
utils.md
vectordb/
vectordb.md
guides/
bug-fix.md
coding-standards.md
commit.md
feature.md
memory.md
new_prebuilt_agent_adding.md
refactor.md
serena.md
subagents.md
testing.md
LICENCE
Makefile
notebooks/
investment_full_report.md
stock_report.ipynb
prebuilt_autonomous_agents/
applied_scientist/
example.sh
first_message.md
skills/
analyze_current/
SKILL.md
benchmark/
SKILL.md
evaluate/
SKILL.md
experiment_management/
SKILL.md
implement/
SKILL.md
progress/
SKILL.md
research/
SKILL.md
system_prompt.md
pyproject.toml
pytest.ini
README.md
release-please-config.json
SECURITY.md
src/
upsonic/
__init__.py
_griffe.py
_json_schema.py
_output.py
_parts_manager.py
_ssrf.py
_utils.py
agent/
__init__.py
agent.py
autonomous_agent/
__init__.py
autonomous_agent.py
filesystem_toolkit.py
shell_toolkit.py
base.py
context_managers/
__init__.py
call_manager.py
context_management_middleware.py
context_manager.py
llm_manager.py
memory_manager.py
reliability_manager.py
system_prompt_manager.py
task_manager.py
deepagent/
__init__.py
backends/
__init__.py
composite_backend.py
memory_backend.py
protocol.py
state_backend.py
constants.py
deepagent.py
tools/
__init__.py
filesystem_toolkit.py
planning_toolkit.py
subagent_toolkit.py
events.py
otel_manager.py
pipeline/
__init__.py
manager.py
step.py
steps.py
policy_manager.py
tool_policy_manager.py
cache/
__init__.py
cache_manager.py
canvas/
__init__.py
canvas.py
chat/
__init__.py
chat.py
cost_calculator.py
message.py
schemas.py
session_manager.py
cli/
__init__.py
commands/
__init__.py
add/
__init__.py
command.py
init/
__init__.py
command.py
install/
__init__.py
command.py
remove/
__init__.py
command.py
run/
__init__.py
command.py
shared/
__init__.py
config.py
dependencies.py
fastapi_imports.py
openapi.py
zip/
__init__.py
command.py
main.py
printer.py
context/
__init__.py
agent.py
default_prompt.py
sources.py
task.py
culture/
__init__.py
cultural_knowledge.py
culture.py
manager.py
db/
__init__.py
database.py
direct.py
embeddings/
__init__.py
azure_openai_provider.py
base.py
bedrock_provider.py
factory.py
fastembed_provider.py
gemini_provider.py
huggingface_provider.py
ollama_provider.py
openai_provider.py
eval/
__init__.py
_pl_helpers.py
accuracy.py
models.py
performance.py
reliability.py
exceptions.py
graph/
__init__.py
graph.py
graphv2/
__init__.py
cache.py
checkpoint.py
errors.py
primitives.py
state_graph.py
store.py
task.py
integrations/
__init__.py
asqav.py
langfuse.py
promptlayer.py
tracing.py
interfaces/
__init__.py
auth.py
base.py
discord/
__init__.py
discord.py
schemas.py
gmail/
__init__.py
gmail.py
schemas.py
mail/
__init__.py
mail.py
schemas.py
manager.py
schemas.py
settings.py
slack/
__init__.py
schemas.py
slack.py
telegram/
__init__.py
schemas.py
telegram.py
websocket_manager.py
whatsapp/
__init__.py
schemas.py
whatsapp.py
knowledge_base/
__init__.py
knowledge_base.py
loaders/
__init__.py
base.py
config.py
csv.py
docling.py
docx.py
factory.py
html.py
json.py
markdown.py
pdf.py
pdfplumber.py
pymupdf.py
text.py
xml.py
yaml.py
memory/
__init__.py
memory.py
messages/
__init__.py
_otel_messages.py
messages.py
models/
__init__.py
_thinking_part.py
anthropic.py
azure.py
bedrock.py
cerebras.py
cohere.py
github.py
google.py
grok.py
groq.py
heroku.py
huggingface.py
instrumented.py
litellm.py
lmstudio.py
mistral.py
model_registry.py
model_selector.py
moonshotai.py
nvidia.py
ollama.py
openai.py
openrouter.py
outlines.py
ovhcloud.py
sambanova.py
settings.py
together.py
vercel.py
vllm.py
... 936 moreFAQ
upsonic is a Claude Code plugin with 17 hand-picked skills for development work, indexed on Flowy. Install it with the command on its page. It includes analyze_current, benchmark, evaluate. 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 upsonic?
- Build Autonomous AI Agents in Python
- How do I install upsonic?
- Run these in Claude Code: npx -y skills add Upsonic/Upsonic --agent claude-code. Then prompt normally.
- Does upsonic 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 upsonic free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.