Metadata-Version: 2.4
Name: agloom
Version: 0.1.73
Summary: Production agent framework on LangChain/LangGraph: nine execution patterns, persistent memory, skills, feedback, multi-level HITL, MCP, AGP protocol, runtime bridge, and observability hooks.
Project-URL: Homepage, https://github.com/HELLOMEDHIRA/agloom
Project-URL: Documentation, https://agloom.readthedocs.io
Project-URL: Repository, https://github.com/HELLOMEDHIRA/agloom
Project-URL: Issues, https://github.com/HELLOMEDHIRA/agloom/issues
License: Apache-2.0
License-File: LICENSE
Keywords: agent,agloom,ai,langchain,langgraph,llm,patterns,skills
Classifier: Development Status :: 4 - Beta
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: <3.13,>=3.12
Requires-Dist: agsuperbrain>=0.0.1
Requires-Dist: fastapi>=0.136.0
Requires-Dist: httpx>=0.28.1
Requires-Dist: langchain-mcp-adapters>=0.2.2
Requires-Dist: langchain>=1.3.0
Requires-Dist: langgraph-checkpoint-sqlite>=3.1.0
Requires-Dist: langgraph>=1.2.0
Requires-Dist: pyyaml>=6.0.3
Requires-Dist: qdrant-client>=1.18.0
Requires-Dist: sse-starlette>=3.4.4
Requires-Dist: tiktoken>=0.12.0
Requires-Dist: tomli>=2.4.1
Requires-Dist: uvicorn[standard]>=0.46.0
Provides-Extra: anthropic
Requires-Dist: langchain-anthropic>=1.4.3; extra == 'anthropic'
Provides-Extra: aws
Requires-Dist: langchain-aws>=1.4.6; extra == 'aws'
Provides-Extra: azure-ai
Requires-Dist: langchain-azure-ai>=1.2.3; extra == 'azure-ai'
Provides-Extra: cerebras
Requires-Dist: langchain-cerebras>=0.8.2; extra == 'cerebras'
Provides-Extra: cohere
Requires-Dist: langchain-cohere>=0.5.1; extra == 'cohere'
Provides-Extra: community
Requires-Dist: langchain-community>=0.4.1; extra == 'community'
Provides-Extra: deepseek
Requires-Dist: langchain-deepseek>=1.0.1; extra == 'deepseek'
Provides-Extra: docs
Requires-Dist: mkdocs-gen-files>=0.6.1; extra == 'docs'
Requires-Dist: mkdocs-literate-nav>=0.6.3; extra == 'docs'
Requires-Dist: mkdocs-material>=9.7.6; extra == 'docs'
Requires-Dist: mkdocs>=1.6.1; extra == 'docs'
Requires-Dist: mkdocstrings[python]>=1.0.4; extra == 'docs'
Provides-Extra: fireworks
Requires-Dist: langchain-fireworks>=1.3.1; extra == 'fireworks'
Provides-Extra: google-genai
Requires-Dist: langchain-google-genai<5,>=4.2.2; extra == 'google-genai'
Provides-Extra: google-vertexai
Requires-Dist: langchain-google-vertexai>=3.2.3; extra == 'google-vertexai'
Provides-Extra: groq
Requires-Dist: langchain-groq>=1.1.2; extra == 'groq'
Provides-Extra: huggingface
Requires-Dist: langchain-huggingface>=1.2.2; extra == 'huggingface'
Provides-Extra: ibm
Requires-Dist: langchain-ibm>=1.0.8; extra == 'ibm'
Provides-Extra: litellm
Requires-Dist: langchain-litellm>=0.6.4; extra == 'litellm'
Provides-Extra: memory
Requires-Dist: langchain-huggingface>=1.2.2; extra == 'memory'
Requires-Dist: sentence-transformers>=5.5.0; extra == 'memory'
Provides-Extra: mistralai
Requires-Dist: langchain-mistralai>=1.1.4; extra == 'mistralai'
Provides-Extra: nvidia
Requires-Dist: langchain-nvidia-ai-endpoints>=1.2.1; extra == 'nvidia'
Provides-Extra: ollama
Requires-Dist: langchain-ollama>=1.1.0; extra == 'ollama'
Provides-Extra: openai
Requires-Dist: langchain-openai>=1.2.1; extra == 'openai'
Provides-Extra: openrouter
Requires-Dist: langchain-openrouter>=0.2.3; extra == 'openrouter'
Provides-Extra: otel
Requires-Dist: opentelemetry-api>=1.27.0; extra == 'otel'
Requires-Dist: opentelemetry-exporter-otlp-proto-http>=1.27.0; extra == 'otel'
Requires-Dist: opentelemetry-sdk>=1.27.0; extra == 'otel'
Provides-Extra: perplexity
Requires-Dist: langchain-perplexity>=1.2.0; extra == 'perplexity'
Provides-Extra: readability
Requires-Dist: trafilatura>=2.0.0; extra == 'readability'
Provides-Extra: sambanova
Requires-Dist: langchain-sambanova>=1.1.0; extra == 'sambanova'
Provides-Extra: snowflake
Requires-Dist: langchain-snowflake>=0.2.3; extra == 'snowflake'
Provides-Extra: superbrain
Requires-Dist: agsuperbrain>=0.0.1; extra == 'superbrain'
Provides-Extra: together
Requires-Dist: langchain-together>=0.4.0; extra == 'together'
Provides-Extra: upstage
Requires-Dist: langchain-upstage>=0.7.7; extra == 'upstage'
Provides-Extra: ws
Requires-Dist: websockets>=12.0; extra == 'ws'
Provides-Extra: xai
Requires-Dist: langchain-xai>=1.2.2; extra == 'xai'
Description-Content-Type: text/markdown

<div align="center">

<img src="https://raw.githubusercontent.com/HELLOMEDHIRA/medhira/main/assets/medhira-logo.png" width="140" alt="agloom">

<br>

# agloom

**Build agents that route themselves.**  
One familiar API — classification, memory, streaming, guardrails, and learning included.

Nine execution patterns. Auto-selected per task. Skills improve over time.

<br>

[![PyPI version](https://img.shields.io/pypi/v/agloom)](https://pypi.org/project/agloom/)
[![Python 3.12](https://img.shields.io/pypi/pyversions/agloom)](https://pypi.org/project/agloom/)
[![License](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
[![Docs](https://readthedocs.org/projects/agloom/badge/?version=latest)](https://agloom.readthedocs.io)

**[Documentation](https://agloom.readthedocs.io)** · **[Quick Start](https://agloom.readthedocs.io/_packages/agloom/getting-started/quickstart/)** · [PyPI](https://pypi.org/project/agloom/) · [Examples](https://github.com/HELLOMEDHIRA/agloom/tree/main/agloom/examples) · [Issues](https://github.com/HELLOMEDHIRA/agloom/issues)

</div>

<br>

## Start here

**agloom** is a Python framework for production-minded agents on **LangChain / LangGraph**. You describe the model and tools; agloom picks how to run the task (single-shot, ReAct, supervisor-style delegation, pipelines, and more), tracks steps and tokens, and can learn reusable **skills** from what worked.

If you already use LangChain’s agent APIs, think of **`create_agent`** as your main entrypoint — with orchestration, memory, streaming, and safety knobs in one place.

### Install

```bash
pip install agloom
# optional extras, e.g. Groq:
pip install agloom[groq]
```

### Your first agent

```python
import asyncio
from langchain_groq import ChatGroq
from agloom import create_agent

async def main():
    llm = ChatGroq(model="meta-llama/llama-4-scout-17b-16e-instruct")
    agent = await create_agent(model=llm, name="my-agent")
    result = await agent.ainvoke("What causes auroras?")
    print(result.output)

asyncio.run(main())
```

`create_agent` is **async** (use `await`). From synchronous code, use **`create_agent_sync`**.

**Next steps:** [Why agloom?](https://agloom.readthedocs.io/_packages/agloom/getting-started/why-agloom/) · [Patterns explained](https://agloom.readthedocs.io/_packages/agloom/concepts/patterns/) · [All parameters](https://agloom.readthedocs.io/_packages/agloom/configuration/parameters/)

<br>

## What you get (in plain language)

| You want to…      | agloom helps by…                                                        |
| ----------------- | ----------------------------------------------------------------------- |
| Ship faster       | Picking a strategy per query instead of hand-writing routers and graphs |
| Keep context      | Session memory by default; optional long-term memory and skills         |
| Show progress     | Token streaming plus structured events for “thinking” / tool UIs        |
| Stay safe         | Human-in-the-loop levels, timeouts, retries, rate limits — configurable |
| Improve over time | Skill library and feedback hooks so behavior compounds                  |

For the full feature tour, see **[What you get](https://agloom.readthedocs.io/_packages/agloom/getting-started/why-agloom/)** in the docs — the README stays short on purpose.

<br>

## agloom CLI & web workspace

- **Terminal:** the **agloom CLI** (npm `agloom-cli`, repo **`agloom_cli/`**) is the terminal client — **React**-based UI. From that folder: `npm install` → `npm run build` → `npm start`. It talks to **`agloom-runtime`** over AGP (stdio by default). [CLI quick start](agloom_cli/docs/index.md)
- **Browser:** **`agloom_web/`** is the Vite workspace for sessions and observability — same idea, run commands inside that folder.

PyPI’s **`agloom`** package includes the library and **`agloom-runtime`**. The **`agloom`** command prints a short pointer to the **agloom CLI** (repo folder `agloom_cli/`) for backwards compatibility.

<br>

## Learn more (documentation hub)

| Guide                                                                                     | What it’s for                             |
| ----------------------------------------------------------------------------------------- | ----------------------------------------- |
| [Quick Start](https://agloom.readthedocs.io/_packages/agloom/getting-started/quickstart/) | Smallest path to a running agent          |
| [Execution patterns](https://agloom.readthedocs.io/_packages/agloom/concepts/patterns/)   | How routing works (conceptual + diagrams) |
| [Streaming & events](https://agloom.readthedocs.io/_packages/agloom/features/streaming/)  | Responsive UI patterns                    |
| [Production](https://agloom.readthedocs.io/_packages/agloom/guides/production/)           | Deploying, testing, operating             |
| [Errors & fixes](https://agloom.readthedocs.io/_packages/agloom/configuration/errors/)    | When something goes wrong                 |

<br>

## Requirements

- **Python** 3.12.x (see `pyproject.toml` on GitHub for the exact pin)
- **Node.js** ≥ 24.15.0 — only if you hack on **`agloom_cli/`** or **`agloom_web/`**
- An **LLM API key** (Groq, OpenAI, NVIDIA, Hugging Face, or another LangChain-compatible provider)

<br>

## Contributing & license

Contributions welcome — see **[CONTRIBUTING.md](CONTRIBUTING.md)**.

Licensed under **[Apache 2.0](LICENSE)**.

<br>

<div align="center">

<img src="https://raw.githubusercontent.com/HELLOMEDHIRA/medhira/main/assets/medhira-logo.png" width="80" alt="agloom">

**agloom** is built by **[MEDHIRA](https://github.com/HELLOMEDHIRA)**

[hello.medhira@gmail.com](mailto:hello.medhira@gmail.com) · [GitHub](https://github.com/HELLOMEDHIRA) · [PyPI](https://pypi.org/user/HELLOMEDHIRA/)

<sub>Founded by [S Muni Harish](mailto:samamuniharish@gmail.com)</sub>

</div>
