Metadata-Version: 2.4
Name: limbi
Version: 1.0.0
Summary: Omni-Agent Orchestration Platform — 86+ specialised AI agents, any LLM provider.
Author: Sayon Manna
License: Apache-2.0
Project-URL: Homepage, https://github.com/sayonmanna/limbi
Project-URL: Repository, https://github.com/sayonmanna/limbi
Keywords: ai,agents,orchestrator,llm,multi-agent,devops,automation,cli
Classifier: Development Status :: 4 - Beta
Classifier: Environment :: Console
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Requires-Python: >=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: click>=8.0
Requires-Dist: rich>=13.0
Requires-Dist: langchain-core>=0.3
Requires-Dist: langchain-ollama>=0.2
Requires-Dist: python-dotenv>=1.0
Provides-Extra: openai
Requires-Dist: langchain-openai>=0.2; extra == "openai"
Provides-Extra: anthropic
Requires-Dist: langchain-anthropic>=0.2; extra == "anthropic"
Provides-Extra: google
Requires-Dist: langchain-google-genai>=2.0; extra == "google"
Provides-Extra: groq
Requires-Dist: langchain-groq>=0.2; extra == "groq"
Provides-Extra: mistral
Requires-Dist: langchain-mistralai>=0.2; extra == "mistral"
Provides-Extra: cohere
Requires-Dist: langchain-cohere>=0.3; extra == "cohere"
Provides-Extra: together
Requires-Dist: langchain-openai>=0.2; extra == "together"
Provides-Extra: azure
Requires-Dist: langchain-openai>=0.2; extra == "azure"
Provides-Extra: rag
Requires-Dist: chromadb>=0.5; extra == "rag"
Provides-Extra: aws
Requires-Dist: boto3>=1.34; extra == "aws"
Provides-Extra: server
Requires-Dist: fastapi>=0.115; extra == "server"
Requires-Dist: uvicorn>=0.30; extra == "server"
Requires-Dist: gradio>=4.0; extra == "server"
Requires-Dist: httpx>=0.27; extra == "server"
Requires-Dist: huggingface-hub>=0.24; extra == "server"
Provides-Extra: all
Requires-Dist: limbi[anthropic,aws,cohere,google,groq,mistral,openai,rag,server]; extra == "all"
Dynamic: license-file
Dynamic: requires-python

# ⚡ Limbi — Omni-Agent Orchestration Platform

[![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue.svg)](https://www.python.org/downloads/)
[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-green.svg)](https://opensource.org/licenses/Apache-2.0)

**87 specialised AI agents. Any LLM provider. One command.**

Limbi is a pip-installable multi-agent orchestrator that connects to any LLM
(Ollama, OpenAI, Anthropic, Google, Groq, Mistral, Azure, Cohere, Together)
and delegates tasks to 87+ purpose-built agents covering DevOps, cloud,
security, analytics, CI/CD, compliance, and more.

---

## Quick Start

```bash
pip install limbi
```

### CLI Usage

```bash
# One-shot prompt
limbi "deploy main branch to staging and create a Jira ticket"

# With a specific provider & model
limbi --provider openai --model gpt-4o "review this code for security issues"
limbi -p anthropic -m claude-sonnet-4-20250514 "plan a database migration"
limbi -p groq -m llama-3.1-70b-versatile "explain kubernetes pods"

# Interactive REPL mode
limbi

# Info commands
limbi --list-agents       # show all 87 agents
limbi --list-providers    # show supported LLM providers
```

### Python API

```python
import asyncio
from limbi import Orchestrator, list_agents, get_llm_provider

# See all agents
print(list_agents())  # → 87 agents, 410 actions

# Chat with the orchestrator
orch = Orchestrator()
result = asyncio.run(orch.chat("deploy to staging"))
print(result["conversation_text"])
```

---

## Supported LLM Providers

| Provider | Install | Env Vars |
|----------|---------|----------|
| Ollama (default) | `pip install limbi` | `LLM_PROVIDER=ollama` |
| OpenAI | `pip install limbi[openai]` | `LLM_PROVIDER=openai LLM_API_KEY=sk-...` |
| Anthropic | `pip install limbi[anthropic]` | `LLM_PROVIDER=anthropic LLM_API_KEY=sk-...` |
| Google Gemini | `pip install limbi[google]` | `LLM_PROVIDER=google LLM_API_KEY=...` |
| Groq | `pip install limbi[groq]` | `LLM_PROVIDER=groq LLM_API_KEY=gsk_...` |
| Mistral | `pip install limbi[mistral]` | `LLM_PROVIDER=mistral LLM_API_KEY=...` |
| Azure OpenAI | `pip install limbi[azure]` | `LLM_PROVIDER=azure LLM_API_KEY=...` |
| Cohere | `pip install limbi[cohere]` | `LLM_PROVIDER=cohere LLM_API_KEY=...` |
| Together AI | `pip install limbi[together]` | `LLM_PROVIDER=together LLM_API_KEY=...` |
| All providers | `pip install limbi[all]` | — |

---

## Agent Categories (87 agents)

| Category | Count | Examples |
|----------|-------|---------|
| ☁️ Cloud & Infrastructure | 5 | AWS, GCP, Azure, Kubernetes, API Gateway |
| 🔄 DevOps & SRE | 5 | CI/CD, Incident, SRE, Performance, DevOps |
| 🛠️ Engineering | 8 | Code, Git, Database, Testing, Migration, File |
| 🔒 Security & Compliance | 3 | Security, Compliance, Policy |
| 📊 Analytics & NLP | 3 | Analytics, NLP, Reporting |
| 🤖 Cognitive | 8 | Planner, Critic, React, Router, Memory, Swarm |
| 💰 Business | 6 | Finance, Sales, Payments, Cost, Procurement |
| 👥 People & Process | 5 | HR, Recruiting, Onboarding, PM, Scheduling |
| 🏥 Verticals | 12 | Healthcare, Education, Legal, Real Estate, ... |
| 🧠 Context Memory | 1 | Shared inter-agent memory bus |
| 📝 Documentation | 2 | Docs generation, Reporting |
| 🌱 Sustainability | 2 | Energy, ESG |
| ⚙️ Platform | 8 | Auth, Workflow, Integration, Feature Flags, ... |

---

## Shared Context Memory

Limbi includes a **context memory bus** that automatically shares execution
results between agents. When the security agent finds vulnerabilities, the
devops agent already knows about them:

```
Security Agent → [shared memory] → DevOps Agent
    "3 CVEs found"     auto-published     "block deploy"
```

No manual wiring needed — the orchestrator handles it.

---

## Configuration

| Variable | Default | Description |
|----------|---------|-------------|
| `LLM_PROVIDER` | `ollama` | LLM provider to use |
| `LLM_MODEL` | `llama3.2:3b` | Model name |
| `LLM_API_KEY` | — | API key for hosted providers |
| `LLM_BASE_URL` | `http://localhost:11434` | Provider base URL |
| `LLM_TEMPERATURE` | `0.3` | Sampling temperature |
| `LLM_MAX_TOKENS` | `4096` | Max output tokens |

---

## License

Apache 2.0 — see [LICENSE](LICENSE).

## Author

**Sayon Manna**
