limbi 1.0.0

Omni-Agent Orchestration Platform — 86+ specialised AI agents, any LLM provider.

⚡ Limbi — Omni-Agent Orchestration Platform

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

pip install limbi

CLI Usage

# 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

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.

Author

Sayon Manna