PraisonAI

PraisonAI 🦞 — **Hire a 24/7 AI Workforce.** Stop writing boilerplate and start shipping autonomous, self-improving agents that research, plan, and execute tasks across your apps. From one agent to an entire organization, deployed in 5 lines of code.
  
  
---
🎯 Use Cases
AI agents solving real-world problems across industries:
| Use Case | Description |
|----------|-------------|
| 🔍 **Research & Analysis** | Conduct deep research, gather information, and generate insights from multiple sources automatically |
| 💻 **Code Generation** | Write, debug, and refactor code with AI agents that understand your codebase and requirements |
| ✍️ **Content Creation** | Generate blog posts, documentation, marketing copy, and technical writing with multi-agent teams |
| 📊 **Data Pipelines** | Extract, transform, and analyze data from APIs, databases, and web sources automatically |
| 🤖 **Customer Support** | Deploy 24/7 support bots on Telegram, Discord, Slack with memory and knowledge-backed responses |
| ⚙️ **Workflow Automation** | Automate multi-step business processes with agents that hand off tasks, verify results, and self-correct |
---
🚀 Meet your first Agent (Under 1 Minute)
1. Install the lightweight core SDK:
2. Run your first autonomous agent:
---
🧬 The Five-Layer Agent Stack
Most frameworks hand you one or two layers and leave the rest as homework. PraisonAI covers **all five** — plus the outer layer that decides *where* your agent actually runs.
Each layer wraps the one inside it. When an agent misbehaves, the layer tells you where to look.
| Layer | The question it answers | PraisonAI |
|:--|:--|:--|
| **1 · Prompt** | Did I say it clearly? | instructions=, role/goal/backstory, output=, templates= |
| **2 · Context** | Is the right thing in the window? | memory=, knowledge=, context=, handoff ContextPolicy |
| **3 · Harness** | Can it act, and be checked? | tools=, MCP(), guardrails=, approval=, hooks=, sandbox= |
| **4 · Loop** | When do we stop? | execution=ExecutionConfig(...), reflection=, autonomy=, doom-loop detection |
| **5 · Graph** | Who runs when, and who checks whom? | AgentFlow, route(), parallel(), loop(), repeat() |
| **⬡ Managed** | *Where does it actually run?* | tools_run_on="docker" — one shared sandbox for the tools, or run_on="anthropic" for the whole agent |
Layer 1 · Prompt — *Did I say it clearly?*
Role, instructions, examples, output format.
Layer 2 · Context — *Is the right thing in the window?*
Write, select, compress, isolate — the four context operations, one parameter each.
> **Isolate** is handoffs=[specialist] — a sub-agent inherits the last few messages and the intersection of your tools, not your whole transcript. 📖 Handoffs
Layer 3 · Harness — *Can it act, and be checked?*
*Agent = Model + Harness.* Tool dispatch, plus the guides that steer before acting and the sensors that observe after.
Layer 4 · Loop — *When do we stop?*
Hard iteration caps, budget ceilings, no-progress detection and completion checks — every brake is explicit.
> **Doom-loop detection is on by default.** Repeated identical tool calls and A→B→A→B oscillation get caught — while a poller whose output keeps changing does not. 📖 Doom Loop Detection
Layer 5 · Graph — *Who runs when, and who checks whom?*
Topology as a versionable artifact: prompt chaining, routing, parallelisation, orchestrator-worker.
> The same graph is expressible in YAML with no Python at all. 📖 AgentFlow
⬡ Outside the stack: Managed Agents — *Where does it actually run?*
The harness is commoditising; **where** the agent executes is the next multiplier. Rather than burning your laptop's CPU, hand an agent a short-lived cloud sandbox — repo, tools and tests run there.
The simplest way in is tools_run_on= — one whole team or workflow shares **one** sandbox, so a file written by step 1 is there for step 2. Thinking stays on your machine:
Same thing with no Python at all:
For a single agent, two words cover it — and they answer different questions:
Ask any object where it runs, and it will tell you:
Naming a place that cannot do the job is a typo, not a preference, so it says so:
To run one block of code somewhere else, name the place on that call:
See what is running and reclaim strays:
Sandboxes shut themselves down when idle (auto_shutdown, idle_timeout_s), and a post-setup snapshot is reused so the next run skips the image pull and dependency install. Commit a .praisonai/environment.yaml and the environment travels with the repo.