Private AI that earns trust one task at a time.
PraisonAI runs AI agents on your own computers, even fully offline, so private data never has to leave the building.
- For highly regulated teams (early access): each task moves to your own AI only after it passes a test. If quality slips, it moves back automatically, and every step is recorded for regulators. How it works
- For everyone else: a free, open-source Python agent framework. With a local model you need no API key and pay no cloud bill, and your files stay yours.
2M+ downloads · 9.3K stars · 600+ releases in the last year · 80+ contributors · Python
pip install praisonaiOnly need the Python library? pip install praisonaiagents installs just the lightweight core.
PraisonAI is still a general-purpose, open-source agent framework, and everything works as before: the same packages, imports, commands and examples. Go straight to what you came for:
- Agents and multi-agent teams: Agents · Handoffs
- Workflows: AgentFlow: route, parallel, loop, repeat
- Memory and knowledge: Memory · Knowledge · RAG
- Tools and MCP: Tools · MCP
- Bots (Telegram, Discord, Slack, WhatsApp): Bot CLI · Bot gateway
- Terminal CLI:
praisonai code·praisonai run·praisonai chat· CLI reference - Training and fine-tuning: PraisonAI Train
- Browser automation: Browser agent · Browser CLI
- Sandboxes: Sandboxed code execution
- Deploy: Deploy guide
- Dashboard and UI: Claw dashboard · Chat UI
- YAML, no code: YAML agents · YAML reference
- JavaScript and TypeScript: JavaScript SDK
- Desktop app: PraisonAI Desktop · Downloads
- Everything else: the full feature reference further down this page
Set a key for any supported provider (OpenAI shown here), or skip the key and use a local model as in the next section.
export OPENAI_API_KEY="your-api-key"from praisonaiagents import Agent
agent = Agent(instructions="You are a helpful assistant.")
print(agent.start("In two sentences, why do some companies keep their data on their own computers?"))Run the same agent on a model on your own computer with Ollama. You need no API key, and your prompts and answers stay on the machine.
Install the package and pull the model while you still have internet; after that, the agent runs with no network at all. If you installed only the core library, use pip install "praisonaiagents[llm]", which adds the local-model support.
# Start Ollama first (the app, or "ollama serve" in another terminal)
ollama pull llama3.2
export DO_NOT_TRACK=true # keeps telemetry off (PraisonAI sends none unless you turn it on)from praisonaiagents import Agent
agent = Agent(instructions="You are a helpful assistant.", model="ollama/llama3.2")
print(agent.start("Why is the sky blue?"))If Ollama runs on another computer on your network, pass base_url (or set OLLAMA_API_BASE):
agent = Agent(instructions="...", model="ollama/llama3.2", base_url="http://192.168.1.10:11434")vLLM and LM Studio work the same way: use hosted_vllm/ (vLLM) or lm_studio/ with your server's base_url. More in the Ollama guide and Models docs.
- Watch: records how each task is done today.
- Test: turns that real work into tests.
- Hand over: a task moves to your own AI only when it passes.
- Roll back: if quality drops, the task moves back automatically.
- Record: every handover leaves a record your regulator can check.
Highly regulated teams, such as banks, insurers and hospitals, want AI but can't send customer data to outside models. From 6 January 2027, OpenAI also takes no new self-serve fine-tuning jobs (notice), so teams that customise models need models they own. The handover lets these teams move work to AI they own, one task at a time, with a record that shows why each step was trusted.
It is built on parts of this framework that are live today: tracing, evaluation, fine-tuning, model routing and local models. The handover itself is in early access, and we are taking on our first design partners. To take part, see praison.ai/enterprise.
- Agents and multi-agent teams: Agents · Handoffs · Workflows
- Memory: Memory · Knowledge and RAG · Sessions
- Tools and MCP: Tools · MCP
- Guardrails and approval: Guardrails · Human approval · Policy engine
- Tracing and evaluation: Tracing · Telemetry · Langfuse · Evaluation
- Your choice of model: Models · Model router
- Fine-tuning: PraisonAI Train
- Deploy: Deploy guide
npm install praisonaiThe TypeScript and JavaScript SDK has its own guide at praison.ai/docs/js. A short example is in Using JavaScript Code below.
- Who: Praison AI Limited in Cambridge, UK, building PraisonAI since September 2023. Co-founders Mervin Praison (CEO), Leebana Smith (COO) and Karthick Subramanian (CBO). About us
- What we're building: the task handover above, as a self-hosted product on top of this framework. It is in early access, and we are taking on our first design partners.
- Why now: highly regulated teams want AI but can't send customer data to outside models, and from 6 January 2027 OpenAI takes no new self-serve fine-tuning jobs.
- How it fits together: the framework stays free and MIT-licensed, and brings developers in. Regulated teams license the handover to run inside their own walls.
- Traction: every number at the top of this page is public and linked to its source.
- Get in touch: design partners, investors and press: [email protected] or praison.ai/enterprise
- Documentation: praison.ai/docs
- Questions and bugs: Discussions · Issues
- Contributing: Contributing guide
- Videos and news: YouTube · X · LinkedIn
- Desktop app: macOS, Windows and Linux builds are on the latest release
- Licence: MIT
Everything below is the full reference that was on this page before. Nothing has been removed; the longest parts are folded, so click a heading's summary to open it.
One-line installer:
curl -fsSL https://praison.ai/install.sh | bashThe full praisonai package, with the CLI, bots, dashboard and integrations:
██████╗ ██████╗ █████╗ ██╗███████╗ ██████╗ ███╗ ██╗ █████╗ ██╗
██╔══██╗██╔══██╗██╔══██╗██║██╔════╝██╔═══██╗████╗ ██║ ██╔══██╗██║
██████╔╝██████╔╝███████║██║███████╗██║ ██║██╔██╗ ██║ ███████║██║
██╔═══╝ ██╔══██╗██╔══██║██║╚════██║██║ ██║██║╚██╗██║ ██╔══██║██║
██║ ██║ ██║██║ ██║██║███████║╚██████╔╝██║ ╚████║ ██║ ██║██║
╚═╝ ╚═╝ ╚═╝╚═╝ ╚═╝╚═╝╚══════╝ ╚═════╝ ╚═╝ ╚═══╝ ╚═╝ ╚═╝╚═╝
pip install praisonai
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 |
- Install the lightweight core SDK:
pip install praisonaiagents
export OPENAI_API_KEY="your-api-key"- Run your first autonomous agent:
from praisonaiagents import Agent
# Give your agent a goal, and watch it work.
agent = Agent(instructions="You are a senior data analyst.")
agent.start("Analyze the top 3 tech trends of 2026 and format as a markdown table.")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.
Show the five layers, examples and Managed Agents
┌─────────────────────────────────────────────────────────────────┐
│ ⬡ MANAGED AGENTS — Where does it actually run? │
│ ┌─────────────────────────────────────────────────────────────┐ │
│ │ 5 · GRAPH — Who runs when, and who checks whom? │ │
│ │ ┌─────────────────────────────────────────────────────────┐ │ │
│ │ │ 4 · LOOP — When do we stop? │ │ │
│ │ │ ┌─────────────────────────────────────────────────────┐ │ │ │
│ │ │ │ 3 · HARNESS — Can it act, and be checked? │ │ │ │
│ │ │ │ ┌─────────────────────────────────────────────────┐ │ │ │ │
│ │ │ │ │ 2 · CONTEXT — Is the right thing in the window? │ │ │ │ │
│ │ │ │ │ ┌─────────────────────────────────────────────┐ │ │ │ │ │
│ │ │ │ │ │ 1 · PROMPT — Did I say it clearly? │ │ │ │ │ │
│ │ │ │ │ └─────────────────────────────────────────────┘ │ │ │ │ │
│ │ │ │ └─────────────────────────────────────────────────┘ │ │ │ │
│ │ │ └─────────────────────────────────────────────────────┘ │ │ │
│ │ └─────────────────────────────────────────────────────────┘ │ │
│ └─────────────────────────────────────────────────────────────┘ │
└─────────────────────────────────────────────────────────────────┘
| 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 |
Role, instructions, examples, output format.
from praisonaiagents import Agent
agent = Agent(
role="Senior Data Analyst",
goal="Turn raw numbers into decisions",
output="verbose", # markdown-formatted output
)
agent.start("Summarise Q3 revenue trends")Write, select, compress, isolate — the four context operations, one parameter each.
from praisonaiagents import Agent
agent = Agent(
instructions="You are a support engineer.",
memory={"user_id": "u-42"}, # write — persists across runs (needs a user_id)
knowledge=["docs/"], # select — retrieves only what's relevant
context="summarize", # compress — auto-compacts before the limit
)Isolate is
handoffs=[specialist]— a sub-agent inherits the last few messages and the intersection of your tools, not your whole transcript. 📖 Handoffs
Agent = Model + Harness. Tool dispatch, plus the guides that steer before acting and the sensors that observe after.
from praisonaiagents import Agent, MCP, tool
@tool
def deploy(env: str) -> str:
"""Deploy the current build to an environment."""
return f"Deployed to {env}"
agent = Agent(
name="ReleaseEngineer",
instructions="You are a release engineer.",
tools=[deploy, MCP("npx -y @modelcontextprotocol/server-filesystem /tmp")],
approval=True, # guide — human gate before risky tools run
)
agent.start("Deploy to staging, then list the files you can read")Hard iteration caps, budget ceilings, no-progress detection and completion checks — every brake is explicit.
from praisonaiagents import Agent, ExecutionConfig
agent = Agent(
instructions="Fix the failing tests.",
execution=ExecutionConfig(max_iter=30, max_budget=0.50, on_budget_exceeded="stop"),
autonomy=True, # required to drive the loop with run_autonomous()
)
result = agent.run_autonomous("Refactor the auth module", max_iterations=5)
print(result.completion_reason)
# goal | no_tool_calls | max_iterations | timeout | doom_loop | needs_help | error
# (with on_budget_exceeded="stop", hitting the cap raises BudgetExceededError,
# surfaced here as completion_reason="error")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
Topology as a versionable artifact: prompt chaining, routing, parallelisation, orchestrator-worker.
from praisonaiagents import AgentFlow
from praisonaiagents.workflows import route, parallel, repeat
flow = AgentFlow(steps=[
classifier,
route({"bug": [bug_agent], "feature": [feature_agent], "default": [triage]}),
parallel([reviewer, tester]), # fan out, join automatically
repeat(editor, until=lambda ctx: "approved" in ctx.previous_result.lower(),
max_iterations=3), # evaluator–optimizer
])
flow.run("Ticket #123: login fails on Safari")The same graph is expressible in YAML with no Python at all. 📖 AgentFlow
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.
pip install praisonaiThe 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:
from praisonaiagents import Agent, AgentFlow
writer = Agent(name="Writer", instructions="You write files.")
reader = Agent(name="Reader", instructions="You read files.")
flow = AgentFlow(tools_run_on="docker", steps=[writer, reader]) # or e2b | modal | daytona | flyio
flow.run("Write 'hello' to /workspace/note.txt, then read it back")Same thing with no Python at all:
name: remote-demo
tools_run_on: docker # every step shares one sandbox
agents:
writer: {role: Writer, goal: Write files}
reader: {role: Reader, goal: Read files}
steps:
- agent: writer
action: "Write 'hello' to /workspace/note.txt"
- agent: reader
action: "Read /workspace/note.txt"For a single agent, two words cover it — and they answer different questions:
from praisonaiagents import Agent
# A. Only the TOOLS move. Thinking stays on your machine.
agent = Agent(name="builder", instructions="You build things.",
tools_run_on="docker") # docker | e2b | modal | daytona | flyio
# tenki | sandlock | ssh | novita | subprocess
# B. The WHOLE agent moves — model calls, loop and tools
agent = Agent(name="teacher", instructions="You teach.", run_on="anthropic") # hosted
agent = Agent(name="builder", instructions="You build.", run_on="docker") # self-hosted
agent.start("Write a Python script that prints the first 10 primes, then run it")Ask any object where it runs, and it will tell you:
>>> Agent(name="builder", instructions="x", tools_run_on="docker")
Agent(name='builder', thinks_on='this machine', tools_run_on='a Docker container')
>>> agent.where_does_it_run()
Thinking (the AI model calls) happens on this machine.
Tools run on a Docker container.
Your own tools (check_db) still run on this machine -- only shell, file and
code tools move. They read and write this machine's files.Naming a place that cannot do the job is a typo, not a preference, so it says so:
>>> Agent(name="x", instructions="i", run_on="e2b")
TypeError: Agent(run_on='e2b') is not valid: run_on= places the whole agent
-- model calls, loop and tools -- on a managed runtime, and 'e2b' runs
commands but cannot host an agent loop.
To run only the tools there: Agent(tools_run_on='e2b')To run one block of code somewhere else, name the place on that call:
agent.execute_code_sync("print(6 * 7)", run_in="sandlock") # kernel-enforcedSee what is running and reclaim strays:
praisonai managed ps # list running sandboxes
praisonai managed stop --all # reclaim themSandboxes 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.
📖 20 runnable examples · manage sessions with
praisonai managed sessions list <agent-id>orpraisonai managed sessions resume <session-id> "<prompt>"
Stack framing adapted from The Five-Layer Agent Stack and Agent Harnesses vs Orbs.
Start simple with the core SDK, or expand to full visual builders and dashboards when you're ready.
- Core SDK (
praisonaiagents): For pure Python development.pip install praisonaiagents - 💻 PraisonAI CLI (
praisonai): For terminal-based developers.pip install praisonai - 🦞 Claw Dashboard: Connect agents directly to Telegram, Slack, or Discord.
pip install "praisonai[claw]" - 🔗 Flow Visual Builder: Drag-and-drop workflow creation.
pip install "praisonai[flow]" - 🤖 PraisonAI UI: Clean chat interface.
pip install "praisonai[ui]"
npm install praisonaiPowered by 100+ LLMs (OpenAI, Anthropic, Gemini & local models).
View all 24 providers with examples
| Provider | Example |
|---|---|
| OpenAI | Example |
| Anthropic | Example |
| Google Gemini | Example |
| Ollama | Example |
| Groq | Example |
| DeepSeek | Example |
| xAI Grok | Example |
| Mistral | Example |
| Cohere | Example |
| Perplexity | Example |
| Fireworks | Example |
| Together AI | Example |
| OpenRouter | Example |
| HuggingFace | Example |
| Azure OpenAI | Example |
| AWS Bedrock | Example |
| Google Vertex | Example |
| Databricks | Example |
| Cloudflare | Example |
| AI21 | Example |
| Replicate | Example |
| SageMaker | Example |
| Moonshot | Example |
| vLLM | Example |
| Feature | How | |
|---|---|---|
| 🔌 | MCP Protocol — stdio, HTTP, WebSocket, SSE | tools=MCP("npx ...") |
| 🧠 | Planning Mode — plan → execute → reason | planning=True |
| 🔍 | Deep Research — multi-step autonomous research | Docs |
| 🤖 | External Agents — orchestrate Claude Code, Gemini CLI, Codex | Docs |
| 🔄 | Agent Handoffs — seamless conversation passing | handoffs=[other_agent] |
| 🛡️ | Guardrails — input/output validation | Docs |
| Web Search + Fetch — native browsing | web=True |
|
| 🪞 | Self Reflection — agent reviews its own output | Docs |
| 🔀 | Workflow Patterns — route, parallel, loop, repeat | Docs |
| 🧠 | Memory (zero deps) — works out of the box | memory=True |
View all 25 features
| Feature | How | |
|---|---|---|
| 💡 | Prompt Caching — reduce latency + cost | caching=True |
| 💾 | Sessions + Auto-Save — persistent state across restarts | auto_save="my-project" |
| 💭 | Thinking Budgets — control reasoning depth | agent.thinking_budget = 1024 |
| 📚 | RAG + Quality-Based RAG — auto quality scoring retrieval | Docs |
| 📊 | Model Router — auto-routes to cheapest capable model | Docs |
| 🧊 | Shadow Git Checkpoints — auto-rollback on failure | Docs |
| 📡 | A2A Protocol — agent-to-agent interop | Docs |
| 📏 | Context Compaction — never hit token limits | Docs |
| 📡 | Telemetry — OpenTelemetry traces, spans, metrics | Docs |
| 📜 | Policy Engine — declarative agent behavior control | Docs |
| 🔄 | Background Tasks — fire-and-forget agents | Docs |
| 🔁 | Doom Loop Detection — auto-recovery from stuck agents | Docs |
| 🕸️ | Graph Memory — Neo4j-style relationship tracking | Docs |
| 🏖️ | Sandbox Execution — isolated code execution | Docs |
| 🖥️ | Bot Gateway — multi-agent routing across channels | Docs |
Show Python examples: single agent, multi-agent, MCP, tools, databases, Claw, Langflow, UI
Unsure whether a result is a bug or model randomness? Check the SDK Behavior Matrix for
stream, memory prefetch, structured output, teams and AG-UI.
from praisonaiagents import Agent
agent = Agent(instructions="You are a helpful AI assistant")
agent.start("Write a movie script about a robot in Mars")from praisonaiagents import Agent, Agents
research_agent = Agent(instructions="Research about AI")
summarise_agent = Agent(instructions="Summarise research agent's findings")
agents = Agents(agents=[research_agent, summarise_agent])
agents.start()from praisonaiagents import Agent, MCP
# stdio - Local NPX/Python servers
agent = Agent(tools=MCP("npx @modelcontextprotocol/server-memory"))
# Streamable HTTP - Production servers
agent = Agent(tools=MCP("https://api.example.com/mcp"))
# WebSocket - Real-time bidirectional
agent = Agent(tools=MCP("wss://api.example.com/mcp", auth_token="token"))
# With environment variables
agent = Agent(
tools=MCP(
command="npx",
args=["-y", "@modelcontextprotocol/server-brave-search"],
env={"BRAVE_API_KEY": "your-key"}
)
)📖 Full MCP docs — stdio, HTTP, WebSocket, SSE transports
from praisonaiagents import Agent, tool
@tool
def search(query: str) -> str:
"""Search the web for information."""
return f"Results for: {query}"
@tool
def calculate(expression: str) -> float:
"""Safely evaluate a numeric arithmetic expression."""
import ast
import operator
# Define allowed operations
_OPS = {
ast.Add: operator.add,
ast.Sub: operator.sub,
ast.Mult: operator.mul,
ast.Div: operator.truediv,
ast.Pow: operator.pow,
ast.USub: operator.neg,
ast.UAdd: operator.pos,
}
def _safe_eval(node):
if isinstance(node, ast.Constant) and isinstance(node.value, (int, float)):
return node.value
elif isinstance(node, ast.BinOp) and type(node.op) in _OPS:
return _OPS[type(node.op)](_safe_eval(node.left), _safe_eval(node.right))
elif isinstance(node, ast.UnaryOp) and type(node.op) in _OPS:
return _OPS[type(node.op)](_safe_eval(node.operand))
else:
raise ValueError("Unsupported expression")
try:
return _safe_eval(ast.parse(expression, mode="eval").body)
except (ValueError, SyntaxError, TypeError, ZeroDivisionError, OverflowError):
raise ValueError("Invalid arithmetic expression")
agent = Agent(
instructions="You are a helpful assistant",
tools=[search, calculate]
)
agent.start("Search for AI news and calculate 15*4")
⚠️ Security Note: Never useeval(),exec(), orsubprocessin tool functions that process LLM-generated or user-supplied input. Always validate and sanitize inputs to prevent code injection attacks. 📖 Full tools docs — BaseTool, tool packages, 100+ built-in tools
from praisonaiagents import Agent, db
agent = Agent(
name="Assistant",
memory={
"db": db(database_url="postgresql://localhost/mydb"),
"session_id": "my-session",
},
)
agent.chat("Hello!") # Auto-persists messages, runs, traces📖 Full persistence docs — PostgreSQL, MySQL, SQLite, MongoDB, Redis, and 20+ more
Connect your AI agents to Telegram, Discord, Slack, WhatsApp and more — all from a single command.
pip install "praisonai[claw]"
praisonai clawCopy .env.example to .env and configure the following variables:
| Variable | Required | Description |
|---|---|---|
OPENAI_API_KEY |
Yes | OpenAI API key for all LLM calls |
TAVILY_API_KEY |
Yes (Claw) | Tavily key for the built-in web-search tool. Get one free at https://app.tavily.com |
Open http://localhost:8082 — the dashboard comes with 13 built-in pages: Chat, Agents, Memory, Knowledge, Channels, Guardrails, Cron, and more. Add messaging channels directly from the UI.
📖 Full Claw docs — platform tokens, CLI options, Docker, and YAML agent mode
Build multi-agent workflows visually with drag-and-drop components in Langflow.
pip install "praisonai[flow]"
praisonai flowOpen http://localhost:7861 — use the Agent and Agent Team components to create sequential or parallel workflows. Connect Chat Input → Agent Team → Chat Output for instant multi-agent pipelines.
📖 Full Flow docs — visual agent building, component reference, and deployment
Lightweight chat interface for your AI agents.
pip install "praisonai[ui]"
praisonai uiShow YAML examples
Create agents.yaml:
framework: praisonai
topic: "Write a blog post about AI"
agents:
researcher:
role: Research Analyst
goal: Research AI trends and gather information
instructions: "Find accurate information about AI trends"
writer:
role: Content Writer
goal: Write engaging blog posts
instructions: "Write clear, engaging content based on research"Run with:
praisonai agents.yamlThe agents automatically work together sequentially
Create two files in the same folder:
agents.yaml:
framework: praisonai
topic: "Calculate the sum of 25 and 15"
agents:
calculator_agent:
role: Calculator
goal: Perform calculations
instructions: "Use the add_numbers tool to help with calculations"
tools:
- add_numberstools.py:
def add_numbers(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 + bRun with:
praisonai agents.yaml💡 Tips:
- Use the function name (e.g.,
add_numbers) in the tools list, not the file name- Tools in
tools.pyare automatically discovered- The function's docstring helps the AI understand how to use it
| Category | Commands |
|---|---|
| Execution | praisonai, --auto, --interactive, --chat |
| Research | research, --query-rewrite, --deep-research |
| Planning | --planning, --planning-tools, --planning-reasoning |
| Workflows | workflow run, workflow list, workflow auto |
| Memory | memory show, memory add, memory search, memory clear |
| Knowledge | knowledge add, knowledge query, knowledge list |
| Sessions | session list, session resume, session delete |
| Tools | tools list, tools info, tools search |
| MCP | mcp list, mcp create, mcp enable |
| Development | commit, docs, checkpoint, hooks |
| Scheduling | schedule start, schedule list, schedule stop |
Show all features by category
🤖 Core Agents
| Feature | Code | Docs |
|---|---|---|
| Single Agent | Example | 📖 |
| Multi Agents | Example | 📖 |
| Auto Agents | Example | 📖 |
| Self Reflection AI Agents | Example | 📖 |
| Reasoning AI Agents | Example | 📖 |
| Multi Modal AI Agents | Example | 📖 |
🔄 Workflows
| Feature | Code | Docs |
|---|---|---|
| Simple Workflow | Example | 📖 |
| Workflow with Agents | Example | 📖 |
Agentic Routing (route()) |
Example | 📖 |
Parallel Execution (parallel()) |
Example | 📖 |
Loop over List/CSV (loop()) |
Example | 📖 |
Evaluator-Optimizer (repeat()) |
Example | 📖 |
| Conditional Steps | Example | 📖 |
| Workflow Branching | Example | 📖 |
| Workflow Early Stop | Example | 📖 |
| Workflow Checkpoints | Example | 📖 |
💻 Code & Development
| Feature | Code | Docs |
|---|---|---|
| Code Interpreter Agents | Example | 📖 |
| AI Code Editing Tools | Example | 📖 |
| External Agents (All) | Example | 📖 |
| Claude Code CLI | Example | 📖 |
| Gemini CLI | Example | 📖 |
| Codex CLI | Example | 📖 |
| Cursor CLI | Example | 📖 |
🧠 Memory & Knowledge
| Feature | Code | Docs |
|---|---|---|
| Memory (Short & Long Term) | Example | 📖 |
| File-Based Memory | Example | 📖 |
| Claude Memory Tool | Example | 📖 |
| Add Custom Knowledge | Example | 📖 |
| RAG Agents | Example | 📖 |
| Chat with PDF Agents | Example | 📖 |
| Data Readers (PDF, DOCX, etc.) | CLI | 📖 |
| Vector Store Selection | CLI | 📖 |
| Retrieval Strategies | CLI | 📖 |
| Rerankers | CLI | 📖 |
| Index Types (Vector/Keyword/Hybrid) | CLI | 📖 |
| Query Engines (Sub-Question, etc.) | CLI | 📖 |
🔬 Research & Intelligence
| Feature | Code | Docs |
|---|---|---|
| Deep Research Agents | Example | 📖 |
| Query Rewriter Agent | Example | 📖 |
| Native Web Search | Example | 📖 |
| Built-in Search Tools | Example | 📖 |
| Unified Web Search | Example | 📖 |
| Web Fetch (Anthropic) | Example | 📖 |
📋 Planning & Execution
| Feature | Code | Docs |
|---|---|---|
| Planning Mode | Example | 📖 |
| Planning Tools | Example | 📖 |
| Planning Reasoning | Example | 📖 |
| Prompt Chaining | Example | 📖 |
| Evaluator Optimiser | Example | 📖 |
| Orchestrator Workers | Example | 📖 |
👥 Specialized Agents
| Feature | Code | Docs |
|---|---|---|
| Data Analyst Agent | Example | 📖 |
| Finance Agent | Example | 📖 |
| Shopping Agent | Example | 📖 |
| Recommendation Agent | Example | 📖 |
| Wikipedia Agent | Example | 📖 |
| Programming Agent | Example | 📖 |
| Math Agents | Example | 📖 |
| Markdown Agent | Example | 📖 |
| Prompt Expander Agent | Example | 📖 |
🎨 Media & Multimodal
| Feature | Code | Docs |
|---|---|---|
| Image Generation Agent | Example | 📖 |
| Image to Text Agent | Example | 📖 |
| Video Agent | Example | 📖 |
| Camera Integration | Example | 📖 |
🔌 Protocols & Integration
| Feature | Code | Docs |
|---|---|---|
| MCP Transports | Example | 📖 |
| WebSocket MCP | Example | 📖 |
| MCP Security | Example | 📖 |
| MCP Resumability | Example | 📖 |
| MCP Config Management | Docs | 📖 |
| LangChain Integrated Agents | Example | 📖 |
🛡️ Safety & Control
| Feature | Code | Docs |
|---|---|---|
| Guardrails | Example | 📖 |
| Human Approval | Example | 📖 |
| Rules & Instructions | Docs | 📖 |
⚙️ Advanced Features
| Feature | Code | Docs |
|---|---|---|
| Async & Parallel Processing | Example | 📖 |
| Parallelisation | Example | 📖 |
| Repetitive Agents | Example | 📖 |
| Agent Handoffs | Example | 📖 |
| Stateful Agents | Example | 📖 |
| Autonomous Workflow | Example | 📖 |
| Structured Output Agents | Example | 📖 |
| Model Router | Example | 📖 |
| Prompt Caching | Example | 📖 |
| Fast Context | Example | 📖 |
🛠️ Tools & Configuration
| Feature | Code | Docs |
|---|---|---|
| 100+ Custom Tools | Example | 📖 |
| YAML Configuration | Example | 📖 |
| 100+ LLM Support | Example | 📖 |
| Callback Agents | Example | 📖 |
| Hooks | Example | 📖 |
| Middleware System | Example | 📖 |
| Configurable Model | Example | 📖 |
| Rate Limiter | Example | 📖 |
| Injected Tool State | Example | 📖 |
| Shadow Git Checkpoints | Example | 📖 |
| Background Tasks | Example | 📖 |
| Policy Engine | Example | 📖 |
| Thinking Budgets | Example | 📖 |
| Output Styles | Example | 📖 |
| Context Compaction | Example | 📖 |
📊 Monitoring & Management
| Feature | Code | Docs |
|---|---|---|
| Sessions Management | Example | 📖 |
| Auto-Save Sessions | Docs | 📖 |
| History in Context | Docs | 📖 |
| Telemetry | Example | 📖 |
| Langfuse Tracing | Docs | 📖 |
| Project Docs (.praison/docs/) | Docs | 📖 |
| AI Commit Messages | Docs | 📖 |
| @Mentions in Prompts | Docs | 📖 |
🖥️ CLI Features
| Feature | Code | Docs |
|---|---|---|
| Slash Commands | Example | 📖 |
| Autonomy Modes | Example | 📖 |
| Cost Tracking | Example | 📖 |
| Repository Map | Example | 📖 |
| Interactive TUI | Example | 📖 |
| Git Integration | Example | 📖 |
| Sandbox Execution | Example | 📖 |
| CLI Compare | Example | 📖 |
| Profile/Benchmark | Docs | 📖 |
| Auto Mode | Docs | 📖 |
| Init | Docs | 📖 |
| File Input | Docs | 📖 |
| Final Agent | Docs | 📖 |
| Max Tokens | Docs | 📖 |
npm install praisonai
export OPENAI_API_KEY=xxxxxxxxxxxxxxxxxxxxxxconst { Agent } = require('praisonai');
const agent = new Agent({ instructions: 'You are a helpful AI assistant' });
agent.start('Write a movie script about a robot in Mars');PraisonAI keeps framework overhead microsecond-class: creating an Agent (one tool, no LLM call) averaged 46 μs in our 2026-10-15 run, so per-agent setup is negligible next to model latency in multi-agent workloads.
| Performance Metric | PraisonAI | Measured |
|---|---|---|
| Avg Agent instantiation (1 tool, 1000 iterations) | 46 μs | 2026-10-15 · praisonaiagents 1.7.12 |
Methodology, comparisons and how to reproduce: benchmarks/BENCHMARK_RESULTS.md · docs
* export TAVILY_API_KEY=xxxxx
pip install "praisonai[langfuse]"
praisonai langfuse
Learn PraisonAI through our comprehensive video series:
View all 22 video tutorials
| Topic | Video |
|---|---|
| AI Agents with Self Reflection |  |
| Reasoning Data Generating Agent |  |
| AI Agents with Reasoning |  |
| Multimodal AI Agents |  |
| AI Agents Workflow |  |
| Async AI Agents |  |
| Mini AI Agents |  |
| AI Agents with Memory |  |
| Repetitive Agents |  |
| Introduction |  |
| Tools Overview |  |
| Custom Tools |  |
| Firecrawl Integration |  |
| User Interface |  |
| Crawl4AI Integration |  |
| Chat Interface |  |
| Code Interface |  |
| Mem0 Integration |  |
| Training |  |
| Realtime Voice Interface |  |
| Call Interface |  |
| Reasoning Extract Agents |  |
We welcome contributions! Fork the repo, create a branch, and submit a PR → Contributing Guide.
Show FAQ and troubleshooting
ModuleNotFoundError: No module named 'praisonaiagents'
Install the package:
pip install praisonaiagentsAPI key not found / Authentication error
Ensure your API key is set:
export OPENAI_API_KEY=your_key_hereFor other providers, see Models docs.
How do I use a local model (Ollama)?
# Start Ollama and pull a model
ollama serve
ollama pull llama3.2from praisonaiagents import Agent
agent = Agent(instructions="You are a helpful assistant", llm="ollama/llama3.2")
agent.start("Why is the sky blue?")The ollama/ prefix is what selects Ollama's handling — tool-call repair,
tool-result formatting and the streaming rules small local models need. Or set
it by environment instead:
export OPENAI_MODEL_NAME=ollama/llama3.2Setting only OPENAI_BASE_URL is not enough: with no model named, the OpenAI
default (gpt-4o-mini) is sent to Ollama, which answers
404 model 'gpt-4o-mini' not found. Always name the model.
Point at a non-default host with base_url= or OLLAMA_HOST:
agent = Agent(instructions="...", llm="ollama/llama3.2", base_url="http://192.168.1.10:11434")The same shape works for other local runtimes — lm_studio/, vllm/ and
hosted_vllm/ with their server's base_url.
See Models docs for more details.
How do I persist conversations to a database?
Use the db parameter:
from praisonaiagents import Agent, db
agent = Agent(
name="Assistant",
memory={
"db": db(database_url="postgresql://localhost/mydb"),
"session_id": "my-session",
},
)See Persistence docs for supported databases.
How do I enable agent memory?
from praisonaiagents import Agent
agent = Agent(
name="Assistant",
# Enables file-based memory (no extra deps!)
memory={"user_id": "user123"},
)See Memory docs for more options.
How do I run multiple agents together?
from praisonaiagents import Agent, Agents
agent1 = Agent(instructions="Research topics")
agent2 = Agent(instructions="Summarize findings")
agents = Agents(agents=[agent1, agent2])
agents.start()See Agents docs for more examples.
How do I use MCP tools?
from praisonaiagents import Agent, MCP
agent = Agent(
tools=MCP("npx @modelcontextprotocol/server-memory")
)See MCP docs for all transport options.
Made with ❤️ by the PraisonAI Team
📚 Documentation •
GitHub •
