parlant
Build reliable customer-facing AI agents with Parlant: an interaction control harness optimized for controlled, consistent, and predictable LLM interactions.
GraphCanon updated 1d · GitHub synced 1d · 30 views this month
Decision brief
Parlant is a specialized interaction control harness designed to ensure that AI agents, particularly those in customer service roles, behave predictably and align with predefined rules.
Good fit when
- When you need precise control over the actions of AI agents based on specific conditions or observations.
- For scenarios where responses must adapt to user behavior, such as distinguishing between technical experts and beginners among customers.
Avoid when
- When the requirements for agent interactions do not demand granular rules based on observable user behavior or conditions, making this level of control unnecessary.
- In cases where the flexibility and spontaneous responses from general-purpose LLMs are preferred without being restricted by controlled guidelines.
- Pricing:
- freemium - The open-source version offers community-supported functionalities which are free to use but might lack advanced support services.
Observed Jul 11, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Steady (38d since push)
- As of 1d
- Provenance
- Not a fork · Organization account
- As of 1d
- Security (OSV)
- 2 low (2 low)
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install parlant PyPIHow it fits your stack(12)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Alternative
Integrates
Related
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
Parlant is a tool designed to create and manage AI agents for customer service purposes. It allows developers to define conditions under which specific agent actions are triggered or excluded, ensuring that responses are appropriate and in line with predefined guidelines.
Capability facts
- CLI
- CLI entrypoint
Source: pyproject.toml:[project.scripts] · Aug 20, 2026
- Languages
- python
Source: github.language+pyproject.toml · Aug 20, 2026
Categories
Graph entities
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Aug 20, 2026)
```python import parlant.sdk as pSource link
Tags
README
Getting started
pip install parlant
import parlant.sdk as p
async with p.Server():
agent = await server.create_agent(
name="Customer Support",
description="Handles customer inquiries for an airline",
)
# Evaluate and call tools only under the right conditions
expert_customer = await agent.create_observation(
condition="customer uses financial terminology like DTI or amortization",
tools=[research_deep_answer],
)
# When the expert observation holds, always respond
# with depth. Set the guideline to automatically match
# whenever the observation it depends on holds...
expert_answers = await agent.create_guideline(
matcher=p.MATCH_ALWAYS,
action="respond with technical depth",
dependencies=[expert_customer],
)
beginner_answers = await agent.create_guideline(
condition="customer seems new to the topic",
action="simplify and use concrete examples",
)
# When both match, beginners wins. Neither expert-level
# tool-data nor instructions can enter the agent's context.
await beginner_answers.exclude(expert_customer)
Follow the 5-minute quickstart for a full walkthrough.
License
Apache 2.0 — free for commercial use.
Try it now • Join Discord • Read the docs
Built by the team at Emcie
For agents
This page has a .md twin and JSON over the API.