#2626th of 48 in Agent frameworks and SDKs
parlant
Python framework for controlling behavior of customer-facing conversational agents
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 18.3k
- License
- Apache-2.0
- Last commit
- Jul 2026
- Last release
- Apr 2026
- Language
- Python
Missed the latest GitHub check; these facts may be older.
Overview
Parlant is a Python SDK where agent behavior is defined as guidelines, observations, journeys, glossary terms and tools instead of one large system prompt. On each turn its engine matches only the relevant rules and tools and builds a narrowed context before generating a reply. It also supports canned-response templates for strict output and OpenTelemetry tracing of every match.
Who it is for: Teams building compliant, customer-facing conversational agents in Python
Strengths
- Per-turn matching keeps only relevant guidelines and tools in the LLM context
- Strict mode with canned responses gives exact, pre-approved wording at critical moments
- OpenTelemetry tracing logs guideline matches and decisions for auditing
- External workflows (LangGraph, LlamaIndex, Agno) can be wrapped as tools
Weaknesses
- README says small off-the-shelf models tend to give inconsistent results
- Extra matching step per turn; latency and token cost are not documented
- Not a workflow builder; README points to LangGraph for workflow automation
- Recommended Emcie models are a vendor-specific service; pricing is unknown
What it needs
- no GPU
- Needs LLM provider (Emcie, OpenAI, Anthropic or LiteLLM)
- Models: Emcie, OpenAI, Anthropic, LiteLLM
Also in Agent frameworks and SDKs
See all 48| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 93 out of 100 |
| 2 | browser-usePython library that lets an LLM agent control a web browser | 89 out of 100 |
| 3 | langchainPython framework for building LLM agents and apps from interoperable components | 88 out of 100 |
| #4 | tradingagentsLangGraph multi-agent framework simulating a trading firm to analyze tickers | 88 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 87 out of 100 |