Skip to content
Agents tracked: 484 Releases (7d): 690 Agent status: 2 with issuesSince last limit reset: Claude 7d · Codex 5d For AI agents: Markdown Updated Nov 18, 2026

Parlant by Emcie

Open-source (Apache-2.0) Python framework for customer-facing chat agents: you describe policies and behaviour (or have a coding agent write them), and its engine keeps the agent on those rules in every conversation, with any model you choose. An optional hosted Dashboard adds session monitoring, simulated test personas and managed hosting.

Customer support AI agents New · Added to AgentGid on Nov 3, 2026Framework for customer-facing chat agentsOpen source · Apache-2.0Free to start

Use it in: API / SDK Web app

Price
Free + $79/mo
free tier available
Popularity
#17 in Support
Gid Score 21 / 100 · #219 of 245 ranked AI agents
Trend
—
about +2 GitHub stars a day
Development
Actively updated
latest 4.0.6, 2d ago
Community
18.3K GitHub stars
public signals

Usage data: latest readings Nov 17 to Nov 18, 2026, last checked Nov 18, 06:37 UTC. Date of each number

What Parlant does

Parlant is a framework for customer-facing chat agents from Emcie, first released in February 2024. You use it through a Python library and a web app. Paid plans start at $79 a month; there is a free tier.

Key facts

MakerEmcie
TypeFramework for customer-facing chat agents
First releasedFebruary 2024
LicenseApache-2.0
InterfacesPython library, Web app
Main languagePython
Open issues and PRs15

Pricing

The framework is open source and you pay your model provider directly. Dashboard: Starter free (development only, 1 local project), Basic $79/month (1 live project), Plus $349/month (5 seats, 3 live projects); yearly billing gives 2 months free.

Checked Nov 3, 2026. Prices change often; confirm before you buy.

Compare prices of all agents

Quick answers

  • Free to start?Yes
  • Open source?Yes (Apache-2.0)
  • Where you use itPython library, Web app
  • Closest alternativeRasa · all alternatives

AgentGid articles about Parlant

All guides

Compare Parlant with another agent

vs
# Agent Gid Score Downloads 7d 7d 30d Stars Latest release Price
35
RasaRasa
52 42.5K down 4.3% down 31.2% 21.4K+2/day 3.6.2122mo ago Free
46
ChatbaseChatbase
482/4 683 up 1,038% up 52.0% — — $150/mo
53 46 — — — 40.1K+69/day 4.19.125d ago Free + $19/mo
59
BotpressBotpress
45 28.1K down 23.4% up 9.9% 15K+2/day 12.30.93y ago Free + $150/mo yearly
63
InkeepInkeep
44 170K up 8.9% up 131.3% 1,501 0.68.47mo ago Free
85
DecagonDecagon
40 — — — — — Custom

Ratings from people who use Parlant

No ratings yet. Used Parlant? Rate it and say what it is good and bad at.

Parlant news

All AI agent news

  1. Release GitHub Releases

    Parlant 4.0.6 released

    parlant lint lints a Parlant agent project through your coding agent. It; parlant init now installs a git pre-push hook (.githooks/pre-push, set; parlant dashboard agent cards AGENT_ID DESTINATION writes every file your

  2. Release GitHub Releases

    Parlant 4.0.5 released

    Gemini 4 Hydrogen works through the Gemini provider, including streamed replies,; The chat widget shows Markdown tables in an agent's reply as tables. They; Event streams (sse=true) now carry an id on every frame and resume from

What changed: recent Parlant releases

4 stable releases in the last 90 days · Full changelog

4.0.6
  • parlant lint lints a Parlant agent project through your coding agent. It
  • parlant init now installs a git pre-push hook (.githooks/pre-push, set
  • parlant dashboard agent cards AGENT_ID DESTINATION writes every file your
  • The chat widget's onPathChanged(path, notifyAgent) tells the agent which page
  • At high agent effort, pruning previously discovered rules now defaults to
  • When one policy entails another, the entailed policy is now judged with the
4.0.5
  • Gemini 4 Hydrogen works through the Gemini provider, including streamed replies,
  • The chat widget shows Markdown tables in an agent's reply as tables. They
  • Event streams (sse=true) now carry an id on every frame and resume from
  • Gemini serves Google's Gemini Decision 1 (gemini-decision-1), which answers
  • Gemini models count tokens on your server instead of asking the Gemini API,
  • Agents no longer repeat what the customer just said back to them before
Earlier releases
4.0.4
  • Agent.queue_response() combines background follow-ups with other ready results or a customer turn. Pass after=coroutine to register work before it starts.
  • When tool preambles are encouraged, the agent writes them, and the progress updates that follow, in the customer's language.
  • Agents acknowledge recurring information gaps when different questions cannot be answered, without treating a new question as one already answered.
  • Agents ask which record or request the customer means when it's ambiguous, and which of several unfinished requests to handle first, before collecting task details.
  • Gemini conversations can resume from background results after history is cleared, without an invalid tool-response ordering error.
  • The Parlant dashboard now shows your agent's reasoning under Agent activity when the agent streams its messages, the default for create_agent.
4.0.2
  • The chat widget lets the AI agent in a visitor's browser talk to your agent
  • Server(session_store=..., customer_store=...) accepts an s3://bucket
  • The chat widget (parlant widget init) takes the agent's picture in one
  • The chat widget's persistent suggestions stand out from its opening ones
  • On phones and tablets, the chat widget closes the on-screen keyboard once a
  • With the LiteLLM provider, review routes now default to
3.3.2
  • Add PARLANT_TOOL_CALL_TIMEOUT environment variable to control the plugin tool-call timeout
  • Include guideline description (in addition to the condition) in matcher prompts
  • Render active journeys' descriptions in the canned response draft prompt
  • Improve error messages surfaced by EmcieService to be more diagnostic
  • Relax the aiopenapi3 pin to >=0.8.1,<0.9.0
  • Fix redundant batch creation in ToolCaller across guideline matches, which in some agents caused a lot of latency unnecessarily
3.3.1
  • Allow passing ToolId when attaching tools throughout the SDK
  • Add AnyOf(tag) and AllOf(tag) modifiers for explicit control over tag dependency semantics in depend_on() — AnyOf requires at least one tagged member to be active, AllOf requires all of them…
  • Add depend_on_any() to Guideline, Tag, and Journey for OR dependency relationships — at least one target must be active.
  • Add event loop health monitoring to /healthz endpoint — measures callback latency and reports healthy, degraded, or unhealthy status with peak latency over a configurable window
  • Add resolution tracking to the relational resolver — every entity that enters resolution gets a Resolution with a ResolutionKind…
  • Split RelationshipEntityKind.TAG into TAG_ALL and TAG_ANY to support explicit tag dependency semantics at the core level (existing TAG entries treated as TAG_ALL for backwards compatibility)

Parlant popularity and usage data

The GitHub repository has 18.3K stars, 65 of them added in the last 30 days. The latest stable release is 4.0.6, published Nov 16, 2026; there were 4 stable releases in the past 30 days.

GitHub starsrunning total 18.3K
Website rankTranco list; a lower rank means more traffic #4,310,566

Download the raw daily series: parlant.csv

Gid Score breakdown

Adoption0
Community53
Attention—
Momentum50

Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.

How fresh these numbers are

NumberLatest readingLast checked
GitHub starsNov 18, 2026Nov 18, 06:30 UTC
Website rank (Tranco)Nov 17, 2026Nov 18, 06:37 UTC

We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.

Parlant FAQ

How much does Parlant cost?

The framework is open source and you pay your model provider directly. Dashboard: Starter free (development only, 1 local project), Basic $79/month (1 live project), Plus $349/month (5 seats, 3 live projects); yearly billing gives 2 months free.

Is Parlant open source?

Yes. Parlant is open source, released under the Apache-2.0 license.

How popular is Parlant?

The GitHub repository has 18.3K stars, 65 of them added in the last 30 days. The latest stable release is 4.0.6, published Nov 16, 2026; there were 4 stable releases in the past 30 days.

What is the latest version of Parlant?

The latest stable release we track is 4.0.6, published on Nov 16, 2026.

What are the alternatives to Parlant?

The closest alternatives in the same category by Gid Score are Rasa, Chatbase, Chatwoot Captain, Botpress.

For the makers of Parlant badges, corrections

Add a live badge to your README or site:

AgentGid: #17 in Support Gid Score: 21/100

[![AgentGid: #17 in Support](https://agentgid.com/badges/parlant-rank.svg)](https://agentgid.com/agents/parlant/)
[![Gid Score: 21/100](https://agentgid.com/badges/parlant-score.svg)](https://agentgid.com/agents/parlant/)

Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.

Where these numbers come from

GitHub: emcie-co/parlant. Site rank: parlant.io on the Tranco list. See data sources for how each one is collected.

Product facts and pricing were checked against: parlant.io, github.com.