SillyTavern
ATH Infosystems · Software Development
Certification per Microsoft Marketplace.
Evidence tier Source Confirmed · 2 captures on record
What the publisher says
As described on Microsoft Marketplace.
SillyTavern is an open-source LLM front-end and chat interface designed for interacting with AI models such as OpenAI, Claude, Gemini, OpenRouter, Ollama, KoboldCpp, Text Generation WebUI, and other compatible backends. It provides a highly customizable chat experience with support for character cards, group chats, personas, extensions, text-to-speech, speech recognition, and advanced prompt management. SillyTavern can be self-hosted on virtual machines, containers, or local systems, making it ideal for AI enthusiasts, developers, researchers, and enterprise AI deployments.
Key Features of SillyTavern:
Show the rest of the publisher’s description (33 more lines)
- Open-source AI chat interface with support for multiple LLM providers and local AI models.
- Compatible with OpenAI, Anthropic Claude, Google Gemini, OpenRouter, Ollama, KoboldCpp, and other backends.
- Advanced character cards and roleplay-focused conversation management.
- Supports group chats, personas, system prompts, and memory management.
- Customizable user interface with themes, extensions, and plugins.
- Built-in support for Text-to-Speech (TTS) and Speech-to-Text (STT) integrations.
- Remote access support through web browsers and reverse proxy configurations.
- Chat history management with import, export, and backup capabilities.
- User authentication, IP whitelisting, and security controls for internet-facing deployments.
- Suitable for AI assistants, chatbots, research environments, content creation, and LLM testing workflows.
- Deployable on Ubuntu, Docker, Azure Virtual Machines, Kubernetes, and other cloud platforms.
SillyTavern Usage:
$ sudo su
# Check SillyTavern Version
$ grep '"version"' package.json
# Start with Remote Access
$ ./start.sh --listen
# Verify Service is Running
$ ps aux | grep server.js
# Verify Listening Port
$ ss -tulpn | grep 8000
# Check Configuration
$ grep -E "listen|whitelistMode|basicAuthMode|enableUserAccounts" config.yaml
# Monitor Access Logs
$ tail -f data/access.log
# Access SillyTavern Locally
http://127.0.0.1:8000
# Access SillyTavern Remotely
http://SERVER_IP:8000
# Get Login Credentials:
$ cat/var/sillytavern/credentials.txt
Disclaimer:
SillyTavern is an open-source project developed and maintained by the SillyTavern open-source community and contributors. SillyTavern and related trademarks belong to their respective owners. This software is not affiliated with, endorsed by, or sponsored by any AI model provider, cloud platform, operating system vendor, or third-party service mentioned for compatibility, integration, or deployment purposes.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment · as of 2026-08-29
Reconciled on 9/3/2026
Sources
Publisher resources
1 linkLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.

