SillyTavern project
Official sources for SillyTavern, a community open-source LLM frontend for original character dialogue. Both original native 1.19.0 cases executed once with Qwen2.5-Coder-1.5B-Instruct Q4_K_M and failed; eight of twelve conditions passed and four failed. Current legal operator, employee count and controlling ownership remain unknown.
Official documentation describes SillyTavern as a passion project maintained by a community of LLM enthusiasts, with independent development since its February 2023 TavernAI fork. Developer contacts cohee, rossascends and wolfsblvt identify maintainer roles; these do not certify legal incorporation, current employee count or controlling ownership. This page groups its supervised character-writing profile and retained official sources. On 2026-10-03, both original Mara cases completed once through the full official 1.19.0 Node server and browser UI with the cached Qwen2.5-Coder-1.5B-Instruct Q4_K_M model. Both failed: primary kept canon but exceeded the word limit and omitted Writer review; boundary retained two unknowns but omitted conflict explanation and all required canon facts. Eight conditions passed, four failed and none remained unverified. First responses and server-created JSONL chats were retained with zero quality reruns. Results cover this local configuration only; World Info, embedding, extensions, tools, cloud models, native export downloads and publication were outside this pilot.
SillyTavern is a free, open-source local LLM frontend maintained as a community passion project. A fiction writer, independent game designer or creator can define an original character, keep its voice and story facts in a character card, then draft dialogue through a separately chosen model. The full browser interface also documents World Info lore, user personas and group conversations. Official docs describe independent development since a February 2023 TavernAI fork and name developer contacts; this does not establish a company employee count, legal operator or controlling ownership. Two original character-chat cases executed once through the complete official 1.19.0 Node server and browser UI at commit 7e8663cd9c184a550b37238218bdd32c6efc68e9 with the cached Qwen2.5-Coder-1.5B-Instruct Q4_K_M model. Both failed: the welcome dialogue kept canon but exceeded its word limit and omitted Writer review; the boundary reply retained two unknowns but omitted conflict explanation and canon. Eight of twelve conditions passed and four failed. These results evaluate only this recorded local configuration. World Info, embeddings, extensions, tools and cloud models are outside the two cases.