Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

TFT-Copilot

Open-source AI agent coach for Teamfight Tactics (TFT): comp planning, augment picks, roll-or-save, and positioning advice, with local screenshot-based board recognition (ONNX vision models) and deterministic trait-verification tools. 云顶之弈(TFT)开源 Agent 教练:定阵容、选海克斯、D牌决策、站位建议,支持本地截图自动识别局面(ONNX 视觉模型)及确定性羁绊核验工具。

Details

External ID
1374824920
Source
GITHUB
Company
—
Product
TFT-Copilot
Website domain
github.com
Launched
Sept. 17, 2026
Cohort
—
Upvotes
11
Upvotes percentile
0.33858570330514987
Tags
—
Fetched at
Sept. 21, 2026, 5:03 p.m.
Updated at
Sept. 21, 2026, 5:03 p.m.

Enrichment

Theme
autonomous agent research and evaluation
Vertical
Media & entertainment
Function
Agent / copilot
Audience
B2C
AI stance
AI-native
Project type
Hobby / open-source project
Normalized one-liner
ai coach for teamfight tactics players
Manually corrected
False

Could you build this?

Partial Building the UI and rule engine is straightforward, but training and deploying local ONNX computer vision models to accurately recognize TFT board elements across resolutions is non-trivial.

What it would actually take: Architecture requires an Electron or Python desktop app with an ONNX Runtime pipeline capturing screen frames. The complex part involves collecting and labeling an extensive dataset of in-game TFT icons, champions, and items under diverse resolutions, aspect ratios, and visual effects, followed by training robust object detection/classification models.

Competitors

Other products that read as similar to this one — 233 launches clear the similarity bar, closest 8 shown.

Attention rank: #122 of 234 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 317 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a agent / copilot tool for Agriculture yet.