Explainable backend flows — automatic causal traces, decision evidence, and MCP tool generation for AI agents

The explainable agent framework — backtrack a wrong answer to the exact context that caused it (evidence, not guesses). Built on footprintjs.

Turn a web app's interaction surface into a typed, traversable journey graph an LLM can plan over — the frontend sibling of footprintjs.

See through your agent's decisions. React components for debugging agentfootprint runs — messages, prompts, tool calls, decision scope, cost.

Framework-agnostic player that replays an agent's runtime footprint (a recorded trace) as an animated, scrubbable story — the LLM brain calling tools and getting back data (reason), an instruction (act), or both.

Themeable React components for visualizing FootPrint pipeline execution

footprint 埋点 SDK 核心：页面任务、事件上报、公共参数

footprint 埋点 SDK Vue3 适配：useTrackTask + v-log 指令

footprint 埋点 SDK Vue2 适配：路由 mixin + v-log 指令

footprint 埋点 SDK 通用指令层：v-log 点击/曝光指令

footprint 埋点 SDK React 适配：useTrackTask Hook

Deterministic CO2 and energy impact calculator for AI inference calls

Teaching films from a storyboard and a recipe: every drawing tied to a spoken phrase, one seekable timeline, pixel-pinned frames, director notes, a local preview studio, and a making-of record for every film.

One component that shows a recorded agent run: Story, Why, Flow, Skill Graph and Data tabs on one shared cursor. You declare what you want to see — or pass nothing and the viewer reads the recording and decides. It wires everything correctly, or refuses i