DeepSeek Harness web plugin that displays cache-hit rate with two decimal places

opencode TUI sidebar panel with prompt cache hit rate and per-category cost for the current session

OpenCode TUI plugin displaying real-time token cache hit rate in the sidebar

Live OpenCode V2 session telemetry — agent, model, branch, cost, tokens, cache hit rate and context usage in your sidebar.

Pi Agent extension that maximizes prompt-cache hit rate and reduces token cost

OpenCode TUI sidebar: prompt cache hit rate, tokens & cost with sub-agent rollup. Works with opencode-visual-cache; optional per-call JSONL timeline.

[Deprecated] Show cumulative session cache hit rate in pi footer

Compact two-line status footer for pi: model, tokens, cache hit rate, context usage, cost, run timer, agent loop count and current task.

Lightweight colored statusline for the pi coding agent: official-style layout, icons, live tok/s, cache-hit rate, and optional AI working vibes

DSH web plugin: a real-time dashboard tab for the current conversation — token usage, cache hit rate, message-role distribution, and timing breakdowns, visualized.

Cost transparency status line for Pi: full-detail token and cost breakdown (input/output/cache), cache hit rate, context usage, model, and thinking level.

Codex-style context visibility for DeepSeek Harness: live context-window occupancy, composition breakdown, KV-cache hit rate, and a GitHub-style 53-week usage heatmap

pi extension: scriptable peak/off-peak tier rules per provider with an enhanced footer (tier label, cache-hit-rate precision, custom currency symbol)

Track token usage, cost and cache hit rate of AI coding agents (ZCode, Claude Code, Codex, OpenCode, Kimi Code) from your terminal.

opencode plugin — live cache hit rate widget in the TUI sidebar + per-session JSONL stats log

OpenCode TUI plugin: a /context command with the exact token breakdown behind the built-in Context panel (last request) plus session-wide usage, subagent totals, cache hit rate and cost.

Enhanced ACP server for DeepSeek Harness: block-level streaming, usage/stat telemetry (cache hit rate, token speed, input/output tokens, context length, turns, tool timing), model & reasoning-effort switching, and permission-preset control over the ACP wi

Per-model token usage and cache hit rate from local Claude Code transcripts — the tokens-report CLI behind the tokens plugin.

Compact two-line status footer for pi: model, thinking level, tokens, TPS, cache hit rate, context usage, live git diff, and working/turn timers.

DSH web plugin: a usage statistics panel with per-day token trend, GitHub-style activity heatmap, cache hit-rate curve and per-model / per-provider breakdowns, replicating the reasonix usage stats feature.