Trefle MCP — global plant database (1M+ species)

MCP server that estimates the dollar cost of LLM API calls and workflows from token counts, using ComparEdge's verified per-1M-token prices for 60+ models across 16+ providers.

Searchable React picker over every OpenRouter model, with live USD-per-1M-token prices, vendor filter, sorting and keyboard navigation. No Tailwind or state library required.

Pricing-aware model picker for pi: select models with per-1M-token cost, context window, cache rates, tiers and reasoning support. Sort models by input/output/total cost with ctrl+s.

MCP server for NVIDIA Nemotron-Personas-USA — 1M American personas, callable from Claude Code

SQLite adapter for @kgensearch — file-based persistence, 10K–1M records

Generate realistic test-data from your Zod-Schemas

Tiny millisecond conversion utility

Extension for the pi coding agent: enforce a context token budget (default 200k) by forcing compaction, including mid-turn during long tool loops, instead of riding long-context models up to 1M.

High-performance, type-safe RPC library for TypeScript/JavaScript. Transport-agnostic with exceptional throughput (1M+ ops/sec).

Format very large numbers in several human-readable ways. `format(1e6)` -> `"1 million"` or `"1M"`

WebGL2 chart companion to @zakkster/lite-charts. GPU-projected data series for the 100k-1M point range; sibling model, config-parity with lite-charts.

 

Tiny columnar SQL engine for browser faceting — Rust/wasm, ~240KB gz, zero dependencies. Open Parquet or CSV instantly, facet 1M rows in milliseconds, persist to OPFS; one install gives the library and the `facetful` command.

Get the visual width of the widest line in a string - the number of columns required to display it

Vercel AI SDK provider for CoralBricks — GLM and Kimi open models with up to 1M context, free cached input.

 

OpenCode plugin to add long-context Claude and GPT-5 variants via GitHub Copilot

reformat a dtrace(1M) one-liner into a script